Artificial Intelligence · Cross-listed from cs.CL
CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA
Fatema Tuj Johora Faria, Mukaffi Bin Moin, Jubayer Al Mahmud et al. (+2 more)
Existing defenses against
hallucination in
retrieval-augmented and multi-
agent pipelines remain partial: evidence is trusted despite modality disagreement, debate verifies an aggregate report rather than individual claims, and such verification occurs only after drafting, leaving inter-
agent errors undetected until the final text. To close this gap, we present CLAIR-Fin, a nine-
agent framework that decomposes each question into atomic claims maintained in a typed Financial Claim Ledger. Each claim is resolved through Asymmetric Evidence Authority, which conditions evidence trust on claim type rather than treating all modalities as equally reliable; Chain-of-Custody Verification, which checks grounding at the hand-off between drafting and
adversarial review rather than only at the pipeline's exit; an Adaptive Rebuttal Cycle, which routes contested claims through
adversarial debate whose depth scales with what that debate finds; and a terminal entailment audit paired with a continuous
Hallucination Risk Index that distinguishes claims that passed scrutiny from claims never contested. We evaluate CLAIR-Fin on BB-FinQA-X, a 500-question cross-modal financial evaluation set built from Bangladesh Bank Annual Report material, stratified by query type, format, and difficulty. Relative to a single-pass
retrieval-augmented generation baseline, it raises faithfulness ($0.780 \rightarrow 0.889$) while abstaining on 5.4% of questions when evidence is insufficient rather than forcing an unsupported response, and it exceeds stronger
retrieval-strategy baselines such as HyDE and Graph-RAG on faithfulness ($\leq 0.874$).
Read the full abstract ▾
All authors Fatema Tuj Johora Faria, Mukaffi Bin Moin, Jubayer Al Mahmud, M. F. Mridha, Md. Alam Hossain
Artificial Intelligence · Cross-listed from cs.LG
SAGE: Surrogate-gradient Adaptation via Attention-Guided Entropy for Spiking Transformers
Kiran Nair, Rodrigue Rizk and KC Santosh
Spiking neural networks (SNNs) offer an energy-efficient alternative to conventional deep neural networks by exploiting sparse event-driven computation, but their training remains challenging because the non-differentiable spike function requires surrogate gradients whose fixed shape may be suboptimal across layers and training stages. In this work, we introduce SAGE, an uncertainty-modulated surrogate-gradient mechanism for
Transformer-based SNNs. SAGE estimates block-level uncertainty from normalized self-
attention entropy and uses this signal to adapt the surrogate-gradient slope during training while leaving the inference model unchanged. By modulating only the training-time surrogate parameter, the proposed method preserves the original architecture and deployment cost while improving optimization flexibility. Experiments on CIFAR-10/100 demonstrate that SAGE achieves improved accuracy over fixed-surrogate baselines, with results up to 1-2% consistent gains across multiple simulation time steps. These results highlight the potential of
attention-derived uncertainty as a lightweight training signal for adaptive surrogate-gradient learning in
transformer-based SNNs.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
MedPlex: Deep Vision-Language Co-Adaptation for Clinically Grounded Medical Segmentation
Rafi Ibn Sultan, Hui Zhu, Chengyin Li et al. (+1 more)
Medical image
segmentation is still largely treated as a
vision-only problem, although clinical interpretation often relies on textual knowledge of anatomy, location, appearance, and surrounding context. Existing text-guided
segmentation methods within the
Vision-
Language Model (VLM) paradigm often use
language only as a late conditioning signal, limiting its influence on visual representation learning. We introduce MedPlex (Medical Plexus of
Vision and
Language), an end-to-end VLM framework that makes text guidance a continuous, clinically grounded component of
segmentation learning. Through Bi-Fusion (Bidirectional Fusion), visual and textual representations evolve jointly across the encoding hierarchy. MedPlex further introduces class-level and region-level concept
alignment to organize the shared representation at complementary granularities. Class-level
alignment anchors each anatomical target to an aggregated clinical concept profile, while region-level
alignment preserves individual concepts, such as shape, location, appearance, and texture, through class-specific visual evidence. In this way,
language provides structured supervision throughout the encoder rather than serving only as a late-stage cue. MedPlex achieves state-of-the-art performance across CT and MR
benchmarks for multi-organ, cardiac substructure, and tumor
segmentation, including settings with real free-text clinical supervision. Code: https://github.com/rafiibnsultan/MedPlex.
Read the full abstract ▾
All authors Rafi Ibn Sultan, Hui Zhu, Chengyin Li, Dongxiao Zhu
Artificial Intelligence
Learning to Assemble Novel Structures with Unfamiliar Parts under Semantic Constraints
Jonghyuk Park, Alex Lascarides and Subramanian Ramamoorthy
This paper describes a neurosymbolic architecture for learning to assemble novel structures using evidence from
embodied conversations and task demonstrations. We focus on scenarios where an
agent encounters, after deployment, semantic constraints on structures–in other words, constraints as to which part types and features make valid structures–that were not available during training, and where it is initially unaware of the relevant structure and component part concepts. The
agent must acquire and exploit such knowledge through user interactions while attempting assembly. We study this setting in a simulated toy truck assembly domain, learning from symbolic evidence encoded in natural
language and from dense visual observations. Our experiments show that communicating semantic constraints through natural
language (e.g., "dump trucks have a dumper") yields more data-efficient online adaptation than relying only on task demonstrations and/or only naming the parts through natural
language.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
Fine-Tuning Qwen3-27B for C-to-Rust Code Translation: A Three-Stage Curriculum of Pretraining, Debugging-Aware SFT, and Task-Specific SFT
Pu Zhao, Changdi Yang, Yixiao Chen et al. (+4 more)
Translating C code into safe, idiomatic Rust is a longstanding software-engineering goal because it can eliminate entire classes of
memory-safety vulnerabilities while preserving the functional behavior of legacy systems. Large
language models (LLMs) have shown promise for this task but typically underperform when applied off-the-shelf, since general-purpose pretraining rarely emphasizes idiomatic Rust generation, cross-
language semantic equivalence, or the ability to reason about and repair compiler/runtime feedback. In this report we describe a three-stage fine-tuning curriculum applied to Qwen3-27B that is designed to progressively specialize the model for the C-to-Rust (C2Rust) translation task: (1) continued pretraining on Rust-centric corpora to strengthen the model's prior over idiomatic Rust syntax and standard-library usage; (2) supervised fine-tuning (SFT) on the microsoft/Verus_Training_Data
dataset to instill debugging and self-repair behavior over Rust code; and (3) task-specific SFT on paired C/Rust solutions derived from LeetCode problems to teach direct semantic translation. We evaluate the resulting model using the agentic, static-analysis-guided verification framework of SACTOR, which performs structure-aware, two-phase (unidiomatic to idiomatic) translation with foreign-function-interface (FFI)-based end-to-end (E2E) testing. We report success rate, idiomaticity (Clippy lint counts, unsafe-code fraction), and failure-mode analyses, and compare our fine-tuned model against baseline Qwen3-27B and other LLMs evaluated under the same framework.
Read the full abstract ▾
All authors Pu Zhao, Changdi Yang, Yixiao Chen, Yi Gao, Yifan Cao, Haochen Zeng, Yanzhi Wang
Artificial Intelligence · Cross-listed from cs.LG
From BERT to Frontier Agents: Eight Years of Language-Model Progress, the Collapse of the Capability-Cost Curve, and the Rise of Task-Targeted Models
Pranav Kumar Kaliaperumal
Between October 2018 and July 2026 AI models progressed from simple systems like BERT to massive
agents that solve complex math and write software. The ability to resolve real coding issues improved by nearly six times per year since late 2024. During this time costs dropped sharply with OpenAIs budget model GPT 5 point 6 Luna matching flagship capabilities for just one to six dollars per million
tokens beating older versions at a fraction of the price. Top performance is now split across specialized models as Claude Opus 5 leads in frontend coding Claude Fable 5 excels at repository level coding and GPT 5 point 6 Sol dominates terminal tasks. In a grade school math test using the Qwen 2 point 5 model basic methods solved 58 of 100 problems while advanced sampling solved up to 79. A confidence ranking tool correctly identified 47 right answers in its top 50 choices proving highly useful for sorting tasks with all research materials made fully public.
Read the full abstract ▾
Artificial Intelligence
Second Thought: Reasoning in Parallel as LLM Agents Act and Observe
Zhensu Sun, Chengran Yang, Yunbo Lyu et al. (+2 more)
LLM
agents in the ReAct paradigm alternate between
reasoning, acting, and observing, but deliberate
reasoning is confined to the Thought phase: while the
agent serializes an action and waits for the environment, its
reasoning is frozen. We identify this recurring interval for Action and Observation as a
reasoning idle window and ask whether it can host additional
reasoning in parallel that serves future turns. Therefore, we propose Second Thought, a training-free inference framework that forks four auxiliary branches the instant each Thought phase concludes, decodes them concurrently with the main loop, and merges the generated thoughts back when the environment observation arrives. In this way, Second Thought relocates the added
reasoning off the main thread's sequential decoding path. Across three agentic
benchmarks and three
reasoning LLMs, Second Thought lowers the average turn count in all nine (model,
benchmark) pairs and reduces main thread decoding in six of them by up to 43% (roughly 20% on average among those settings), while leaving it essentially unchanged in a seventh; Pass@1 shows no significant change in seven of nine pairs and the two significant differences are +12.4 and +10.2 points. Against a compute-matched control that forces an equivalent budget onto the main thread's own
reasoning, it attains strictly higher Pass@1 with 1.3 to 3.2 less sequential decoding in all four settings where the control applies.
Read the full abstract ▾
All authors Zhensu Sun, Chengran Yang, Yunbo Lyu, Jieke Shi, David Lo
Artificial Intelligence
Ontology-Grounded Project Memory for Coding Agents
James Adam
Coding
agents have become the primary means of generating new code in many software projects, and the resulting velocity of changes makes keeping track of the reasons behind those changes challenging. This paper introduces MOOSEDev, a system designed to give coding
agents structured, ontology-grounded project
memory. The system captures architectural decisions, lessons, constraints, and rationales in a knowledge graph exposed to
agents via a Model Context Protocol (MCP) interface. Records carry lifecycle status, provenance, and supersession links, queryable via MOOSE, a proprietary neurosymbolic engine that treats the symbolic layer as the primary
reasoning substrate. We compared MOOSEDev against a production vector-
memory tool on a neutral public corpus of 835 typed records. MOOSEDev returned the expected answer set essentially in full (0.98-1.00) on supersession, set-completeness, and negation questions, whereas the baseline's top-k
retrieval surfaced between 6% and 27%. Conversely, relevance recall and
token cost were largely equivalent between the two systems. We also describe a temporal commit-history bootstrap of our own codebase, a pre-registered live trial, and lessons learned.
Read the full abstract ▾
Artificial Intelligence
Exploring ESC Winners with Nested Diagrams
Anurag Sharma, Marcel Nöhre and Gerd Stumme
We present ConceptFlow, a scikit-learn-compatible Python library for Formal Concept Analysis that constructs and renders nested line diagrams from many-valued formal contexts. Given a many-valued context and a partition of its attributes into conceptual scales, ConceptFlow performs conceptual scaling, computes the factor
lattices, identifies filled nodes of the corresponding subdirect product, and produces an interactive visualization. We apply ConceptFlow to the winners of the Eurovision Song Contest from 1975 to 2025, exploring relationships between voting patterns and musical characteristics. Voting support is captured by an outer scale spanning regional, cultural, historical, and political dimensions, while an inner scale captures musical characteristics via tempo and key. The resulting nested line diagram reveals implications across both scales, exposing dependencies between how winning entries were voted for and the musical properties they share.
Read the full abstract ▾
Artificial Intelligence
A Calibrated Test of Internal Action Maps: State Signals Without Global Affine Closure
Dekun Yang
A hidden state signal can be decodable or causally usable without supporting a reusable action map. We test whether action maps fitted without a source reach its natural post-action activation and compose. We organize the tests as an evidence
lattice and validate the
geometric branch on a known affine S_5 carrier: all held-source folds pass one-step, composition, inverse, decoding, and commutativity gates. Structured
curvature and held-domain conjugacy raise error monotonically, but only 23/30 strongest
cells flip a closure gate, bounding rather than universalizing calibration. In post-trained Qwen/Qwen3-4B, frozen final-
token h28 affine maps have mean held-entity error .519, versus .398 for within-test-domain cross-fit. Seven randomized entity splits and map geometry do not support a purely entity-specific account. Earlier h4/h16 layers fit one-step transitions better, but h4 conflict-state decoding is weak and lexical controls remain unresolved. Three matched intervention
datasets regenerated from one frozen checkpoint show causal effects only at h28/h36. Outcome-aware refitting improves h28 one-step error to .474 (.469 with weighting), yet no refit passes composition. Learned finite worlds likewise preserve relative algebraic signals or shared charts without held-source affine closure. Within the tested carriers, state availability, causal use, local geometry, and reusable closure are separable. The result is limited to one pretrained model, sampled final-
token layers, two finite worlds, and the tested affine or diagnostic function classes.
Read the full abstract ▾
Artificial Intelligence
Reward Machines for Signal Temporal Logic
Alper Kamil Bozkurt, Shangtong Zhang and Yuichi Motai
Signal temporal logic (STL) provides a formal
language for specifying real-time properties of real-valued observations, along with a quantitative robustness score for monitoring satisfaction. Control synthesis from STL specifications is of interest since manual controller design becomes infeasible as real-world systems grow in complexity. Moreover, many modern autonomous and AI-enabled systems lack accurate and complete system models, which makes optimization-based synthesis approaches unsuitable and motivates learning-based control. Prior work uses STL robustness scores as rewards in reinforcement learning (RL) to obtain control policies satisfying given specifications; however, robustness depends on execution history, leading to intractable state space expansion for general long-horizon specifications with arbitrarily nested temporal operators. This work introduces a novel automata-based approach that provides an efficient
memory mechanism and associated Markovian rewards suitable for RL frameworks. Our approach constructs a timed alternating automaton from the given STL specifications, augments the state space with automaton locations and clock valuations, and derives rewards from the automaton acceptance condition. We empirically demonstrate that our approach learns policies that achieve higher robustness scores and satisfaction rates than those learned by existing approaches using robustness-based rewards.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Measuring Fairness in Large Audio Language Models via Semantic-Aware Bias Estimation
Zhe Liu
Large Audio
Language Models (LALMs) have seen increasing use for audio understanding tasks such as
speech recognition and audio question answering, raising concerns about
fairness across demographic subgroups.
Fairness evaluation in spoken-input settings is challenging due to confounding factors, including semantic variation in spoken content and speaker-specific characteristics. Ignoring these factors can result in misleading conclusions about model bias. We propose a semantic-aware mixed-effects regression framework for
fairness evaluation in LALMs that explicitly accounts for these confounders. Our approach incorporates sentence-level semantic
embeddings of reference text as
covariates and models speaker identity as a random effect. Notably, semantic representations are extracted from the same LALM under evaluation, enabling semantic control over variation as perceived by the model itself. Experiments on simulated data and real-world
benchmarks demonstrate that the proposed approach substantially reduces spurious
fairness findings and yields more robust and interpretable estimates of subgroup performance differences.
Read the full abstract ▾
Artificial Intelligence
ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction
Yongqi Tong, Tan Li Hui Faith, Choy Zhen Wen Marcus et al. (+5 more)
Open-ended real-world interaction admits multiple valid behaviors: an
agent may answer directly, ask for clarification, provide progress updates, or confirm before acting. This flexibility breaks a core assumption behind group-based RL: rollouts compared within a group are no longer guaranteed to be behaviorally comparable. As a result, reward-model preferences over interaction style can distort relative advantages and steer optimization toward reward-preferred behaviors rather than context-appropriate ones. We formalize this as a reward
fairness problem and propose ARC (Advantage Regularization via Conditioning), a training recipe that restores fairer relative comparison through strategy-conditioned rollout grouping, together with hybrid rewards and
entropy regularization. We study ARC in our proposed \inter, a novel paradigm for responsive, steerable, and execution-aware user-
agent interaction that decouples user-visible communication from latent
reasoning and tool use. \inter\ also provides the annotation and
distillation pipeline for constructing \inter-86K, our strategy-annotated training corpus for supervised and RL training. Empirically, ARC substantially strengthens the core $\tau/\tau^2$ tool-use
benchmarks, while \inter\ reduces time-to-first-
token from 4.91s to 1.27s relative to a think-style baseline. Together, these results suggest that a central bottleneck in open-ended interactive learning is not only how
agents are rewarded, but whether their behaviors are compared fairly in the first place. The ARC implementation and \inter-86K training data will be released.
Read the full abstract ▾
All authors Yongqi Tong, Tan Li Hui Faith, Choy Zhen Wen Marcus, Zhou Jin, Kewei Fu, Jiang-Ming Yang, Jianshe Li, Xin Zhang
Artificial Intelligence
Your Probabilistic JEPA Is Secretly a Hidden Markov Model: A State-Space Interpretation of Joint-Embedding Predictive Learning
Yongchao Huang
A hidden Markov model (HMM) combines three roles: inference of a hidden-state belief from observations, propagation through a Markov transition, and emission back to observation space. We show that full, time-indexed Predictive Information Bottleneck VJEPA (PIB-VJEPA) exposes the same computational structure: a
stochastic context encoder plays the role of an amortized filtering distribution, a probabilistic predictor defines latent-state dynamics, and a decoder, inverse target encoder, or induced implicit conditional supplies the emission direction. We distinguish 4 progressively stronger levels of correspondence and give sufficient conditions for exact sequence-level HMM equivalence. To make the connection concrete, we introduce Markov-Chain JEPA (MCJEPA), which replaces the latent predictor by a learned transition
matrix; in the finite time-homogeneous case,
matrix powers guarantee exact multi-horizon Chapman–Kolmogorov consistency. Conditioned discrete-state transitions, continuous-state Markov kernels, and continuous-time dynamics extend this construction, while deterministic temporal JEPA appears as a degenerate Dirac-kernel special case. We further interpret predictive information-bottleneck learning as seeking a compact predictive state: compression promotes minimality, while residual predictability tests sufficiency. Controlled experiments support transition composition, the filtering interpretation, predictive Markovization in a known synthetic process, and the distinction between JEPA latent prediction and HMM-style sequence learning. Together, these results give temporal JEPA a principled state-space interpretation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Yaxin Luo, Haobin Jiang, Jialv Zou et al. (+11 more)
Transforming
multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a long-horizon agentic process centered on a model-harness system. While an ideal harness system should align with human design priors and accumulate reusable experience through empirical exploration to drive recursive self-improvement, existing paradigms remain static and fall short of this capability. In this paper, we present AutoDesign, a framework that aligns with human design priors, where a meta-harness optimizer guides a code
agent to recursively improve harness based on rollout feedback. To instantiate and evaluate this framework, we focus on the academic paper-to-poster generation task and introduce PosterBench, comprising a 100-paper Main Track spanning five disciplines and PosterBench-mini, a shared 10-paper subset for controlled evaluation. On the PosterBench Main Track, AutoDesign achieves the highest score of 78.32, surpassing the closed-source commercial system Claude Design by 7.45 points. Across seven controlled code-
agent-model configurations, integrating the learned DesignHarness consistently improves performance, increasing the average PosterBench Score from 54.99 to 67.39 (+12.4%). In a fully autonomous long-horizon loop, it executes 253 tool calls and 11 editing turns within 40 minutes for under $3, reaching average conference-poster quality in human evaluation. A system-blind human study further demonstrates that AutoDesign achieves the highest human preference among evaluated systems.
Read the full abstract ▾
All authors Yaxin Luo, Haobin Jiang, Jialv Zou, Xu Huang, Wenhao Yan, Haodong Li, Zhengrong Yue, Jing Li, Xiaofu Chen, Xiaohan Zhao, Jiacheng Liu, Jiacheng Cui, Zhiqiang Shen, Xiaotong Li
Artificial Intelligence
OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
Bobo Li, Hao Fei, Tianjie Ju et al. (+2 more)
Recent advances in foundation models have enabled AI scientists to automate increasingly complete research workflows, from hypothesis generation and code execution to manuscript preparation. Yet workflow coverage alone does not provide access to the full evidence on which scientific discovery depends. Existing systems typically reason over text, code, labels, or precomputed summaries, leaving scientifically decisive spatial, temporal, cross-channel, and procedural relations unavailable to the
agent. We introduce OmniScientist, an end-to-end, omni-modal AI scientist that conducts multidisciplinary research directly from heterogeneous raw evidence. A perception layer and 3 autonomous
agents for ideation, experiment, and writeup operate within a deterministic pipeline, allowing observations to shape research questions, experimental decisions, and final claims throughout the research lifecycle. By running idea, rigour, and claim checks in code, the system enforces novelty screening, statistical validity, execution provenance, and numerical traceability. We evaluate OmniScientist on 36 real-data cases spanning 5 discipline families, 4 families of scientific evidence, and modalities including images, signals, audio,
video, 3-D structures, trajectories, tables, formulae, and graphs. The system completes the full path from raw data to a compiled manuscript in all 36 cases and achieves a mean overall paper score of 6.3 with the reference
reasoning backbone. In paired comparisons against a blind variant that receives only precomputed scalar features, direct perception improves all 7 evaluation dimensions and wins 85% of head-to-head judgments. These results show that lifecycle-wide perception is essential for evidence-grounded scientific discovery and provides a practical path toward broadly capable AI scientists.
Read the full abstract ▾
All authors Bobo Li, Hao Fei, Tianjie Ju, Mong-Li Lee, Wynne Hsu
Artificial Intelligence · Cross-listed from cs.RO
HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark
Dairu Liu, Zekun Qi, Jiayu Zeng et al. (+11 more)
Humanoid motion tracking is central to teleoperation and whole-body imitation, yet evaluation often disagrees with what people perceive in
videos. Kinematic errors average per-frame pose differences but miss the physical artifacts that matter most, particularly unstable support and incorrect contacts such as foot skating and mistimed touch-downs. Meanwhile, widely used test suites are small and lack the diversity needed to stress contact-rich, long-horizon behaviors. We introduce HumanTracker to make
humanoid tracking evaluation both perceptually aligned and scalable. The HumanTracker
benchmark contains approximately 153 hours of optical motion trajectories from multiple professional performers, organized into four motion families with text labels for fine-grained diagnosis. We further propose HumanScore, a preference-aligned metric trained on 12K motion pairs containing 24K motions. Across representative state-of-the-art trackers, HumanScore better predicts human preferences and reveals contact and stability failures that kinematic metrics often miss.
Read the full abstract ▾
All authors Dairu Liu, Zekun Qi, Jiayu Zeng, Ruixi Yu, Yu Guan, Yintianrun Zhang, Xuchuan Chen, Sikai Liang, Zekai Li, Chenghuai Lin, Xinqiang Yu, Wenyao Zhang, He Wang, Li Yi
Artificial Intelligence
QuoteBench: How Matched Scores Can Hide Command-Path Failures
Shangao Li, Yao Zhang, Volker Tresp et al. (+1 more)
LLM coding
agents issue Bash commands through interfaces that may serialize, wrap, and reparse model output. Matched execution scores alone cannot distinguish command-generation errors from failures introduced after generation. QuoteBench measures this boundary with exact final-state validation on 56 one-shot tasks from 14 incident-derived families, crossing the generation contract with the execution transport around one deliberately unescaped added parser. Escaping at the interpolation point reproduces each replayed reply's raw-path outcome, so any recovery under a disclosed boundary must come from the model changing its generation. Across eight same-window configurations, replaying the same reply through the added parser lowers success by 55.4 to 73.2 percentage points; disclosure recovers 30.4 to 60.7 points for six configurations, and zero or slightly negative for the other two. Raw generation is nearly saturated at the frontier; boundary adaptation is what still separates models. GPT-5.6-sol's matched gap of -3.6 points hides -64.3 points of damage and +60.7 points of compensation. The deployment configuration reorders models: one reversal among 26 comparable pairs is unambiguous and four more sit on single-task margins. Evaluations of command-issuing
agents should report the model configuration, generation contract, execution path, operating point, and final-state validator rather than treat a matched score as an intrinsic model property.
Read the full abstract ▾
All authors Shangao Li, Yao Zhang, Volker Tresp, Yuanyuan Yang
Artificial Intelligence · Cross-listed from cs.CL
LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure
Fanfei Li, Jana Zeller, Manuel Prada-Corral et al. (+4 more)
Modern
language models are trained on heterogeneous web-scale text corpora. Consequently, studying knowledge and skill acquisition is difficult, as prior exposure to related content is hard to characterize. To address this challenge, we introduce LittleCurriculum, a curated 88B-
token pretraining corpus tailored to U.S. elementary school material, explicitly excluding concepts, facts, and vocabulary taught above Grade 5. Training a 5B-parameter LLM from scratch on LittleCurriculum yields LittleLearner, a model with sufficient
language competence for open-ended evaluation, yet with clear knowledge and capability boundaries mapped to interpretable curriculum guidelines. We release LittleCurriculum and LittleLearner as a developmentally restricted sandbox to study how models acquire, represent, and use data under a well-defined training scope. We illustrate the sandbox's utility in a first suite of experiments on injecting new knowledge through post-training and in-context learning. These methods let LittleLearner better utilize existing knowledge, but do not raise out-of-scope capabilities. Our findings underscore the value of this controlled environment for future investigations.
Read the full abstract ▾
All authors Fanfei Li, Jana Zeller, Manuel Prada-Corral, Thaddäus Wiedemer, Prasanna Mayilvahanan, Ryan Cotterell, Wieland Brendel
Artificial Intelligence · Cross-listed from cs.LG
Vero: Can AI Agents Build Formally Verified Software Repositories?
Zhe Ye, Hantao Lou, Yuechun Sun et al. (+8 more)
AI
agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code. Verified code generation, in which an
agent produces both an implementation and a machine-checked proof of its specification, offers a stronger path toward trustworthy AI-generated software. Existing
benchmarks in this direction either focus on individual functions or only evaluate proof generation with provided implementations. It is still an open question whether
agents can make coherent implementation and proof choices across real multi-module codebases. To bridge this gap, we introduce Vero, the first
benchmark to evaluate joint implementation and proof synthesis at the repository level. Vero contains 43 multi-module instances sourced from real-world repositories spanning Python, Dafny, Verus, and Coq, and covering diverse domains from cryptographic protocols to distributed systems. Each instance consists of a multi-module Lean 4 repository with predetermined API interfaces, manually curated formal specifications, and reference implementations, supporting both proof-only and code-and-proof evaluation modes. To improve
benchmark reliability, Vero also includes an audit mechanism where
agents are allowed to formally prove unsatisfiability of provided specification or incorrectness of reference code, which surfaces and corrects latent code and specification errors during curation. We evaluate frontier coding-
agent configurations with Lean toolchain access. The strongest
agent fully solves only 27 of 43 instances and closes no specifications on the hardest repositories. Vero provides a concrete testbed for measuring progress toward repository-scale verified software synthesis, where current
agents still fall short. We release the
benchmark, curation pipeline, and evaluation harness at https://github.com/sunblaze-ucb/vero.
Read the full abstract ▾
All authors Zhe Ye, Hantao Lou, Yuechun Sun, Peiyang Song, Zhengxu Yan, Timothe Kasriel, Qingyang Zhang, Kaiyu Yang, Soonho Kong, Jingxuan He, Dawn Song
Artificial Intelligence · Cross-listed from cs.LG
The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity
Martin J. Wainwright
We study masking
diffusion for discrete sampling and introduce a path-resolved measure of data geometry called the unmasking growth complexity ({UGC\xspace}). Its local increments directly control Kullback–Leibler (KL) discretization error, yielding a unified analysis of Bernoulli-subset and fixed-cardinality unmasking schemes. In log-reveal-odds coordinates, this structure yields optimized single-block and multi-block schedules, and quantifies the gains from adapting computational effort to data geometry. Crucially, we show how {UGC\xspace} increments can be estimated from samples via KL increments along coupled reveal trajectories. This leads to certified-optimal samplers that achieve a prescribed KL error with high probability and iteration complexity within a constant factor of the corresponding oracle procedure. Collapsing the \ugc path yields the aggregate {UGC\xspace} mass, which connects to classical multivariate dependence measures and complexity measures from previous analyses of discrete
diffusion. In the fine-partition limit, the squared integral of the square-root {UGC\xspace} density determines the sharp leading-order optimal Euler discretization error. Examples exhibit substantial dimension-dependent gains over coarse schedules, including $\widetilde{\Omega}(\sqrt{d})$ improvements achievable with a constant number of adaptively placed blocks.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Mimir: A Sub-2B Hierarchical Reasoning Model Trained on Permissible Data Punches Above Its Weight Class
Peter Schneider-Kamp, Jacob Nielsen, Gianluca Barmina et al. (+4 more)
Training capable
language models typically relies on web-scale pretraining followed by multi-stage post-training, creating substantial computational and data-governance barriers for settings in which training data must satisfy explicit permissibility constraints. We introduce Mimir, a 1.78B-parameter
language model based on the Hierarchical
Reasoning Model Text (HRM-Text) architecture, a recurrent-depth
transformer whose layers are split into a low-level (L) and a high-level (H) stack that are applied repeatedly in an interleaved schedule. Mimir is trained from random initialization directly on a curated mixture of instruction,
reasoning, tool-use,
multilingual, and synthetic data: 161
datasets and 70.5B
tokens per epoch for Mimir v1, extended to 103B
tokens per epoch for its continued-training successor Mimir v1.5, with synthetic replacements for sources that do not satisfy permissibility criteria. Across 20
benchmarks in English, Danish (a low-resource
language with ~6M speakers), and Math & Code, Mimir v1.5 attains the highest average score of all sub-2B models in every domain, outperforming both HRM-Text 1B and the looped
transformers Ouro 1.4B and Ouro 2.6B, and Mimir matches or exceeds the performance of models of up to 9B parameters, such as Qwen 3.5 9B and Gemma 4 E4B, on the English and Danish averages. Two independent memorisation audits indicate low memorisation risk despite multi-epoch training. Inference-time ablations show that the number of L-stack applications can be changed with graceful degradation, whereas changing the number of H-stack applications breaks the model. Our results provide evidence that hierarchical recurrent
language models can learn effectively from post-training-oriented, permissible data mixtures without conventional web-scale pretraining.
Read the full abstract ▾
All authors Peter Schneider-Kamp, Jacob Nielsen, Gianluca Barmina, Danial Namazifard, Annemette Brok Pirchert, Kenneth Enevoldsen, Lukas Galke Poech
Artificial Intelligence
AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1)
AlayaWorld Team: Kaipeng Zhang, Chuanhao Li, Yifan Zhan et al. (+14 more)
This report presents an improved version of AlayaWorld. While the backbone architecture, chunk-wise autoregressive generation scheme, and training data remain unchanged from the previous release, we substantially revise how conditioning signals are represented and integrated into the model. The new design is guided by a simple principle: conditioning signals should match the generated content as closely as possible in both latent representation and temporal structure. To this end, we make two major changes. First, we replace the previous depth-warping-based spatial
memory with a streaming 3D point-cache renderer. Second, we redesign the conditioning pipeline so that visual conditions are encoded in the same causal-VAE latent space, with temporal statistics consistent with those of the generated
video. Concretely, the new version introduces six modifications: (1) replacing static-frame image conditioning with motion-aware latent conditioning; (2) causally encoding re-rendered spatial
memory as a continuous sequence; (3) aligning the temporal-
memory window in pixel space; (4) adopting hard
memory dropout that removes
memory tokens rather than zeroing them; (5) unifying the VAE encoding and decoding protocol across training and inference; and (6) removing the camera AdaLN branch, such that viewpoint control is provided entirely through the re-rendered spatial condition.
Read the full abstract ▾
All authors AlayaWorld Team: Kaipeng Zhang, Chuanhao Li, Yifan Zhan, Yongtao Ge, Yuanyang Yin, Jiaming Tan, Kang He, Liaoyuan Fan, Mingliang Zhai, Ruicong Liu, Xiaojie Xu, Xuangeng Chu, Zhen Li, Zhengyuan Lin, Zhixiang Wang, Zian Meng, Zihui Gao
Artificial Intelligence · Cross-listed from cs.CL
Toward a Gricean Retreat: Probing LLMs for Knowledge Boundaries and Referent Specificity
Dananjay Srinivas, Saksham Khatwani and Maria Pacheco
When asked about entities outside their knowledge boundary, LLMs routinely fabricate plausible-sounding details rather than backing off to safer, more general claims. We frame this failure through a Gricean lens: a cooperative speaker who is uncertain about a referent retreats up the specificity hierarchy, trading informativeness for truthfulness. We ask whether LLMs have the ingredients to perform this retreat. Using a T-REx-based
benchmark that varies entity familiarity and referent specificity, we probe models to answer two questions: (i) do their activations encode whether a referent falls inside the knowledge boundary, and (ii) do they anticipate the specificity of the referent they are about to generate? We find that the answer to both is yes, but the two signals are not reconciled in generation. Models overwhelmingly prefer specific referents even when the entity is unknown to them, and do so even when offered correct generic alternatives. The substrate for a Gricean retreat is present, but the policy that would act on it is not. We position our findings as a first step toward Gricean
alignment, training or steering objectives that couple knowledge-boundary awareness to referent-specificity during generation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Synthetic Persona Pretraining: Alignment from Token Zero
Julian Minder, Viktor Moskvoretskii, Raghav Singhal et al. (+12 more)
As
language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical. Today,
alignment, and the assistant identity itself, are typically introduced only after pretraining, once behavioral priors are already established. This can make values a thin overlay, rather than deeply rooted, and facilitate subsequent misalignment. Pursuing a different paradigm, we introduce Synthetic Persona Pretraining (SPP), which installs the desired assistant persona from
token zero in pretraining. First, we annotate pretraining documents with value-aligned first-person reflections derived from a normative value constitution. Second, we pretrain via the standard cross-
entropy loss on standard pretraining documents as well as their reflections, which installs the desired persona among a multitude of other personas. Finally, we post-train on user-assistant dialogue data, which binds this desired persona to the assistant identity, a process we call persona binding. By pretraining models up to 3B parameters on 500B
tokens, we show that SPP improves constitution following and jailbreak robustness, and reduces the misalignment rate in out-of-distribution moral dilemmas, while preserving capabilities. Early intervention matters: compared with
alignment from
token zero, introducing SPP only at the end of pretraining yields weaker constitution adherence, does not shift value priorities, and leads to less aligned choices in dilemmas. This advantage depends on persona binding and, importantly, increases with pretraining budget. Overall, our results show that shaping values early is critical for
alignment and establish pretraining-time persona interventions as an effective approach to do so.
Read the full abstract ▾
All authors Julian Minder, Viktor Moskvoretskii, Raghav Singhal, Difan Jiao, Andy Arditi, Shaobo Cui, Yiderigun Borjigin, Kartik Bali, Stefan Krsteski, Harsh Raj, Huu Nguyen, Jannik Brinkmann, Ashton Anderson, Roland Aydin, Robert West
Artificial Intelligence
MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination
Saisha Shetty, Satvik Tripathi, Austin Lin et al. (+6 more)
We present Multi-
Agent Reasoning and Coordination (MARC), an open-source framework that replaces monolithic LLM prompting with deterministic multi-
agent orchestration for clinical
reasoning. MARC coordinates role-specialized
agents for extraction,
reasoning, answer generation, and evaluation, with explicit context passing and traceable intermediate outputs, enabling stage-wise failure attribution. We additionally introduce a Decomposer module that generates task-specific
agent prompts from a plain-
language description, eliminating manual
prompt engineering. The framework supports both API-based and local CPU-compatible deployments and is entirely configurable via YAML, without code modifications. MARC is designed to be model-agnostic, interpretable, and accessible to clinical domain experts without programming expertise. The full framework is available at https://github.com/Penn-RAIL/MARC-v1.
Read the full abstract ▾
All authors Saisha Shetty, Satvik Tripathi, Austin Lin, Colin Zhao, Theodore Kim, Don Enwerem, Jacinta Arnold, Shahriar Faghani, Tessa S Cook
Artificial Intelligence · Cross-listed from eess.SY
AaLLM: An End-to-End Analog Circuit Design Framework from Topology Generation to Sizing Using Large Language Models
Mohammed Ayman Habib, Rylan Hart and Morteza Fayazi
Analog
circuit design is a time-consuming, iterative process in a nonlinear and high-dimensional design space that relies heavily on expert intuition. Among recent developments, LLMs have introduced a promising approach by bringing natural
language reasoning to
circuit design tasks. The majority of conventional LLM-based approaches provide fragmented solutions that focus either only on sizing or
topology generation. These methods require adding specific technical knowledge manually, which is inefficient and prone to
hallucinations during
circuit sizing. Moreover, the inherent trade-off in meeting different specs makes current approaches iterative and tedious. Another shortcoming is the inability to create innovative
topologies, which may lead to sub-optimal designs due to reliance on conventional
topologies. In this paper, we present AaLLM, an open-source end-to-end multi-
agent LLM workflow that takes user specs as input and outputs the appropriate netlist, encompassing both
topology generation and
circuit sizing. AaLLM automates the creation of a relevant knowledge base from research papers and textbooks to combat tedious manual data collection. A RAG model is implemented to emulate
circuit design expertise using this knowledge base. Moreover, AaLLM uses a novel tri-
agent feedback system comprising a Designer that determines
circuit component values, a Critic that scrutinizes these values, and an Evaluator that minimizes
circuit sizing iterations by arbitrating between the other two
agents. AaLLM-generated novel
topologies achieve a figure of merit (FoM) comparable to that of known
topologies, and up to 3x higher for certain
circuits. Testing on several
circuit topologies, our results show a 3x - 4.5x decrease in the number of SPICE calls at inference when compared to SOTA multi-
agent LLM pipelines. The results also show a 40x decrease in wall-clock time compared to existing approaches.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Concept Drift Detection and Adaptive Retraining of Malware Classification Models
Christofer Washington Berruz Chungata, Martin Jurecek, Katerina Potika et al. (+2 more)
Concept drift refers to changes over time in the statistical properties of data, as compared to the data that was used to train a learning model. Machine learning models for malware detection or classification are particularly susceptible to performance degradation caused by concept drift, as attackers constantly modify existing malware. In this chapter, we analyze two machine learning-based approaches to automated concept drift detection-a novel approach based on One-Class Support Vector Machines (OCSVM) and a previously-studied technique based on Minibatch K-Means (MK-Means). For comparison we also consider Maximum Mean Discrepancy (MMD), a statistical technique for detecting changes in multidimensional data. We conduct an extensive series of experiments comparing the effectiveness of four learning models, namely, Multilayer Perceptron, Random Forest, Support Vector Machines, and eXtreme Gradient Boosting. For each of these models, we consider three distinct scenarios: A static scenario where no model retraining occurs, a periodic scenario where models are constantly retrained irrespective of concept drift, and a drift-aware scenario where models are only retrained when concept drift is detected. Under the drift-aware scenario, we analyze the tradeoff between accuracy and training efficiency using Pareto Front analysis. We find that all three concept drift detection techniques achieve classification accuracy comparable to periodic retraining, while offering substantially greater efficiency in terms of the number of models that must be retrained. In addition, drift-aware retraining based on our OCSVM technique generally outperforms the MK-Means and MMD approaches. Overall, these results provide strong evidence that we can accurately detect concept drift in malware classification models.
Read the full abstract ▾
All authors Christofer Washington Berruz Chungata, Martin Jurecek, Katerina Potika, William B. Andreopoulos, Mark Stamp
Artificial Intelligence · Cross-listed from cs.CV
MLLM-Routed Heterogeneous Ensembles for Robust Cross-Dataset Image Classification
Daniel Perkins, John Squires, Janou Milligan et al. (+2 more)
Modern image classification models excel when trained on single task-specific
datasets but often struggle to generalize across domains and difficulty levels. We propose ARMDIL, an Adaptive Router for Multi-Domain Image Classification with LLMs. ARMDIL is an ensemble that uses a
multimodal large
language model (MLLM)
agent to dynamically route each image to the most suitable
vision backbone. Our diverse ensemble employs convolutional neural networks (ResNets), self-supervised representation learners (SSL), and
vision language models (VLMs), each trained on a unified label space constructed from multiple image
datasets with differing distributions and characteristics. Empirical evaluations illuminate the distinct capabilities and vulnerabilities of each architecture across disparate visual domains. Crucially, we show that ARMDIL effectively navigates these tradeoffs, performing competitively with specialized training-based routers. Furthermore, it drastically improves adaptability by allowing new information to be integrated via simple
prompt modifications, while enhancing interpretability through natural
language reasoning traces. These advances in cross-
dataset image classification pave the way for more reliable general-purpose
vision systems such as AI assistants and autonomous
robots.
Read the full abstract ▾
All authors Daniel Perkins, John Squires, Janou Milligan, Chandra Raskoti, Linda Ungerboeck
Artificial Intelligence · Cross-listed from cs.SE
CAPRI: Contract-Aware Proof Repair for Isabelle
Jim Woodcock, Gabriel Leite, Augusto Sampaio et al. (+1 more)
We address the use of large
language models (LLMs) to help discover Isabelle proofs. An Isabelle build establishes that the submitted theory is accepted, but not that an LLM changed only what the developer authorised. We present CAPRI, a contract-aware repair workflow in which Isabelle checks the proof and an independent checker enforces a machine-readable edit contract.
Prompts, proposals, candidate repositories, diagnostics, verdicts, and hashes are retained for audit. We evaluate five workflows on twelve failed proofs from four developments, with three replicates per task and condition, giving 180 runs and 138 valid repairs. Of 144 terminal candidates accepted by Isabelle, six had modified protected text; all arose in iterative workflows that could edit a complete theory. A proof-body-only interface produced 29/36 valid repairs and no contract violations, compared with 31/36 for the corresponding full-theory workflow. One-shot repair produced 22/36, while a later prospectively frozen iterative workflow produced 32/36; these figures compare complete workflows rather than individual mechanisms. A separate post hoc OpenRouter campaign found no improvement in the designated Luna comparisons. A Sol configuration with matched demonstrations produced 33/36 repairs, compared with 29/36 in the frozen OpenAI Responses condition, but the difference was not statistically significant in a one-sided exact McNemar test ($p=0.0625$).
Read the full abstract ▾
All authors Jim Woodcock, Gabriel Leite, Augusto Sampaio, Ran Wei