Artificial Intelligence · Cross-listed from cs.RO
When World Models Lie: Adaptive Safety Analysis Under Wrong Imaginations
John Cao and Somil Bansal
World models offer a powerful substrate for safety
reasoning in high-dimensional robotic systems, but they are also fallible: their predictions can be biased, miscalibrated, or confidently wrong. This creates a central challenge for latent-space safety filters, which often learn Hamilton-Jacobi safety value functions on the dynamics of a world model. If the world model is incorrect, the resulting value function can inherit its errors and produce overconfident safety estimates. Existing latent safety filters often rely on auxiliary signals such as ensemble disagreement or value-target consistency residuals for adaptation, but these signals can remain small even when the world model's predictions deviate from observations. We propose an adaptive latent safety filter that calibrates safety
reasoning using directly observed world-model error. Our method uses Adaptive Conformal Inference to construct online uncertainty sets from discrepancies between predicted and observation-inferred latent states, then evaluates safety pessimistically by minimizing the learned value function over these sets. This allows the filter to remain minimally conservative when the world model is accurate, while becoming more cautious when observations reveal model mismatch. We provide a finite-time coverage guarantee for the adaptive uncertainty radius. Through simulation and hardware experiments, we show that our method significantly reduces failures relative to state-of-the-art latent safety filters while preserving task completion.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Dr.Credit: Rubric-Grounded Process Credit Assignment for Deep Research Agents
Yingjian Zhu, Zhenyi Wang, Jiaxin Guo et al. (+6 more)
Rubric-based tasks are increasingly addressed through reinforcement learning (RL), with rubric scores used as training rewards. However, these rewards typically supervise final answers without distinguishing the contributions of intermediate decisions. Many existing credit assignment methods rely on ground-truth answers to define process rewards, limiting their applicability to open-ended tasks without canonical solutions. To address this limitation, the proposed rubric-grounded credit uses task requirements as a shared reference for final answer evaluation and process supervision. The information returned by tools is assessed for the additional support it provides toward satisfying each rubric relative to that rubric's history of accepted support. By referencing these histories, credit distinguishes new support from evidence already present in the trajectory while recognizing partial support for each rubric. Dr.Credit uses rubric-grounded credit to supervise intermediate tool turns in an RL framework for deep research
agents. The resulting process advantages are combined with GRPO outcome advantages to guide research decisions while retaining supervision of final-report quality. Evaluations on four in-domain and out-of-domain
benchmarks show that Dr.Credit outperforms the evaluated open deep research baselines on every primary metric and submetric. Meanwhile, with an 8B-parameter backbone, the trained
agent achieves average performance competitive with the evaluated frontier proprietary models. Further analyses suggest more efficient evidence acquisition and higher-quality reports under limited research-turn budgets, motivating the extension of rubric-grounded process supervision to a broader range of rubric-based tasks.
Read the full abstract ▾
All authors Yingjian Zhu, Zhenyi Wang, Jiaxin Guo, Kun Ding, Ying Wang, Shen Huang, Xunjie Zhu, Pengjun Xie, Shiming Xiang
Artificial Intelligence · Cross-listed from cs.CL
ReScraper: Unified Scraping and Cleaning of Web Data for Effective LLM Pretraining
Zichun Yu, Jiarui Yan, Shlok Sanghvi et al. (+2 more)
LLM pretraining corpora are normally cleaned by a stack of hand-written heuristics. A heuristic scraper extracts the main content from HTML, and dozens of rule-based filters then clean it, so corpus quality is capped by the coarseness and accuracy of the rules. In this work, we propose ReScraper, a unified
language model of only 0.6B parameters that replaces this entire stack. To train ReScraper, we carefully curate supervised data from the outputs of three teacher models, so it learns to first extract the main content from raw data and then choose among four operations: keeping the page as extracted, editing out noisy lines and spans, deleting it entirely, or rewriting it when it is poorly written but informative. Based on the same crawled data pool, pretraining 400M, 1.4B, and 2.8B models on our curated data improves the DCLM Core score by a relative 3.8–4.7% over the strongest baseline at each scale, including the costly multi-
agent curation. Our analyses show that each operation plays a distinct and complementary role, and that extracting and cleaning in one model outperforms a cascade of separate models. ReScraper also concentrates its operations on the pages that need them, raising the quality of poor pages the most while keeping the corpus diverse. These results demonstrate the feasibility and effectiveness of AI4AI for pretraining data curation, where a small learned model takes over an entire stage of the pipeline from hand-written heuristics. We open-source our code at https://github.com/cxcscmu/ReScraper
Read the full abstract ▾
All authors Zichun Yu, Jiarui Yan, Shlok Sanghvi, Nihar Atri, Chenyan Xiong
Artificial Intelligence
MoSPR: Histology-to-Gene Expression Prediction with Morpho-Spatial Macrostates and Low-Rank Molecular Programs
Dongmyung Shin, Geongyu Lee, Yesung Cho et al. (+1 more)
Predicting molecular profiles from histopathology remains challenging because whole-slide images contain spatially organized, heterogeneous tissue patterns, while gene expression comprises thousands of correlated targets. We introduce MoSPR (Morpho-Spatial Program Regression), a linear framework that couples an adjacency-informed histology representation with a low-rank molecular basis. MoSPR clusters frozen patch
embeddings into morphology microstates, aggregates their spatial adjacencies across the training cohort, and groups microstates with similar adjacency patterns into shared macrostates. Each slide is then represented by global morphology and macrostate-specific deviations, which are linearly mapped to coefficients of a training-derived low-rank gene-expression basis. Across three cancer cohorts from The Cancer Genome Atlas, MoSPR achieves the highest mean gene-expression prediction scores among all evaluated methods. Without pathway-level supervision, pathway scores derived from its predicted expression profiles rank first in eight of nine comparisons across three pathway collections. Ablation studies on the breast cancer cohort show complementary gains from adjacency-derived macrostate representation and low-rank molecular prediction. Moreover, with half of the training data on this cohort, MoSPR exceeds the full-data gene-prediction score of the strongest competing baseline. Finally, its linear formulation enables exact decomposition of each predicted expression profile into global and macrostate-specific molecular contributions, providing an interpretable link between spatially coherent macrostate regions and their associated molecular programs. Our code is available at https://github.com/Radisen-Panthera/MoSPR.
Read the full abstract ▾
All authors Dongmyung Shin, Geongyu Lee, Yesung Cho, Park Jong Bae
Artificial Intelligence · Cross-listed from cs.LG
Direct Self-Evolving Optimization: Evolving LLMs without Challenger Training
Yuyang Deng, Yu Wang and Jiayun Wang
Self-evolving
language models improve by generating tasks and learning from their own feedback, but adapting the task generator often requires a separate challenger-training loop. Can we generate tasks adapted to the current solver without explicitly training a challenger? We introduce Direct Self-Evolving Optimization (DEO), which replaces challenger parameter updates with solver-guided task sampling. The KL-regularized challenger objective defines an exponential tilt of a fixed base task distribution. DEO uses this distribution as a sampling target: a frozen LLM generates and mutates tasks, the solver scores them, and an approximate Metropolis selection rule refines the training pool. Only the solver is trained. Theoretically, for an idealized variant that samples exactly from the tilted distribution, and under regularity, local gradient-dominance, and initialization conditions, we show that DEO learns distributionally robust
reasoning ability. In experiments, DEO achieves
reasoning performance competitive with R-Zero while using over $50\%$ less wall-clock training time, and improves
reasoning accuracy over a no-walk ablation. Replacing the task generator with a frozen API-only LLM further improves the local solver, illustrating a capability enabled by removing challenger training.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
See, Measure, and Reason: Learning Visually Grounded Reasoning in Pathology
Chengyang Zhang, Wenchuan Zhang, Bo Li et al. (+8 more)
Pathological assessment relies on recognizing fine-grained visual details in histological images.
Vision-
language models (VLMs) increasingly support pathology interpretation, yet their ability to perceive these details remains inadequate. This weakness leads to inaccurate cellular observations that can persist even when final answers are correct. In this paper, we propose ASPECT to improve visually grounded
reasoning through explicit supervision of cellular appearance and abundance. ASPECT trains intermediate visual
tokens through pathology feature reconstruction,
cell feature
alignment, and count supervision. Three-stage supervised fine-tuning teaches the model to perceive, generate visual
tokens, and reason, followed by reinforcement learning that rewards answer correctness and consistency with reported measurements. We also introduce PathoVernier, a
benchmark of 759 expert-reviewed questions from five pathology
datasets covering four cellular composition tasks. It evaluates both final answers and intermediate measurements to expose errors hidden by answer accuracy. On PathoVernier, ASPECT achieves relative accuracy gains of approximately 19.2% over the strongest baseline, Gemini-3.1-Pro, and 99.3% over its Qwen3-VL-8B backbone, while reducing RAWR, which measures counting errors within correct responses, by 28.1% and 42.7%, respectively. ASPECT also improves over its backbone on three external pathology
benchmarks covering classification and question answering beyond cellular composition tasks.
Read the full abstract ▾
All authors Chengyang Zhang, Wenchuan Zhang, Bo Li, Mengran Li, Xinyu Liu, Jiaming Yang, Jie Chen, Zhang Zhang, Yuhao Yi, Hong Bu, Jiancheng Lv
Artificial Intelligence
BIABench: Evaluating AI agents on real-world bioimage analysis tasks
Zixuan Pan, Davide Panzeri, Lukas Johanns et al. (+5 more)
Artificial-intelligence (AI)
agents hold promise for automating bioimage analysis, yet no
benchmark evaluates whether they can carry out real-world analyses end to end. Such analyses are hard for
agents because 2D images, 3D volumes and time-lapse sequences are often too large to read as context, so an
agent must choose and run an analysis through code, specialized software and rendered views. Published studies make this capability testable, because each pairs raw images with a peer-reviewed result. We introduce BIABench, a
benchmark of 16 tasks reconstructed from published biological studies that retain their scientific questions, imaging data and ground truth. The tasks span eleven analysis subtasks and modalities from H&E histology to single-molecule localization microscopy. Each submission receives an outcome score, which compares the output files with the ground truth using field-standard metrics, and a process score, in which a
vision-
language model judges method choice and quality control against an expert-written rubric. We evaluated general-purpose and biology-specific
agents across several
language models, with repeated runs of every task. Routine two-dimensional tasks were solved well, but on some tasks that added a third dimension or a time axis no
agent scored above 0.19. Neither biological specialization, stronger models nor detailed expert instructions closed this gap. The
agents were also unreliable, with scores varying more between repeated runs of one
agent than between different
agents, and without ground truth a correct run could not be told from a wrong one by its process score or by the time spent. Released openly with its data and code, BIABench provides a verifiable framework for evaluating, and eventually training,
agents for reliable long-horizon bioimage analysis.
Read the full abstract ▾
All authors Zixuan Pan, Davide Panzeri, Lukas Johanns, Marilin Moor, Yu Zhou, Hedi Peterson, Yiyu Shi, Jianxu Chen
Artificial Intelligence
Query Expansion and Key Specialization in Transformer Attention Geometry
Vidit Gupta, Siddhesh Nadkarni, Mihik Chaudhari et al. (+2 more)
The projection of queries and keys are central to the
attention mechanism in
Transformer architectures. While they are mathematically symmetric, they play different roles in
attention mechanisms. The question of whether there is an effect from their functional distinction on their
geometric development in training remains unanswered. We investigate the problem through the training of small GPT-like
Transformers on character-level WikiText-103 for three different depths (4, 6, and 8 layers), three types of initialization for queries and keys, and four random seeds, resulting in 36 runs and 54 trajectories of average layers across seeds. We track the effective dimensionality of those layers using participation ratios and discover that effective dimension of queries expand while keys shrink, and that $PR_Q - PR_K$ is positive in all trajectories studied. In connection to
attention, the shrinking of keys leads to a narrower spectrum of $QK^\top$ and more peaked
attention weights. In order to determine if this connection is causal or coincidental, we directly control the spectrum of keys during training across five seeds: restricting it to make it shrink sharpens the
attention with high directional confidence, while keeping it constant to the level of initial dispersion makes
attention softer. Additional
token-level checkpoint analyses show that the monotonic paired-contrast trend is not universal across pretrained families, but survives as an early-training regime that later decays over a full pretraining run, and the link between interaction-rank geometry and
attention entropy remains visible in several models.
Read the full abstract ▾
All authors Vidit Gupta, Siddhesh Nadkarni, Mihik Chaudhari, Vinaya Sawant, Prachi Tawde
Artificial Intelligence · Cross-listed from cs.RO
Bayesian Active Learning for Intent Disambiguation in Interactive Robot Planning
Huao Li, Carson Sobolewski, Augustinos Saravanos et al. (+3 more)
Interactive
robot planning requires
robots to infer and execute human intentions from natural
language instructions that are often ambiguous, incomplete, or underspecified. Although large
language models (LLMs) provide a powerful interface for clarification, relying on the generative model to drive an multi-turn conversation can introduce systematic failures. We propose a
Bayesian framework that treats clarification as an active learning problem over grounded Signal Temporal Logic (STL) task specifications. Our method uses LLMs to initialize candidate formal specifications and translate informative contrasts into natural-
language clarification questions, while
Bayesian optimization maintains uncertainty estimation over user intent and selects queries that maximize information gain. After convergence, the inferred STL specification is passed to a formal planner to synthesize a verifiable
robot trajectory. Across four simulated and real-world task domains, our approach generally achieves higher task satisfaction and requires fewer clarification rounds than LLM baselines, while helping smaller models close the performance gap against larger
reasoning models.
Read the full abstract ▾
All authors Huao Li, Carson Sobolewski, Augustinos Saravanos, William Tan, John Karigiannis, Chuchu Fan
Artificial Intelligence · Cross-listed from cs.RO
SAGE: Symbolic Action-Gating and Editing for LLM Task Planners
Trung Minh Bui, JongSul Moon, YoungOuk Kim et al. (+3 more)
Large
language models (LLMs) are now the default cognitive core of
embodied household
agents, yet the plans they emit are rarely checked against a grounded model of the environment before execution, and the task-success they report is often measured on
benchmarks so saturated that no method can be separated from another. We present SAGE (Symbolic Action-Gating and Editing), a single-LLM planner built from two lightweight mechanisms: a domain-agnostic symbolic gate (~250 lines of Python, zero
tokens, $O(|\pi|)$) that blocks precondition-violating actions with typed reasons as a runtime safety monitor, and a local edit that regenerates only the failed sub-goal's suffix, keeping completed and untouched work intact; a hybrid seed+live
memory store supports cold-start coverage. We evaluate under a leak-free protocol (leave-one-out
retrieval) over five open-weight models and a 75-task AI2-THOR
benchmark. On the standard
benchmark goal-completeness saturates (52% of instances trivially solved) and SAGE ties strong hierarchical baselines. On a harder, method-agnostic multi-goal composition, SAGE's completeness lead re-emerges large (+0.06 to +0.23 across four models). Under injected mid-execution failures, SAGE recovers as reliably as whole-plan replanners at 2.4-3.3x fewer LLM calls. As a verify-before-execute gate, the symbolic monitor blocks unsafe actions before actuation and raises simulator-reported step-success for every planner tested (up to +0.11), a signal the verifier never sees (non-circular). Because the gate calls no model (0.008 ms/plan), it is a safety layer that runs essentially free on the edge: SAGE planning reproduces its quality on a Jetson AGX Orin, where small-model verification helps most. We release the
benchmark, the leak-free protocol, the recovery and safety-gate harnesses, and a verifier-portability study (auto-induced on ALFWorld, 0.89 held-out).
Read the full abstract ▾
All authors Trung Minh Bui, JongSul Moon, YoungOuk Kim, Quang-Ngoc Phung, Se-Woong Jun, Dongin Shin
Artificial Intelligence
Maintaining Benchmarks Against Increasingly Capable Agents: Detection and Remediation of Unearned Passes
Weijun Luo, Kelvin Luu, Xinyi Liu et al. (+6 more)
Agentic
benchmarks guide model selection and training. Yet an
agent can pass a task without demonstrating the intended capability. Such outcomes constitute unearned passes; their proportion among all passes defines the integrity gap. As
agents improve,
benchmark surfaces that once seemed harmless can become exploitable, making
benchmark validity an ongoing maintenance problem. We introduce a process-verification framework that audits passing trajectories, distinguishes evidenced reward hacking from verifier weakness, and localizes exploitable surfaces for repair. Across 3,810 passing trajectories from 29 model-
benchmark cohorts, confirmed violations often increase with model generation but not monotonically. On SWEBench Pro V1.0, confirmed violation rates rise from 24% to 73% between Opus 4.7 and Fable 5 on matched tasks; later cohorts fall to 11% for Fable 5.1 and 0% for GPT-6 Astra. These comparisons are descriptive: configurations were not normalized, and the latest models also pass fewer exploitable tasks. Violations concentrate around a small set of recurring surfaces, especially unintended access to reference solutions through git history. Three repair case studies across two
benchmarks show why blocking a recorded exploit is insufficient: the same protected information can remain accessible through another route. Therefore, we combine minimal patches with exploit replay and fresh
agent evaluation,
auditing new passes under the original standard. No evaluated attempt against the final patches reached the protected channel, and every post-patch pass was judged legitimate.
Benchmark integrity requires ongoing maintenance: audit passing behavior, repair the enabling surface, and re-evaluate both exploit access and legitimate solvability.
Read the full abstract ▾
All authors Weijun Luo, Kelvin Luu, Xinyi Liu, Guangze Luo, Miguel Romero Calvo, Soham Dan, Daniel Yue Zhang, Ying Liu, Mohamed Elfeki
Artificial Intelligence
QuantaSpike: Short-Window Spike-Driven Quantization for Large Language Models
Bang Hu, Guowei Zhu, Changze Lv et al. (+4 more)
Large
language models (LLMs) achieve strong performance across many tasks but rely on dense multiply-accumulate (MAC) operations during inference, resulting in high energy cost. Spiking neural networks (SNNs) offer an event-driven alternative in which synaptic integration uses lightweight accumulation. However, spike-driven LLM inference remains difficult because outlier-heavy activations typically require long firing windows or auxiliary non-spiking paths. We propose QuantaSpike, a short-window spike-driven quantization framework for LLMs built around Logarithmic Ternary Integrate-and-Fire (LTIF)
neurons. LTIF uses ternary events with power-of-two membrane-response quanta, improving the information represented by each firing step while retaining shift-ACC-compatible computation. QuantaSpike combines this
neuron with group-adaptive gain and selective outlier admission: normal values use residual LTIF steps, whereas admitted outliers receive one additional onset spike before entering the same residual dynamics. Across OPT and Llama-2, QuantaSpike achieves state-of-the-art or competitive perplexity and zero-shot accuracy among spike-driven LLM quantization methods. It also transfers to newer dense LLMs, remaining close to the FP16 reference on Llama-3-8B and Qwen3-8B under the same four-step firing window. Analytical linear-energy projections show that QuantaSpike reduces the energy of one linear transformation by about $80.0\%$ on OPT models and $67.1\%$ on Llama-2 models relative to SpikeQuant, providing an accurate and energy-efficient spike-driven path for LLM inference.
Read the full abstract ▾
All authors Bang Hu, Guowei Zhu, Changze Lv, Xiaoqing Zheng, Fengzhe Zhang, Fan Zhang, Wei Cao
Artificial Intelligence · Cross-listed from cs.CY
Investigating Human–AI Discrepancies via Multiple-Solution Problems
Zihao Wang, Francesco Insulla and Andrea Montanari
Frontier artificial intelligence (AI) models are benchmarked on whether they reach a correct answer. Yet many problems admit several correct answers and repeated attempts, by different people or by the same model resampled, trace out a distribution over them. In this work, we ask whether human and model
reasoning lead to different distributions over valid solutions. Our testbed comprises 270
reasoning puzzles across five puzzle families. These multiple-solution puzzles each have 3 to 8 valid solutions and are simple enough that humans and models can solve them reliably. The resulting distributions differ markedly: models differ from one another, yet resemble each other far more than they resemble humans. Model distributions are, moreover, within every puzzle family, less diverse than human ones. We compare these discrepancies across puzzle categories, and trace how they respond to
reasoning-effort settings, to prompting, and to perturbations of the puzzle that leave its solutions unchanged. Together, these results point at significant differences between human and AI problem-solving processes, and their choice among equally defensible solutions. As progressive deployment of AI systems in society comes into focus, evaluating such differences (beyond one-dimensional accuracy metrics) is increasingly important. Data and code are available at https://hai-discrepancies.github.io/
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
WAM-OPD: Sharpening World Action Models via On-Policy Distillation
Panjun Liu, Xiaohan Lei, Shiqi Zhang et al. (+8 more)
Pretrained world action models (WAMs) provide generalist capabilities across diverse robotic manipulation tasks, yet improving target-task performance to an expert level without degrading pretrained skills remains challenging. We explore on-policy
distillation (OPD) for WAMs and introduce WAM-OPD. WAM-OPD inherits the advantage of OPD methods that transfer task-specific teacher knowledge under the student's own induced distribution, rather than directly fitting the student to a narrow task-specific data distribution. However, in closed-loop manipulation, the observation histories change as the student policy evolves, requiring fresh environment rollouts to remain on-policy. Applying OPD to WAMs entails repeated data collection, which is costly even in simulation and often impractical on real
robots. To avoid repeated environment rollouts during
distillation, we introduce prefix-weighted trajectory replay (PWTR). PWTR uses a fixed trajectory pool composed primarily of initial-student rollouts, supplemented with task-specific teacher rollouts to broaden trajectory coverage. For each trajectory replayed from this pool, PWTR conditions the current policy on successive stored histories to generate fresh denoising paths, along which the task-specific teacher provides supervision. Although these denoising paths are refreshed as the policy evolves, the replayed environment trajectories remain fixed. PWTR therefore reweights per-decision
distillation losses using proxy importance weights derived from path scores accumulated over the trajectory prefix preceding each decision to mitigate the resulting shift in the history distribution. Simulated and real-world experiments demonstrate task adaptation without additional environment interaction during
distillation. In both settings, WAM-OPD improves target-task performance while retaining near-initial performance on tasks excluded from adaptation.
Read the full abstract ▾
All authors Panjun Liu, Xiaohan Lei, Shiqi Zhang, Yikun Wang, Yongxin Zhang, Mingyi Hu, Shida Sun, Jiateng Shou, Wengang Zhou, Jiajun Deng, Zhiwei Xiong
Artificial Intelligence
Evolving Support Priorities in Empathetic Reinforcement Learning
Pengyu Huang, Zhiyuan Han, Wenwen Tong et al. (+6 more)
We identify a fundamental mismatch in empathetic reinforcement learning: support priorities evolve with the dialogue state, yet existing methods typically optimize predefined reward specifications that remain fixed across turns. To model these evolving support priorities, we organize empathetic support along cognitive, affective, and proactive empathy, and propose Context-Adaptive Rubric
Evolution (CARE). At each turn, CARE generates a context-adaptive rubric by adjusting both the weights of these three empathy dimensions and their fine-grained evaluation criteria. The rubric generator is trained with turn-level rubric supervision and human preference data through supervised fine-tuning followed by preference-based reinforcement learning, and then serves as an adaptive reward interface for online empathetic RL. Integrated with both RLVER and MICA, CARE achieves state-of-the-art performance across SentientBench, EQBench3, and EMPA under three independent LLM judges. Notably, on EMPA, CARE improves EPM-Idx over the strongest baseline by at least 13 points under all three judges, including an increase from 28.11 to 83.54 under Gemini-2.5-Pro. Further analyses show that learned rubric priorities systematically vary across dialogue stages and user
emotions, demonstrating that CARE adapts what is rewarded as support needs evolve. Code is available at https://asa13opp.github.io/CARE-project-page.
Read the full abstract ▾
All authors Pengyu Huang, Zhiyuan Han, Wenwen Tong, Hewei Guo, Jiangnan Chen, Sirui Chen, Lewei Lu, Beier Zhu, Xun Yang
Artificial Intelligence · Cross-listed from cs.CR
Certified Multi-Source Integrity for Structured Agent Actions
Anmol Pandey, Aditya Jain, Liang Chen et al. (+2 more)
LLM
agents increasingly take privileged, often irreversible structured actions, such as paying an invoice. They assemble each action from action-critical fields in documents and tool outputs that an adversary can corrupt, and indirect
prompt injection can drive the model itself to extract attacker-chosen values. Current defenses gate on a source's trust label or certify free-text answer quality. None certifies the integrity of a coupled, policy-bound structured action under a corruption budget that accounts for shared upstream sources. We characterize when such an action is safely certifiable and give the maximally live safe certifier. It admits an action only when each field clears the rule its evidence structure supports: a bounded corruption radius over corruption-distinct evidence classes, counted by a minimum hitting set so that re-publishing or laundered copies cannot manufacture a quorum, deterministic reconciliation for complementary fields, and a trusted anchor where the evidence leaves a field single-sourced. We formalize two robustness notions, validate each mechanism by ablation, and measure how often the multi-source precondition holds on sanctions designations (70,966 entities) and software supply-chain provenance (450 packages). Under upper-bound proxies, genuine corroboration is a minority phenomenon in both, and naive attestation counting overstates it, since witnesses that look independent collapse to two corruption-distinct domains once shared origin is counted. Across five current models in a real
agent loop, a realistic injection fools every model but one and a naive
agent then executes the fraudulent action on most attacks. The certifier admits no unsafe action and recovers the correct value where corroboration permits, while action-gating and provenance baselines are broken in every world of our harness by some attack in its space.
Read the full abstract ▾
All authors Anmol Pandey, Aditya Jain, Liang Chen, Carsten Maple, Christo Panchev
Artificial Intelligence
Stashbird: Episode-Grounded Lifecycle Reconciliation for Conversational Agent Memory
Chidera Biringa, Lucas Yannul, Xiaowen Wang et al. (+5 more)
AI
agents require
memory that remains consistent as conversational evidence changes. We present Stashbird, an episode-grounded
memory system that uses provenance to reconcile derived graph and
retrieval state during updates and deletion. Repeated evidence extends support, corrections supersede prior active relations, and deletion removes unsupported state while preserving relations with remaining support. Under fixed semantic decisions, reconciliation produces correct final states in all 20 update sequences, compared with eight without reconciliation, and satisfies the defined checks across 263 deletion interventions. Across four long-term
memory benchmarks, Stashbird achieves competitive question-answering accuracy and strong model efficiency. On LoCoMo, it uses 76.4x fewer ingestion
prompt tokens than Graphiti and 8.1x fewer
retrieval prompt tokens than reproduced Hindsight
Read the full abstract ▾
All authors Chidera Biringa, Lucas Yannul, Xiaowen Wang, Marco Ayala, Nicholas Yi, Alex Moyse, Nishant Manchanda, Vivek Gupta
Artificial Intelligence
AdaGuard: An Adaptive Guard Model with User-defined Policies
Yunhao Feng, Yifan Ding, Yuxiang Xie et al. (+4 more)
Guard models support the safe deployment of
language model
agents, but fixed risk taxonomies limit their ability to accommodate requirements that vary across applications and tasks. Under user-defined policies, detecting violations requires interpreting both the applicable rules and the
agent's behavior, since identical actions can receive different judgments under different policies. To support learning this capability, we introduce AdaptiveSafety, a
dataset of 10,939 training examples and 1,000 test examples covering policies with 1–100 rules. The
dataset combines trajectories from multiple sources with policy and behavioral counterfactuals, pairing each example with an explanation and the complete set of violated rules. These counterfactuals expose changes that alter compliance, while structural augmentations provide supervision for consistency under rule reordering and identifier remapping. Building on this supervision, we propose SafePO, a reinforcement learning
algorithm for refining violation identification while balancing explanatory
reasoning and final verdicts. SafePO uses structured rewards to assess prediction correctness, retains group-relative advantages at the response level, and employs a separately trained value model to modulate
token weights within explanation and verdict regions. Separate normalization controls their relative contribution to training despite differences in length. Through supervised initialization followed by SafePO, we develop AdaGuard, a family of 0.6B, 4B, and 8B guard models that assess
agent trajectories under policies supplied at inference time. Our 4B model achieves binary accuracies of 89.30% on AdaptiveSafety and 71.82% on DynaBench. The project repository is available at https://github.com/Yunhao-Feng/AdaGuard
Read the full abstract ▾
All authors Yunhao Feng, Yifan Ding, Yuxiang Xie, Zheng Li, Mingrui Lao, Zeyuan Wang, Yanming Guo
Artificial Intelligence · Cross-listed from cs.CL
Coherence-Aware Distributional Evaluation of Open-Ended Text Generation
Jinnuo Liu, Junhao Zhu, Weifeng Jiang et al. (+2 more)
Existing open-ended generation metrics measure likelihood, lexical diversity, or distributional similarity in generic representation space, yet can miss fundamental dimensions of quality. A prominent blind spot is global coherence: a generated passage may be locally fluent while remaining globally contradictory, causally inconsistent, or topically disconnected. We identify representation as a central bottleneck in detecting these failures and introduce CHORD (Coherence-aware Hidden-state Open-generation Reference Distance), a coherence-sensitive distributional metric. CHORD encodes generated and human-written corpora in the hidden-state space of a frozen LLM using a coherence-eliciting
prompt, and compares the resulting distributions using RBF-MMD. To test coherence sensitivity and selectivity, we construct a counterfactual evaluation suite pairing graded coherence-degrading perturbations with meaning-preserving controls. CHORD selectively detects relation, discourse, structural, and mixture failures that perplexity,
entropy, MAUVE, FBD, and MMD-based baselines either miss or cannot separate from benign rewriting. Factorial ablations show that representation is the primary source of coherence sensitivity, while RBF-MMD improves sample efficiency. Larger backbones capture finer-grained distinctions, but coherence prompting improves selectivity only when the backbone can follow the
prompt. On unconditional generation and prefix continuation, CHORD yields model rankings that strongly align with human judgments of whether outputs make sense and appear human-written. Together, these results establish representation design as central to reliable distributional evaluation. Code: https://github.com/MAPS-research/CHORD. Experiments: https://github.com/MAPS-research/CHORD-Experiment.
Read the full abstract ▾
All authors Jinnuo Liu, Junhao Zhu, Weifeng Jiang, Haoming Liu, Hongyi Wen
Artificial Intelligence · Cross-listed from cs.CV
ReGDiff: Guided Diffusion in Regulated Latent Space for Exploring Metamaterial Voxel Geometry
Wangzhi Zhan, Jianpeng Chen, Dongqi Fu et al. (+1 more)
Metamaterials are artificially engineered structures whose mechanical and physical behaviors are strongly shaped by geometry rather than composition. Voxel representation provides a unified format for metamaterial geometry generation, as it can express diverse classes such as truss, shell, and porous structures within a single cubic discretization. However, voxel-based generation faces a plausibility-novelty trade-off: staying close to known geometries helps preserve
geometric regularities, while moving away from them is necessary for novelty but may produce degenerate geometries. To address this challenge, we propose REGDIFF, a generative framework that couples voxel representation with latent space regulation and guided
diffusion. REGDIFF introduces a repel-and-sink (RAS) mechanism to smooth the latent distribution of plausible geometries, and short-range repulsion (SRR) guidance to discourage generation overly close to known samples while maintaining
geometric plausibility. We further contribute a voxel-based
benchmark covering truss- and shell-type metamaterial geometries, together with an evaluation module for
geometric plausibility, novelty, and diversity. Experiments show that REGDIFF outperforms voxel-based generative baselines, achieving +8.9% in
geometric plausibility, +46.4% in novelty, and +128.6% in diversity on average across two
datasets. These results suggest that REGDIFF is a strong geometry candidate generator for downstream evaluation. Our code is provided at https://github.com/wzhan24/ReGDiff.
Read the full abstract ▾
All authors Wangzhi Zhan, Jianpeng Chen, Dongqi Fu, Dawei Zhou
Artificial Intelligence
When Does Selection Replace Extraction? A Pre-Registered Test of Agent Memory with a Typed Decision Model
Rishabh Sharma and Rishika Lall
Does conversational
memory need LLM-extracted facts, or is selecting the right raw turns enough? Published results disagree. Extraction-based systems report gains from distilled facts. Recent studies find raw history with good ranking does as well, but disagree about whether ranking matters. We ran a pre-registered study on held-out LoCoMo conversations and LongMemEval. At a tight budget on LoCoMo, raw turns selected by a single call to Jev, a typed decision model, are non-inferior to an LLM-extraction
memory (one-sided 95% bound -3.0 points against a -5-point margin). Blind human grading narrows the margin but does not change the result. Raw turns cost 3,061 times less to write, and the result holds with a second answer model. Within this study, reranking's gain shrinks as the budget grows. It adds 17.4 points on LoCoMo and 9.1 on LongMemEval when three of 30 candidates are kept. At generous budgets it adds 1.5 and 1.1, and extraction systems are more accurate. This suggests why published results disagree. At matched context, Jev selects as accurately as an LLM reranker (non-inferiority bound -2.0) at a third of the latency, and more accurately than a multi-call graph traversal. Reranking lowers correct abstention. Plans, code and graded answers are released.
Read the full abstract ▾
Artificial Intelligence
Same Winners, Different Success Rates: Evaluating How LLM Agents Recover from Failures
Dong Xu, Zhangfan Yang, Jiantao Wu et al. (+5 more)
Evaluating how LLM
agents recover from mid-task failures is central to deploying reliable agentic systems. Existing checkpoint-based
benchmarks measure recovery by comparing which action is selected as best across independent runs, a quantity known as set agreement. However, set agreement is a purely ordinal measure that records which action wins without reflecting the absolute level of performance. When all actions fail, they tie at zero reward, and independent runs produce the same tied set with high probability, creating an illusion of stability that masks near-zero recovery success. We formalize this limitation through a set-path
symmetry result, proving that for equal-cost Bernoulli actions the success probabilities (0.9, 0.8) and (0.2, 0.1) yield identical best-action-set distributions at every sample size. No procedure based solely on which action wins can distinguish these two regimes. We further prove that certifying exact population ties is impossible in finite time, and that the assignment of outcomes to checkpoints carries information beyond marginal outcome distributions. The pooled success probability is the missing scalar that resolves the ordinal ambiguity. Experiments on 864 frozen RecoveryBench episodes and two planning cohorts totaling 3,456 responses confirm the theoretical predictions. Agreement and held-out quality can move in opposite directions, and permuting checkpoint-to-action bindings changes 8 to 13 percent of
cell-level conclusions. Based on these findings, we propose reporting four diagnostic quantities (agreement, all-zero fraction, held-out success, and pooled success) that expose this failure mode with no additional data collection.
Read the full abstract ▾
All authors Dong Xu, Zhangfan Yang, Jiantao Wu, Shipeng Zhang, Zexuan Zhu, Jiangqiang Li, Jun Zhang, Junkai Ji
Artificial Intelligence
GlyphBench: A Playground for Language-Model Reinforcement Learning
Roger Creus Castanyer, Marc-Alexandre Côté, Matthew James Sargent et al. (+3 more)
We introduce GlyphBench, an environment suite for reinforcement learning (RL) post-training of
language-model
agents, with over 360 tasks spanning diverse games. GlyphBench renders spatial observations as two-dimensional Unicode grids and connects training, evaluation, and trajectory replay through a unified interface designed to support efficient and reproducible research. We use GlyphBench to study how observation interfaces,
reasoning effort, and
agent harnesses affect performance, and how RL configurations shape learning dynamics. Our results show that glyph observations outperform native text and pixels in our Craftax experiments, with further gains on several BALROG environments. RL on 100 GlyphBench tasks improves Qwen3.5-4B on held-out
Reasoning Gym problems, reaching 63.48% accuracy and outperforming the base model, a math-trained baseline, and a code-trained baseline. These experiments provide empirical evidence that
reasoning gains from gameplay can yield stronger transfer than math or code. Together, these results highlight GlyphBench's value as a testbed for systematic research on how
language-model
agents learn, interact, and generalize.
Read the full abstract ▾
All authors Roger Creus Castanyer, Marc-Alexandre Côté, Matthew James Sargent, Augustine N. Mavor-Parker, Glen Berseth, Pablo Samuel Castro
Artificial Intelligence
Behavior-Grounded Semantic Enrichment for Financial Fraud Modeling and Reasoning
Linbo Shao, Huilin He, Yating Lou et al. (+1 more)
In financial fraud detection, rich semantic context can provide important evidence for transaction behavior modeling and fraud
reasoning. However, public real-world financial
datasets often lack rich semantics due to
privacy constraints. Consequently, synthetic
datasets incorporate generated semantics, but at the cost of behavioral realism; textual descriptions for contextual
reasoning remain scarce. We address this gap through a semantic enrichment framework grounded in original transaction behavior to simulate
multimodal financial data. We (1) propose a multi-
agent semantic enrichment framework that generates interpretable financial semantics grounded in transaction behavior through role-specialized
agents and consistency refinement, and (2) newly contribute a valuable
multimodal financial fraud
dataset, MS-FFSD, enriched with structured semantics and textual semantics while preserving real-data-grounded transaction behavior. Furthermore, we systematically analyze the quality and utility of semantic enrichment. Results demonstrate statistical fidelity and framework generalizability, while showing that richer semantics benefit fraud modeling and context-aware LLM
reasoning. Overall, this work advances
multimodal financial fraud research and bridges emerging LLM and multi-
agent capabilities with operational anti-fraud practice. The framework and
dataset are released at https://github.com/AI4Risk/MS-FFSD.
Read the full abstract ▾
All authors Linbo Shao, Huilin He, Yating Lou, Dawei Cheng
Artificial Intelligence
PainterBench: A Figural Divergent-Thinking Benchmark for Tool-Using Language Models
Shane K.A. Dalumura Hettige and Jonas Oppenlaender
Figural divergent thinking is the ability to develop a given shape fragment into an original drawing. In humans, this ability is assessed with incomplete-drawing tasks. We introduce PainterBench, a
benchmark that ports the incomplete-drawing task to the agentic setting. The
agent draws on a canvas through tool calls and observes the result after every turn. The canvas includes a starting shape which cannot be erased, and the
agent's goal is to incorporate this shape into the most original drawing it can produce. The task is open-ended, and the
agent itself decides when the drawing is finished. The
benchmark tests incremental visual planning over a short horizon and the transfer of creative ability from pretraining to multi-turn tool use. We evaluate 14
multimodal language models from small to frontier scale. Across the primary study and six sensitivity analyses, we collect 2,700 drawings and crowdsource creativity and recognizability ratings for every drawing and for 300 human reference drawings. We also present ViDrA-adapted, an automated scorer that predicts human creativity ratings of
agent drawings (r = 0.85 on random held-out test split). Figural divergent thinking varies widely across the 14 models, and GPT-6 Astra produces the most creative drawings. Relative to the human drawings, the
agent drawings score higher in creativity but lower in recognizability. We release the final drawings, per-round canvas snapshots, tool call traces, stimulus bank,
benchmark harness, crowdsourced ratings (N = 72,000), and ViDrA checkpoint.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from stat.ML
AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning
Yingbo Zhao, Zeyu Yang and Zhoufan Zhu
Formulaic alpha discovery is a core challenge in quantitative trading, as identifying alphas that work well together remains difficult. Recent reinforcement learning (RL) methods formulate this task as a Markov decision process (MDP), but two important issues remain unresolved. First, as the alpha pool evolves, the reward function changes accordingly, making the MDP inherently non-stationary. Second, most existing methods optimize a single objective, typically predictive power, while ignoring other important properties of a high-quality alpha pool. Motivated by these challenges, we propose AlphaPareto, an RL method for formulaic alpha discovery. To address non-stationarity, AlphaPareto augments the state to include both the alpha under construction and the current alpha pool, and applies a large
language model (LLM) to encode the pool. This design allows the
agent to adapt to the evolving search environment. To overcome the limitation of single-objective reward design, AlphaPareto replaces the scalar reward with a multi-objective vector-valued reward that simultaneously captures predictive power, temporal stability, perturbation robustness, and diversity, and optimizes these objectives through a Pareto-regularized learning procedure. Empirical applications to real-world
datasets show that our AlphaPareto method outperforms its competitors.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
LLMs are not stochastic parrots: Evidence for meaning-mediated abstraction from conlang-like tasks
Julia Witte Zimmerman, Calla G. Beauregard, Tabia Tanzin Prama et al. (+3 more)
The strong version of the
stochastic parrot argument claims that, although large
language models (LLMs) may exceed rote regurgitation, they cannot move beyond statistical pattern matching into abstraction or
reasoning, remaining ontologically near the lower bound of pattern reuse despite producing alluringly fluent text. We test this hypothesis using conlang-like tasks. Several LLMs are given only natural-
language descriptions of fictional
languages that subvert prominent superficial patterns in training data by combining statistically uncommon and unattested features. Crucially, no example outputs are given. We argue that if the models exhibit rule-following behaviour, they cannot be relying solely on superficial statistical patterns; such patterns often work against the correct output. Instead, successful performance requires representations of the constraints specified in the
prompt. Across three complementary task families, models systematically move in the meaning-predicted direction: they distinguish
prompt exposure from instructed use, alter semantic relationships in response to novel constraints, and sometimes produce exact matches to complex translation answer keys. Although performance varies across the spectrum of models used, these results provide evidence for meaning-mediated abstraction in LLMs and refute the strong
stochastic parrot hypothesis. Our work shows that, under appropriate architectural and contextual constraints, statistical learning can produce meaning-mediated abstractions, although generation remains strongly constrained by superficial plausibility. We discuss implications for model development and for understanding how increasingly abstract representations may emerge from plausible-text-generation objectives.
Read the full abstract ▾
All authors Julia Witte Zimmerman, Calla G. Beauregard, Tabia Tanzin Prama, Parisa Suchdev, Kathryn Cramer, Elisabeth Kollrack
Artificial Intelligence · Cross-listed from cs.LG
EntroPack: Fast and Accurate Entropy-Coded Weight Compression at Arbitrary Bitrates
Hong Zhang, Zhongjie Duan and Yingda Chen
Weight compression helps large neural networks fit deployment
memory budgets, but common fixed-width formats offer only coarse storage choices.
Entropy coding supports finer rates, yet the achieved size depends on the quantized weight distribution and coding overhead. Exploiting this flexibility requires accurate rate selection and efficient weight reconstruction for inference. We present EntroPack, an
entropy-coded weight compressor that supports arbitrary target bitrates without activation calibration or fine-tuning. It combines row-normalized $E_8$
lattice quantization with a conditional probability model of
lattice coordinates. Sampled storage estimates select the quantization resolution without repeated full-stream encoding. The final coordinates are
entropy-coded in independently decodable tiles, enabling fast, fused symbol decoding and numerical weight reconstruction on the GPU. EntroPack supports floating-point and integer weight containers, such as BF16, FP16, FP8, and INT8, with storage bitrate controlled independently of numerical precision. Online decoding adds latency that grows with weight count, making the method well suited to compute-intensive workloads such as
diffusion denoising and
Transformer prefill. Experiments demonstrate fast encoding and modest inference overhead in these settings. When compressing the linear-layer weights of the image generator Z-Image-Turbo, EntroPack achieves substantially lower weight and denoiser output errors than fixed-width formats at comparable storage rates, with modest denoising-step overhead. Targeting 4 bits per parameter, it achieves lower weight and denoiser output errors than NF4, including about 24% lower relative $L_2$ weight error, with less storage. Source code is available at https://github.com/modelscope/entropack.
Read the full abstract ▾
Artificial Intelligence
CASS: Contribution-Aware Structured Sparsity for Model Merging
Yan Li, Guiping Cao, Meng Xu et al. (+5 more)
Model merging integrates task-specific fine-tuned models into a single multi-task model, but often suffers from parameter interference caused by conflicting task-vector updates. Existing methods typically mitigate conflicts by
pruning task vectors based on weight magnitude or random heuristics, treating
Transformers as unstructured “bags of parameters” and overlooking their inherent modularity. In this paper, we propose Contribution-Aware Structured Sparsity (CASS), a unified framework that reduces parameter interference by identifying and preserving task-specific components. At the core of CASS is a contribution-aware structured mask that identifies task-relevant
attention heads and FFN
neurons. We instantiate this mask in two settings: CASS-Merging, the primary post-hoc setting where masks serve as a plug-and-play denoising filter for existing merging operators, and CASS-Tuning, an extension for scenarios with fine-tuning access where masks constrain gradients to reduce structural overlap between task vectors. Our analysis shows that task-relevant components are sparse and partially disjoint, supporting structured component-level filtering as an effective way to reduce merging interference. Extensive experiments across
vision (ViT, 20 tasks) and
language (RoBERTa, 8 tasks; Qwen2.5, 4 tasks)
benchmarks demonstrate that CASS improves a range of representative merging baselines.
Read the full abstract ▾
All authors Yan Li, Guiping Cao, Meng Xu, Tao Jiang, Yaguang Song, Ming Tao, Yaowei Wang, Dongmei Jiang
Artificial Intelligence · Cross-listed from cs.RO
Unified Visual-Tactile-Action Modeling from Human Demonstrations for Dexterous Manipulation
Wenqiao Li, Qianyou Zhao, Jiawen Hao et al. (+5 more)
Dexterous manipulation requires tactile feedback. However,
robot tactile demonstrations are difficult to scale,because dexterous-hand teleoperation provides limited tactile feedback to the operator. In contrast, human demonstrations offer a substantially more scalable source of diverse tactile interactions. Motivated by a simple premise: hands can change, but the underlying physics of interaction does not. We leverage human tactile data to improve dexterous manipulation policies. Specifically, we first build a tactile motion-capture system that synchronously records images, tactile signals, and hand motions. Using this system, we construct the UVTA
dataset spanning five contact-rich tasks, with 1,000 human demonstrations covering diverse interaction patterns and 150
robot demonstrations per task. To transfer the underlying physics of human interaction to
robot control, we propose a Unified Visual-Tactile-Action Model that maps both embodiments into aligned tactile and action representations and jointly predicts future action and tactile trajectories. The joint objective enables human demonstrations to supervise contact-aware representation learning, while only
robot actions are executed during deployment. In real-
robot evaluations across five tasks, our method achieves an average success rate of 70%, outperforming the strongest visual-tactile baseline, which achieves 29%, and an architecture ablation, which achieves 42%. Performance improves consistently with additional human demonstrations and exhibits no saturation at 1,000 demonstrations per task, validating the effectiveness of scalable human tactile data for dexterous manipulation. Project page is available at https://uni-vta.github.io/.
Read the full abstract ▾
All authors Wenqiao Li, Qianyou Zhao, Jiawen Hao, Xuezhou Zhu, Tengyu Liu, Kaifeng Zhang, Chuan Wen, Siyuan Huang