Artificial Intelligence · Cross-listed from cs.LG
MemCalib: Benchmarking and Optimizing Memory Use in LLM Agents
Ruike Cao, Fanyu Zhao, Fugen Yao et al. (+5 more)
The effectiveness of
agent memory ultimately depends on whether the underlying LLM gives each
memory in context an appropriate degree of influence over its response. Yet this capability has remained largely overlooked. To assess this capability, we introduce MemCalib, a
benchmark grounded in realistic
memory-system scenarios for evaluating
memory use and advancing optimization
algorithms. Results on the MemCalib test set reveal that frontier open- and closed-source models struggle to use
memory appropriately. They frequently over-use or under-use
memory rather than matching each proposition's actual use to its target level, leading to biased, low-quality responses. Experiments with common post-training
algorithms, including group relative policy optimization and on-policy self-
distillation, further reveal a clear directional skew: trained models improve in one direction while deteriorating in the other. We therefore propose MemCalib-RL, an ordered bidirectional counterfactual credit-assignment
algorithm that separates over- and under-use signals and localizes their credit to response
tokens through exact atom ablation. Results across model families and scales (Qwen3-8B, Ministral-3-8B-Instruct, and Qwen3.5-35B-A3B) show that MemCalib-RL achieves the best overall performance while better balancing over-use and under-use, with gains generalizing beyond MemCalib in external
benchmark evaluation. Further experiments support its design choices and robustness and provide insight into its training dynamics.
Read the full abstract ▾
All authors Ruike Cao, Fanyu Zhao, Fugen Yao, Liang Dong, Jian Xu, Yifei Zhao, Han Zhang, Li Xiao
Artificial Intelligence · Cross-listed from cs.CL
Taramandal-GPT: Enhancing Astrodynamics Problem-Solving with Knowledge Retrieval and Structured Thinking
Akhil Sharma, Jatin Gupta and Ali Imam Abidi
Large
language models (LLMs) have shown remarkable progress in natural
language understanding, yet their effectiveness in specialized fields like astronomy and astrodynamics remains limited due to challenges in multi-step
reasoning, symbolic manipulation, and domain-specific terminology. To address this, we present Taramandal-GPT (Constellation-GPT), a domain-adapted framework built on the Qwen3-8b backbone, enhanced with a
Retrieval-Augmented Generation (RAG) pipeline and a fallback mechanism for improved contextual precision. We evaluate it on the Astrodynamics Problems
Benchmark (APBench), a
dataset of 299 questions covering foundational to advanced levels of space science. Using a dual evaluation method - numeric margin-based scoring and semantic similarity assessment - Taramandal-GPT achieves competitive performance against state-of-the-art open- and closed-source models, with notable strength in thinking-intensive tasks. These results highlight the value of specialized LLMs for domains demanding accuracy and interpretability, positioning Taramandal-GPT as a step toward reliable Artificial Intelligence (AI) assistants for astrophysics, spacecraft engineering, and space exploration.
Read the full abstract ▾
Artificial Intelligence
Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation-Level Enforcement
Xutao Mao, Jianing Zhu, Jinman Zhao et al. (+4 more)
Reinforcement learning (RL) has substantially improved the
reasoning capabilities of
vision-
language models (VLMs), yet it can induce chain-of-thought (CoT) obfuscation, an operational, non-intentional regime where models achieve high accuracy while producing
reasoning traces that are less grounded and harder to monitor. While prior work documents this decay at the behavioral level, the underlying representational correlates of such drift remain poorly understood. In this work, we find that obfuscation is accompanied by a representational shift, where RL-induced optimization makes task-agnostic template features less separable from visually grounded content in the model's activation space. Based on this insight, we propose TAME, an activation-level intervention framework that leverages Sparse Autoencoders (SAEs) to regularize VLM internal features during RL training. Specifically, TAME utilizes an anti-obfuscation feedback loop to reduce behavioral obfuscation and applies an asymmetric SAE constraint to specific internal directions, penalizing template activations while preserving visual evidence. By directly intervening on the features associated with obfuscation, our method improves the transparency and visual grounding of
reasoning traces. Experiments on the VIRL-39k and SPA-VL
benchmarks across two model families show that TAME improves CoT monitorability (by up to +30.9 points on VIRL and +16.7 points on SPA-VL over GRPO), while largely preserving task accuracy and general-capability performance across four standard VLM
benchmarks, with task-specific trade-offs. Our code is available at https://github.com/henrymao2004/TAME.
Read the full abstract ▾
All authors Xutao Mao, Jianing Zhu, Jinman Zhao, Tongliang Liu, Xiaowen Chu, Cong Wang, Bo Han
Artificial Intelligence · Cross-listed from cs.LG
Hessian Rank Constraint for Learning Structure of Nonlinear Latent Variable Models
Zijian Li, Ruichu Cai, Feng Xie et al. (+7 more)
Uncovering latent variables and their causal relations from observed data is a fundamental yet challenging problem. Existing methods often rely on restrictive assumptions, such as linear relations or invertible mixing functions. To better address this problem under general nonlinear mixing procedures, we propose a condition called the cross-Hessian Rank Constraint (HRC), which serves as a primitive rank-based tool for nonlinear latent causal discovery. In particular, we show that a rank-based property arises from the cross-Hessian of the observed-data log-density in the nonlinear case, revealing information about the latent variables, and reduces to the Tetrad constraints in the linear Gaussian case. More specifically, when two groups of observed variables are d-separated by a set of lower-dimensional latent variables, the rank of this cross-Hessian is equal to the dimension of the latent variables, under a mild affine derivative assumption on the conditional log-density derivatives. This assumption can be naturally satisfied when the noise level is low or the relevant nonlinearity is moderate. As a downstream application, we instantiate HRC in the pure one-factor measurement setting for locating latent variables and recovering their causal structure up to Markov equivalence. Experimental results on synthetic and real-world
datasets support the theoretical claims.
Read the full abstract ▾
All authors Zijian Li, Ruichu Cai, Feng Xie, Xinshuai Dong, Haoyue Dai, Yuewen Sun, Yujia Zheng, Guangyi Chen, Yingyao Hu, Kun Zhang
Artificial Intelligence · Cross-listed from cs.CL
Memory vs. Context? Influential Factors of Factual Recall in Language Models
Guilhem Fouilhé, Nicholas Asher and Philippe Muller
We reproduce and stress-test the work of Yu et al. (2023), who characterize how
language models (LMs) arbitrate between memorized knowledge and contradictory in-context statements. We replicate their world-capitals experiments on 31 models spanning Pythia, GPT-2, Qwen3, and Ministral families, including base and post-trained variants, and extend evaluations to five additional knowledge relation types from the ParaConflict
dataset. We empirically confirm most of their original findings: larger models and higher-frequency entities tend to favor memorized answers, with substantial family-level variance. However, several conclusions do not generalize cleanly: entity-frequency effects disappear on Qwen3-14B and 32B; post-training shifts the
memory-context trade-off inconsistently across families; question phrasing alone can change a model's reliance on memorized knowledge by up to 80 percentage points; and semantically unrelated prose can mimic coherent supporting context. Our results clarify where Yu et al.'s claims hold and to what extent they generalize to other
prompts.
Read the full abstract ▾
Artificial Intelligence
Recovering Lost Details: Multi-Scale Frequency Compensation for Long-Term Time Series Forecasting
Runmin Zou, Siyi Xie, Yaohui Huang et al. (+1 more)
Long-term time series
forecasting has made significant progress by leveraging multi-scale information to capture hierarchical temporal patterns and model long-range dependencies. However, temporal downsampling in existing multi-scale methods inevitably smooths detailed temporal fluctuations, and this information loss is further aggravated by their emphasis on dominant trends across scales, resulting in insufficiently expressive representations. To address this, we propose a Multi-Scale Wavelet Mixing (MWMixer) model, which incorporates a Bidirectional Frequency-Bands Mixing strategy to recover lost temporal details across scales, enabling complementary cross-scale information interactions. Then, a Dynamic Scale-Adaptive Fusion module learns time-varying weights for each scale to fuse multi-scale forecasts into the final prediction, enhancing the flexibility of multi-scale aggregation. In addition, a cross-scale consistency loss aligns each coarse-scale prediction with the interval-averaged fine-scale outputs, while a multi-scale supervision loss enforces prediction accuracy at each scale, promoting consistent learning across scales. Extensive experiments on seven real-world
datasets demonstrate that MWMixer achieves competitive performance in long-term
forecasting.
Read the full abstract ▾
All authors Runmin Zou, Siyi Xie, Yaohui Huang, Yun Wang
Artificial Intelligence · Cross-listed from cs.LG
Opinion Leader Dynamics: How Sparse Attention Shapes Token Clustering
Jingkun Liu and Yue Song
Sparse
attention reduces the quadratic cost of global self-
attention while retaining strong empirical performance, but how its restricted interactions shape the
evolution of
token representations remains theoretically underexplored. Modeling
tokens as particles on the unit sphere, we introduce opinion leader dynamics, a framework that identifies two mechanisms through which
token groups converge internally while maintaining distinct limiting directions. In the explicit model, fixed representatives induce a potential that attracts
tokens toward distinct local maxima. In the implicit model, disconnected interaction groups evolve toward separate consensus directions. We formulate both models as reverse Wasserstein gradient flows and establish exponential convergence under suitable conditions. We further connect these theoretical predictions to
token evolution in frontier sparse-
attention LLMs that motivate our framework. Across four
benchmarks, Kimi-K3, MiniMax-M3, and DeepSeek-V4-Flash consistently exhibit clearer cluster separation and higher clustering scores than the dense-
attention model GLM-4.7-Flash in projected
token representations. These observations support the relevance of the predicted multiple-group structure to trained frontier LLMs, while finite-particle simulations illustrate the theoretical convergence behavior. Together, our results connect restricted
token interactions to distinct group-level attractors, providing a dynamical account of how sparse
attention can support
alignment within groups while preserving separation between them.
Read the full abstract ▾
Artificial Intelligence
SKstars at SHROOM: Visions Agreement-Guided Ensembling of Zero-Shot and LoRA-Adapted Vision–Language Models
Ali Athar, Imran Ahsan and Joon-Yong Jung
This paper describes the SKstars submission to SHROOM-
Visions 2026, a shared task on fine-grained
hallucination detection in large
vision-
language model outputs. The task requires systems to identify hallucinated character spans, assign
hallucination categories, and provide confidence estimates for their predictions. Our approach combines zero-shot predictions from Qwen2.5-VL-72B-Instruct with those of a LoRA-adapted Qwen2.5-VL-7B-Instruct model. The outputs of the two models are integrated through a lightweight ensemble procedure, followed by span refinement and confidence adjustment. We evaluate the main system components on a small internal development subset and report the performance of the submitted system on the official English test set. SKstars achieved a Cor+Lbl score of 0.2902, ranking 15th among 29 teams, and obtained Cor and IoU scores of 0.3642 and 0.3151, respectively, ranking 18th on both metrics. The results show that combining a large zero-shot model with a smaller adapted model provides a practical framework for
multilingual and fine-grained
hallucination localization, while also highlighting the difficulty of transferring development-set improvements to hidden test data. Code and predictions: https://github.com/aliathar1401/SK-
Stars-shroom-
visions-2026
Read the full abstract ▾
Artificial Intelligence
LIMIT: Less Is More for Instruction Tuning in Text-to-SQL
Haoyuan Ma, Hengwei Liu, Linjuan Wu et al. (+2 more)
Large
language models have achieved remarkable progress on Text-to-SQL through
reasoning-enhanced fine-tuning, yet existing approaches predominantly rely on massive instruction corpora under the assumption that scale drives performance. We challenge this paradigm by investigating a fundamental question: what is the minimal data requirement for effective Text-to-SQL instruction tuning? We propose LIMIT(Less Is More for Instruction Tuning in Text-to-SQL), a data-centric framework that demonstrates strong database
reasoning can emerge from an extremely compact training set when examples are strategically selected. LIMIT operates through four stages: difficulty-aware filtering that identifies samples within the model's learning frontier, chain-of-thought synthesis with consistency-based selection, multi-dimensional quality scoring via LLM-as-judge, and genetic
algorithm optimization that jointly maximizes schema coverage and sample quality. On the BIRD and Spider
benchmark, LIMIT selects only 796 and 863 samples while achieving 100% table coverage, enabling Qwen3-8B to reach 69.1% and 88.9% execution accuracy.This result surpasses methods trained on 20 times more data and establishes a new state-of-the-art among open-source approaches. Our findings suggest that careful data curation, rather than scale, is the key to efficient Text-to-SQL learning.
Read the full abstract ▾
All authors Haoyuan Ma, Hengwei Liu, Linjuan Wu, Yongliang Shen, Weiming Lu
Artificial Intelligence
CREDO: Variance-Guided Rubric Evolution for Replay-Corrected Credit Assignment
Xuchun Hu
Long-horizon
language agents receive sparse terminal feedback, while intermediate rubrics provide structured but potentially misspecified assessments of progress. In resettable training environments, counterfactual continuation rollouts can measure local credit, but exhaustive replay is costly. We propose Credo, a framework that couples evolving semantic rubrics with selective, execution-based credit correction. A frozen judge maps visible transitions to rubric features, and a credit head predicts the change in expected terminal reward associated with the realized transition. Independently sampled two-sided replays correct prediction residuals using their recorded inclusion probabilities. We derive conditional unbiasedness and a variance decomposition that connects two design choices: which rubric features to retain, and where to allocate a fixed expected replay budget. The resulting criterion weights prediction errors by policy-score sensitivity and missing replay coverage; its allocation rule additionally accounts for continuation cost. We also describe a practical mixture with terminal leave-one-out advantages and distinguish its clipped,
token-normalized PPO implementation from the ideal policy-gradient
estimator. This preliminary report provides the method, proofs, an exact finite-model audit, and a controlled evaluation protocol. It makes no claim of empirical superiority on
language-
agent benchmarks.
Read the full abstract ▾
Artificial Intelligence
APEXA: Execution-Integrity Enforcement for Multi-Agent LLM Automation of Synchrotron Data Reduction
Pawan K. Tripathi, Hemant Sharma, Andrew Chuang et al. (+1 more)
LLM
agents can make expert scientific workflows accessible through natural
language, but a plausible response does not establish that the requested computation ran. This matters at synchrotron facilities, where calibration and integration are multi-step operations over terabyte-scale
datasets. We present APEXA, a deployed framework coordinating 61 tools for synchrotron data reduction. A deterministic execution-integrity guard prevents it from returning results for tool calls that did not execute, and the same tool layer enforces motor safety: across 50
adversarial scenarios and four models, it produced 0/200 violations against a simulated EPICS controller, versus 15/200 for a
prompt-only baseline. We also introduce APEXA-Bench, 58 facility tasks organized by scientific correctness and physical consequence. On real APS beamline data, one
prompt recovered detector geometry and integrated a full attenuation and exposure sweep. Trustworthy scientific
agents need deterministic validation of execution, not model-side assurances. We release the framework,
benchmark, and traces.
Read the full abstract ▾
All authors Pawan K. Tripathi, Hemant Sharma, Andrew Chuang, Mathew J. Cherukara
Artificial Intelligence · Cross-listed from cs.DC
MCP-GRANITE Benchmark: GRANularity Interface TEsting for MCP-Based LLM Agents
Demetris Paschalides, Moysis Symeonides, George Pallis et al. (+1 more)
As LLM
agents increasingly interact with external tools through standardized protocols such as MCP, tool-interface design becomes a critical yet underexplored factor. How fun{\psi}tionality is decomposed into tools affects whether an
agent can select the right tool and construct valid arguments. This choice is especially consequential at the edge, where resource constraints limit which models can run locally and scaling up is often not an option. We present MCP-GRANITE, an open-source extensible
benchmark framework that treats tool-interface granularity as a controlled variable for MCP-based
agents, evaluated under edge and IoT scenarios. It comprises 81 multi-step scenarios across 9 domains, instantiated at 4 granularity levels from fine-grained primitive tools to a single tool. We evaluate 9 locally deployed models (268M-20.9B parameters) across 8,748 trials using task completion, tool selection F1, argument accuracy, latency, and resource-usage metrics. Results show that a 4-tool interface offers the best trade-off, improving task completion by 16.4% over fine-grained primitives and 33.6% over a single monolithic tool, while nearly doubling argument accuracy. Model size is only weakly correlated with task completion and strongly with latency, while its association with argument accuracy is less robust, and a 3.2B model at the optimal granularity outperforms a 20.9B model at a mismatched one. These findings identify tool-interface granularity as a key design parameter for MCP-based
agents.
Read the full abstract ▾
All authors Demetris Paschalides, Moysis Symeonides, George Pallis, Marios D. Dikaiakos
Artificial Intelligence · Cross-listed from cs.CL
TAC-Time: Texts as Channels For Multimodal Time Series Forecasting
Jiayi Liang, Xiaotian Gu, Xinyu Xie et al. (+2 more)
Most existing time series
forecasting methods rely solely on numerical observations, overlooking rich contextual information from auxiliary texts. Recent
multimodal approaches attempt to incorporate textual signals, but they often treat text as static features or use large
language models as
forecasting backbones, limiting their ability to capture temporal dynamics and increasing computational cost. To address these challenges, we propose TAC-Time, a unified framework that transforms textual information into additional temporal channels. By modeling text features jointly with numerical sequences in a shared temporal backbone, TAC-Time preserves temporal continuity and periodic structures while remaining efficient and scalable. This formulation also enables systematic interpretability analyses. We show strong cross-modal dependencies through
attention and frequency-domain analyses, and identify predictive textual signals whose correlation-aware
alignment yields partial
forecasting improvements. Extensive experiments on real-world
multimodal benchmarks demonstrate that TAC-Time outperforms prior methods.
Read the full abstract ▾
All authors Jiayi Liang, Xiaotian Gu, Xinyu Xie, Yuanbin Wu, Xiaoling Wang
Artificial Intelligence · Cross-listed from cs.IR
Graded-Relevance Composed Multimodal Retrieval for E-commerce Visual Search at Scale
Anubhav Gupta, Hrushikesh Mohapatra, Prijith Chandra et al. (+6 more)
Visual search on large e-commerce catalogs must serve both "similarity" queries that ask for items resembling an uploaded image and "modifier" queries that comprise an image and text describing a desired modification (e.g. a color change or style swap). The latter is the setting known as composed image
retrieval (CIR). Existing CIR methods, however, treat relevance as binary and train on triplets with a single positive target - a poor fit for real catalogs where many candidates partially satisfy a user query and ranking across that partial-match spectrum drives the customer experience. We propose a methodology for training CIR retrievers on graded relevance, consisting of: (i) a VLM to curate training data, generating both queries (object detection + modifier synthesis) and 4-level relevance labels without manual annotation, (ii) an iterative relevance-feedback loop that expands the training set by mining hard negatives from the in-training retriever, and (iii) a hierarchy-aware angular objective to train the retriever directly on the graded labels rather than collapsing them to a binary split. We call this methodology GradCIR and instantiate it on a PaliGemma2 bi-encoder trained on 3.5M graded pairs curated from raw Walmart catalog data. A controlled graded-vs-binary ablation isolates the supervision granularity and shows lift of 4.9%-5.9% in NDCG@10. The same recipe applied to other
multimodal encoders lifts early-fusion backbones by up to 8.5% NDCG@10. On the public FashionIQ
benchmark, GradCIR (applied to PaliGemma2) reaches 0.6703 average recall when fine-tuned, slightly ahead of the strongest peer-reviewed supervised baseline we compare against, and matching or exceeding all published CLIP-L-class zero-shot CIR methods. The system is deployed in production at Walmart, where it's serving live visual-search user traffic.
Read the full abstract ▾
All authors Anubhav Gupta, Hrushikesh Mohapatra, Prijith Chandra, Asish Mohapatra, Anuj Garg, Arvind Maan, Sudip Datta, Venkat Bulusu, Sitesh Kumar Jalan
Artificial Intelligence · Cross-listed from cs.CV
STAR: Scene- and Task-Aware 4D Radar Preprocessing Towards End-to-End Cognitive Radar
Seung-Hyun Song, Dong-Hee Paek and Seung-Hyun Kong
Four-dimensional (4D) Radar has emerged as a key sensor for environmental perception, providing range, azimuth, elevation, and Doppler measurements while remaining robust to illumination changes and adverse weather conditions. However, conventional Radar preprocessing methods, such as constant false alarm rate (CFAR) detection, select measurements primarily based on signal-level criteria and may therefore discard information valuable for downstream perception during point cloud generation. In addition, existing 4D Radar perception pipelines typically optimize Radar data processing and downstream perception independently, preventing task objectives from directly guiding the preprocessing stage. To address these limitations, we propose a Scene- and Task-Aware Radar (
STAR) Preprocessor together with an end-to-end training framework. The
STAR Preprocessor incorporates scene context and downstream task objectives to generate task-relevant Radar points, enabling the Radar representation to be optimized directly for perception. On the K-Radar
benchmark, the proposed method achieves 74.3 AP, outperforming the previous state of the art by 5.6 AP points. Furthermore, applying the task-relevant points generated by
STAR to various existing 3D detectors improves detection performance in most evaluation settings and yields an overall positive average gain over point clouds produced by conventional preprocessing.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.DB
Data Agents: Agentic Data Systems
Guoliang Li, Peiyao Zhou, Xuanhe Zhou et al. (+3 more)
Traditional data systems face profound limitations in the AI era, relying on human-crafted pipelines, lacking semantic understanding of heterogeneous data, and operating through rigid, reactive processing. To address these challenges, we propose a new paradigm called the Data
Agent, designed to manage, process, and analyze data with minimal human intervention. Data
agents autonomously execute a wide range of data-related tasks, transforming traditional data systems by shifting from manual design to autonomous orchestration, from literal manipulation to semantic interpretation, and from reactive to proactive processing. Our Data
Agent system includes six components: semantic data organization, semantic operators, agentic pipeline orchestration and optimization, feedback-driven refinement,
memory management, and proactive adaptation. Building on this foundation, we also develop two specialized
agents: the data analytics
agent and the data science
agent. Experiments on real
benchmarks demonstrate significant performance gains of our data
agent over state-of-the-art methods. We identify open challenges to guide future research in building fully autonomous data systems.
Read the full abstract ▾
All authors Guoliang Li, Peiyao Zhou, Xuanhe Zhou, Ji Sun, Yuyu Luo, Ju Fan
Artificial Intelligence
Self-Healing Harness for Runtime Oversight of Agent Self-Modification
Sina Tayebati, Divake Kumar, Nastaran Darabi et al. (+2 more)
LLM
agents can change their own future behavior, raising a basic control question of which self-generated changes should be allowed to persist. We formulate this as admission control for self-modification. The
agent may propose changes to its operating instructions, while an external runtime gate controls persistence. We implement this principle as a model-agnostic self-healing harness that runs a Detect, Notice, Heal, Validate loop around an otherwise unmodified
agent. The
agent authors candidate behavioral rules in an external workspace, where they receive provisional execution authority during evaluation and acquire persistent cross-episode authority only after measured improvement on the triggering failure without regression beyond a fixed margin on protected cases. Replay provides matched evidence when available, forward trials provide a weaker fallback, and a corpus-level guard re-tests the accumulated active rule set. Across 16 matched Baseline and Harness runs spanning AppWorld, Terminal-Bench, and $\tau^2$-Bench, the gate rejected 383 replay-decided proposals. Of these, 211 (55%) improved their triggering failure while degrading a case that previously worked. This shows that locally beneficial self-modifications can introduce collateral regressions often enough to materially affect gate decisions, providing direct empirical motivation for external admission control. Task-completion score is higher under the Harness in all 16 pairs, with two paired bootstrap intervals excluding zero, while repeated-trial reliability is higher in 12 pairs, tied in 4, and lower in none. Because adaptation modifies the policy-inducing context while leaving model weights fixed, admitted changes remain inspectable, reversible, and compatible with closed-weight models.
Read the full abstract ▾
All authors Sina Tayebati, Divake Kumar, Nastaran Darabi, Ranganath Krishnan, Amit Ranjan Trivedi
Artificial Intelligence · Cross-listed from cs.CV
Action-Slot: Structured Action-Centric Representation Learning for Multi-Agent Atomic Activity Understanding
Yu-Ho Chang, Chi-Hsi Kung, Yi-Hsuan Tsai et al. (+1 more)
Atomic activity understanding aims to recognize and localize structured traffic behaviors that jointly encode motion patterns and their grounding in road
topology. Unlike conventional action recognition, atomic activities are multi-
agent, multi-label, and
topology-aware: multiple activities co-occur while many
agents remain inactive. We introduce Action-Slot, a structured action-centric representation learning framework. Slot
attention is widely used for object-centric decomposition, but its permutation-invariant design and object-level inductive bias are misaligned with atomic activity semantics. We reformulate slot learning as structured activity decomposition through three designs: (1) category-aligned action slots that anchor slots to predefined activity categories, (2) parallel spatio-temporal slot updating for holistic
video-level
reasoning, and (3) background and negative-slot regularization that enforces competition between foreground activities and irrelevant regions. Together these establish an activity-centric inductive bias that disentangles concurrent and asynchronous activities directly from raw
video. Beyond recognition, the learned representations encode transferable spatio-temporal grounding signals. We further propose an
attention-difference-based pseudo mask selection framework that suppresses false positives by measuring
attention changes before and after candidate region removal, enabling weakly supervised localization without dense annotations. To support systematic evaluation, we introduce TACO, a balanced synthetic
dataset with full atomic activity coverage and pixel-level annotations. Experiments on OATS, TACO, and annotated nuScenes show superior recognition, strong sim-to-real transfer, and state-of-the-art weakly supervised localization.
Read the full abstract ▾
All authors Yu-Ho Chang, Chi-Hsi Kung, Yi-Hsuan Tsai, Yi-Ting Chen
Artificial Intelligence · Cross-listed from cs.RO
ActiveArena: Benchmarking and Understanding Active Perception in Robotic Manipulation
Yibo Li, Enshen Zhou, Rui Chen et al. (+7 more)
Active perception and manipulation are crucial for
robots to interact with complex scenes. Existing
benchmarks struggle to evaluate how
robots effectively acquire and maintain information in
memory in an active manner. To this end, we introduce ActiveArena-Sim, an active-perception simulator with controllable viewpoints and large-scale workspaces as the foundation. Built on this, we propose ActiveArena-Bench, which comprises 35 tasks across 5 fine-grained categories, covering visual exploration and interactive information acquisition. Each task is difficult to solve from passive observations alone, requiring multi-round evidence acquisition and
memory-based
reasoning. The
benchmark provides rich
memory annotations, standardized training data, and ID/OOD protocols featuring disjoint scenes, unseen distractor configurations, and novel backgrounds. Moreover, we present ActiveArena-VLA, a modular suite of 13
vision-
language-action configurations for controlled studies of
memory writing,
memory capacity, proprioceptive state, subtask supervision, and high-level planning in active perception.
Benchmark results reveal a substantial ID-OOD gap: uniform
memory sampling, increased
memory capacity under reliable write policies, proprioceptive inputs, and subtask supervision improve OOD generalization, while planner-guided
memory management and decision-making achieve performance close to the best-performing configuration using only sparse
memory. ActiveArena thus provides a unified testbed to develop and diagnose models for active perception and manipulation.
Read the full abstract ▾
All authors Yibo Li, Enshen Zhou, Rui Chen, Yanjun Ding, Mengzhen Liu, Yi Han, Jiabo Zhan, Lipeng Wang, Shanghang Zhang, Lu Sheng
Artificial Intelligence
EDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation
Harshavardhan Abichandani, Penny Chong, Jiyuan Shen et al. (+7 more)
Tool-calling LLM
agents are increasingly deployed in enterprise applications. However, effective evaluation and optimization require high-quality, diverse task
datasets that are often difficult to obtain due to
privacy and other constraints. Existing synthetic task generation methods often produce generic tasks that ignore an
agent's underlying state or database and fail to reflect real-world usage diversity. We propose EdgeGen, a synthetic task generation framework that extracts compliance rules from an
agent's specification and uses them to generate database-grounded edge-case tasks designed to violate these rules. When combined with existing synthetic data generation techniques, EdgeGen enables
agent improvement through finetuning and harness optimization. The resulting pipeline forms a fully automated closed-loop system that requires no human annotation. Finetuning on data generated by EdgeGen yields a consistent mean progress improvement of 2 percent to 42 percent on tau2bench airline domain, while other baseline methods show degradation for some models. On the other hand, for harness optimization, our method shows a mean progress improvement of 10 percent and 30 percent over the human-curated and base harnesses, respectively, for the Gemma-4-e4b model.
Read the full abstract ▾
All authors Harshavardhan Abichandani, Penny Chong, Jiyuan Shen, Gunraj Singh, Ashutosh Hathidara, Marcus Duigan Xing Yu, Jane Lo, Atin Ghosh, Yipeng Li, Daniel Dahlmeier
Artificial Intelligence · Cross-listed from cs.LG
Reinforcement Learning under State and Outcome Uncertainty: A Foundational Distributional Perspective
Larry Preuett, Qiuyi Zhang and Muhammad Aurangzeb Ahmad
In many real-world planning tasks,
agents must tackle uncertainty about the environment's state and variability in the outcomes of any chosen policy. We address both forms of uncertainty as a first step toward safer
algorithms in partially observable settings. Specifically, we extend Distributional Reinforcement Learning (DistRL)-which models the entire return distribution for fully observable domains-to Partially Observable Markov Decision Processes (POMDPs), allowing an
agent to learn the distribution of returns for each conditional plan. Concretely, we introduce new distributional Bellman operators for partial observability and prove their convergence under the supremum p-Wasserstein metric. We also propose a finite representation of these return distributions via psi-vectors, generalizing the classical alpha-vectors in POMDP solvers. Building on this, we develop Distributional Point-Based Value Iteration (DPBVI), which integrates psi-vectors into a standard point-based backup procedure-bridging DistRL and POMDP planning. By tracking return distributions, DPBVI lays the foundation for future risk-sensitive control in domains where rare, high-impact events must be carefully managed. We provide source code to foster further research in robust decision-making under partial observability.
Read the full abstract ▾
Artificial Intelligence
When More Evidence Hurts: Publication-Bias Drift and Principled Stopping for Biomedical Causal Search
Fred Sun and Shangqi Guo
Automated biomedical evidence synthesis depends on retrieving published studies, but the biomedical literature is systematically skewed toward positive findings. Deeper
retrieval can therefore make a system more likely to falsely infer benefit when the true effect is null. We formalise this phenomenon as evidence drift and prove that, under a standard publication-bias model, the false-positive probability on null-effect queries follows a strictly increasing large-sample envelope in
retrieval depth, approaching one. Empirically, on a held-out test set of 140 Cochrane-derived queries, drift rises monotonically from 7.9% to 15.7% as the
retrieval budget grows from 3 to 20 steps, and concentrates in the null-effect class. We present DACG-
agent, a drift-aware causal-graph
agent that incrementally builds a causal knowledge graph from PubMed abstracts and applies a two-layer stopping policy with complementary roles: a KL-divergence monitor that detects posterior convergence (the accuracy layer), and a Bradley–Terry process reward model (PRM) whose online decline detection halts
retrieval once evidence quality peaks (the efficiency layer). Against full-budget
retrieval, DACG-
agent reduces evidence drift from 15.7% to 6.4% and improves null-effect accuracy by 21 percentage points (40.0%$\to$61.4%) while using 67% fewer
retrieval steps; overall accuracy rises from 61.4% to 69.3% (95% CI 61–77). A simulation confirms the drift result transfers from the analysed vote-counting aggregator to the deployed noisy-OR one.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.HC
WidgetVA: A Widget-Centric Framework and Benchmark for Agentic Visual Analytics
Yutong Chen, Zhike Tang, Zhihao Mai et al. (+4 more)
Visual analytics (VA) enables sensemaking through interactive visualization, but effective analysis often requires experts to translate high-level intents into long sequences of interface operations and iteratively interpret visual feedback. We study whether modern
vision-
language models (VLMs) can take on this role as autonomous VA operators that observe the interface, plan multi-step exploration, execute interactions, and adapt based on intermediate visual feedback. To support systematic development and evaluation, we first introduce WidgetVA, a widget-centric agentic VA framework that standardizes interactive components as structured widgets with unified action (e.g., filter and zoom) and perception-query (e.g., selection summaries) APIs. This standardization supports two modes of system construction: wrapping an existing VA system to make it
agent-operable without rebuilding it, and composing a new system from widgets as modular building blocks. To help
agents coordinate across widgets rather than plan each interaction from scratch, each widget further packages reusable analytical workflows, giving
agents more than a bare set of callable functions to plan over. Building on this framework, we present WidgetVABench, a
benchmark of single- and multi-widget VA tasks that require
agents to perform multi-step interactions to uncover evidence and produce verifiable results. Each task also provides fine-grained reference annotations so that WidgetVABench can score Answer, Reference Trace Similarity, and State separately rather than collapsing
agent performance into one success score. Experiments across multiple VLMs show that our framework provides an effective scaffold for agentic VA, while the diagnostic measures expose persistent limitations for future work. The WidgetVA framework and WidgetVABench have been released in https://github.com/Hiverwin/widgetva.
Read the full abstract ▾
All authors Yutong Chen, Zhike Tang, Zhihao Mai, Zhihao Shuai, Danli Luo, Jing Xu, Weikai Yang
Artificial Intelligence
DocMIDE: Learning Multi-Hop Implicit Derivation in Visually Rich Documents
Jeremy Cerwin Wang, Wai Kit Wong and Jeff Kai Tai Tang
Real-world document processing systems rely on rigid, predefined schemas, yet critical target fields often lack direct visual counterparts on the page. Extracting these implicit values requires multi-hop derivation, such as aggregating sub-categories or
reasoning over visual marks. While existing methods handle explicit text spans or simple implicit queries, they fail at multi-hop visual
reasoning even after standard fine-tuning: models retrieve incorrect visual evidence, or retrieve it correctly and then skip the intermediate steps of the derivation. To address this, we introduce DocMIDE, a fine-tuning framework that trains compact
vision-
language models to retrieve visual evidence explicitly before deriving an answer. DocMIDE constrains generation to a plan-retrieve-derive structure and optimizes it with Group Relative Policy Optimization under a four-component, rule-based reward that scores output format, the retrieved evidence block, every intermediate derivation step, and the final value against a verified reference trace. On a 4,151-pair implicit extraction
benchmark, DocMIDE raises accuracy from 70.8% to 95.9% on Qwen3.5-4B from only a small set of annotated examples, and transfers to a second backbone architecture. Supervised demonstrations alone do not close this gap at any budget we tested; rewarding the intermediate steps is what does.
Read the full abstract ▾
Artificial Intelligence
Incremental Consistency Execution for Autonomous Intelligent Systems
Cheng Li, Jiexiong Liu, Yixuan Chen et al. (+1 more)
Long-horizon autonomous intelligent systems rely on heterogeneous components such as large
language models, databases, external APIs, and rule engines, while their external states continuously change during execution. Re-executing the entire workflow after every change introduces substantial redundant computation. This paper proposes an incremental consistency execution method based on task fact contracts, field-level dependency masks, and state perturbation result invariant domains. After an initial verified execution, the system constructs conservative invariant domains for critical inputs and uses them to determine whether downstream results can be safely renewed without re-invoking expensive components. When re-execution is required, only the smallest affected output fields are recomputed, and an equivalence barrier prevents unnecessary downstream propagation. A submission-time version consistency gate further ensures the safety of side-effecting actions. Experiments on industrial fault diagnosis, enterprise analytics, and LLM-based multi-tool assistants show that the proposed method significantly reduces expensive component calls and end-to-end latency while maintaining high consistency and low incorrect-reuse rates.
Read the full abstract ▾
All authors Cheng Li, Jiexiong Liu, Yixuan Chen, Ziheng Huang
Artificial Intelligence · Cross-listed from cs.LG
FlashBoB: I/O-Efficient Exact Backward-over-Backward for Softmax Attention
Anthony Givans, Michael Crawshaw and Mingrui Liu
Transformer models built on the
attention mechanism have become a central building block in modern deep learning, yet softmax
attention remains a major bottleneck for long-context workloads. While FlashAttention makes the forward and first backward passes I/O-efficient, it does not support backward-over-backward (BoB), which enables exact differentiation through the backward pass for applications such as second-order optimization, test-time training, gradient-based
memory, and meta-learning. Existing BoB implementations either materialize large intermediate tensors or exhaust GPU
memory at long sequence lengths. We present FlashBoB, an exact, I/O-efficient
algorithm for BoB in softmax
attention that keeps computation within on-chip tiles and avoids all $N \times N$ intermediate tensors, where $N$ is the sequence length. The key insight is a hierarchical affine structure in the softmax double backward: two row-wise scalars determine all outputs through affine transformations. This yields a two-pass schedule with bounded on-chip static random-access
memory (SRAM) usage and minimal off-chip high-bandwidth
memory (HBM) traffic. FlashBoB achieves $\Theta(N^2 d^2/M)$ HBM traffic ($d$ is the head dimension and $M$ is the
memory size) and, within the standard FlashAttention-style score-recomputation model, matches the inherited large-cache lower bound for exact forward
attention. Empirically, it scales exact
attention BoB to $N=262\text{K}$ on a single A100 80GB GPU, where prior PyTorch exact baselines fail by $N=16\text{K}$, and is up to $6.3\times$ faster than FlashBack. These results make exact second-order
attention practical at long-context sequence lengths where prior implementations cannot run efficiently.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
From Bits to Beliefs: Recoverable Semantic Fingerprints for Black-Box Verification of Large Language Models
Jiaxin Hong, Yuxin Peng, Hongyao Yu et al. (+3 more)
Open-weight large
language models (LLMs) can be copied, modified, and redeployed behind black-box APIs, making post-release ownership verification difficult. Existing black-box fingerprints often rely on secret query-key pairs that reproduce predefined responses, and can therefore be easily disrupted by fine-tuning,
pruning, quantization, model merging, and serving-time
prompt changes. We propose SimPrint, a recoverable semantic fingerprinting framework for black-box LLM ownership verification. Rather than relying on isolated exact matches, SimPrint encodes a private owner signature into a coded semantic fingerprint domain, distributing ownership evidence across natural binary question-answering probes. It implants only base-deviating probes through a low-interference batch update that preserves the original model behavior, and later recovers the signature by parsing suspect-model responses into reliable bits or erasures with an error-correcting recovery mechanism. Because verification only uses input-output queries, SimPrint remains applicable when model weights or activations are inaccessible. Experiments on three open-weight LLMs show that SimPrint reliably recovers the owner signature in both clean and modified settings, remains robust under fine-tuning,
pruning, quantization, model merging, and serving-time perturbations, and maintains comparable downstream utility.
Read the full abstract ▾
All authors Jiaxin Hong, Yuxin Peng, Hongyao Yu, Hao Fang, Shuoyang Sun, Bin Chen
Artificial Intelligence · Cross-listed from cs.CL
From Content Generation to Learning Support: Pedagogy-Guided Generative Video Tutors for STEM Learning
Xinchen Ma, Shuimu Wang, Gaole He et al. (+4 more)
Generative AI enables scalable production of educational
videos, but current systems largely focus on producing visually coherent content rather than supporting learning. As a result, generated
videos often lack explicit pedagogical structure, reliable quality control, and mechanisms for assessing learner understanding or addressing misconceptions. In this work, we introduce PIVOT (Pedagogy-guided Instructional
VideO Tutoring), a generative
video tutoring framework for STEM learning via learning-centered instructional support.1 Inspired by conventional teaching workflows, our framework integrates pedagogy into the full generation pipeline: it first uses instructional principles to guide storyboard generation, then produces verified
multimodal videos through code-centric generation and a pedagogical verification harness, and finally connects
videos with assessment and misconception-aware remediation. Experiments and expert evaluations across four STEM domains show that our framework produces educational
videos with pedagogically aligned content, clear and engaging presentation, coherent instructional flow, and perceived effectiveness for learning. These findings suggest a human-centered perspective on educational content generation: generative systems should be evaluated and designed not only by what they produce, but also by how they support teaching practices, learner understanding, and corrective feedback.
Read the full abstract ▾
All authors Xinchen Ma, Shuimu Wang, Gaole He, Yanbin Zhang, Chunyang Wang, Yunshi Lan, Weining Qian
Artificial Intelligence · Cross-listed from cs.SD
MECT: Mixture of Experts with CNN-Transformer Network for Speaker verification
Yu Zheng, Jinghan Peng, ChangHao Zhang et al. (+2 more)
In this paper, we propose MECT, a speaker verification model that integrates the Mixture-of-Experts (MoE) mechanism into a CNN-
Transformer backbone with optimized block structure and stacking scheme. Specifically, we investigated four MoE variants that span utterance-level and frame-level granularity with dense and sparse routing strategies. The MoE mechanism proves to be effective over the baseline without MoE with only a small increase in parameters. We further scale MECT to a series of model sizes, all maintaining compact parameters and low computational complexity. In particular, MECT-B2 achieves state-of-the-art performance on VoxCeleb1 and delivers strong results on CN-Celeb, demonstrating its effectiveness across diverse
datasets. In addition, we establish a streaming inference paradigm through causal retraining, which maintains strong performance at a chunk size of 100ms.
Read the full abstract ▾
All authors Yu Zheng, Jinghan Peng, ChangHao Zhang, Jian Liu, Weiqiang Wang
Artificial Intelligence
Representation-guided in-context learning for medical image interpretation with multimodal large language models
Minda Zhao, Fangyu Hu, Yan Luo et al. (+8 more)
Medical image interpretation is central to diagnosis and care, yet adapting general-purpose
multimodal large
language models (MLLMs) often requires resource-intensive domain-specific fine-tuning. Here we introduce representation-guided in-context learning (RG-ICL), a training-free inference framework that retrieves query-aligned demonstrations using frozen encoders, without task-specific parameter updates. Across eight
datasets spanning histopathology, radiology and retinal fundoscopy, RG-ICL improved classification (mean gain 20 percentage points) and visual question answering (VQA) (mean gain 13 percentage points) over no-context and conventional ICL, approaching or exceeding training-based comparators. Which cases were retrieved mattered more than how many: 6 query-aligned cases outperformed up to 32 randomly selected ones, whereas fixed or random cases often reduced accuracy below baseline. For VQA, aligning reference cases with both image content and question intent produced further gains. These findings indicate that for medical image interpretation, curating which reference cases an MLLM sees is a practical alternative to retraining it.
Read the full abstract ▾
All authors Minda Zhao, Fangyu Hu, Yan Luo, Yutong Yang, Jiahui Cai, Kaichen Zhou, Manling Li, Paul Liang, Yilun Du, Lucy Q. Shen, Mengyu Wang