Artificial Intelligence · Cross-listed from cs.LG
CheMLFlow: An Open-Source Platform for Cheminformatics and Materials Informatics Applications
Brendan Smith, Susana Lopez-Moreno, Eric Dolores-Cuenca et al. (+3 more)
CheMLFlow is an open-source platform for building and executing end-to-end, high-throughput, and agentic workflows for scientific and technological applications. CheMLFlow targets a common bottleneck in scientific machine learning development, where researchers often need to assemble data acquisition, curation, representation, model training, validation, screening, interpretation, and reporting into a reproducible pipeline, even when their primary research contribution concerns only one stage. CheMLFlow provides modular workflow components, ready-to-run reference pipelines, standardized artifacts, and evaluation outputs that reduce orchestration overhead and support benchmarking across methods and
datasets. The platform is designed to be extensible, reproducible, and automation friendly, with pluggable representations and models, deterministic splits, explicit run artifacts, batch execution, and report generation. As scientific software increasingly moves toward
agent assisted experimentation, CheMLFlow's configuration driven workflows and structured outputs also provide a practical interface for coding
agents to help users construct experiments, inspect results, and summarize findings under human supervision. This article describes the system architecture, core workflows, and
benchmarks that reach literature performance for
quantum mechanical, physicochemical and bioactivity property prediction, and use cases involving time series
datasets demonstrating applications beyond molecular chemistry
datasets.
Read the full abstract ▾
All authors Brendan Smith, Susana Lopez-Moreno, Eric Dolores-Cuenca, Sangil Kim, Jose L. Mendoza-Cortes, Nijamudheen Abdulrahiman
Artificial Intelligence · Cross-listed from cs.LG
SVI-DAG: A Structured Variational Inference Approach to Bayesian Causal Discovery
Shrenik Zinage
Bayesian causal discovery seeks to determine the posterior distribution of causal theories, which are interpreted as directed acyclic graphs (DAGs) that explain the observed data. The resulting posterior allows systematic
reasoning regarding epistemic uncertainty within these theories. Nonetheless, finding such graphs is difficult due to identifiability problems and limited observational data. Furthermore, precisely approximating posterior over graphs is challenging given vast range of potential DAGs. Recent
Bayesian approaches have addressed some of these challenges, yet they remain limited as they fail to encode dependencies between edges, and lack principled ways to incorporate domain knowledge as inductive biases during the search process. To overcome these limitations, we propose SVI-DAG, a structured variational inference approach to
Bayesian causal discovery using observational data and prior beliefs that uses normalizing flows to model dependencies between edges, supporting expressive and
multimodal posterior learning over DAGs. To mitigate mode seeking behaviour in evidence lower bound optimization and promote mode coverage, we use stein variational gradient descent to update the node potentials using a kernel in acyclicity space. We evaluate SVI-DAG against 5 state-of-the-art
Bayesian DAG learning methods and demonstrate competitive performance in terms of both accuracy and uncertainty quantification.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning
Xuehang Guo, Pengyuan Li, Tom Hope et al. (+3 more)
As chart images, tabular data, and visualization code play increasingly important roles across diverse domains, cross-representation understanding across these modalities poses fundamental challenges for AI systems: the relationships across representations are inherently one-to-many, supervision is ambiguous and costly, and model optimization lacks a principled signal that is both direction-adaptive and representation-generalizable beyond task-specific objectives. We introduce CoCoEvolve to improve consistency across chart, table, and code representations. Instead of treating cross-representation mapping as a one-to-many problem, we define explicit one-to-one correspondences and optimize models using agreement between representations, without additional annotations. During training, CoCoEvolve@Train performs co-
evolution across the chart-table-code cycle, while CoCoEvolve@Test applies the same consistency objective at inference time for test-time co-optimization. We also present CoCoEvolve@Eval, an evaluation suite covering all six cross-representation tasks. Across four
benchmarks, CoCoEvolve improves performance in both training-time and test-time settings. Our project page: https://xhguo7.github.io/CoCoEvolve/.
Read the full abstract ▾
All authors Xuehang Guo, Pengyuan Li, Tom Hope, Tirthankar Ghosal, Manling Li, Qingyun Wang
Artificial Intelligence · Cross-listed from cs.SE
A Chain Is Only as Strong as Its Weakest Link: A Scoping Review of System Integration Audits in AI
Leah Davis, Dominic Martin and AJung Moon
As AI systems become increasingly integrated into diverse interfaces and applications, model-centric audits are insufficient to address risks arising from interactions among system components and deployment environments. System integration has long been central to software audits in safety-critical domains such as aerospace. However, its role in AI
auditing remains underexplored. Scanning through 4,259 documents, we present a scoping review of AI audits that treat system integration as a core tenet of evaluation (n = 58). Using reflexive thematic analysis, we analyze their elements, actors, enablers, and constraints. We find that the corpus represents an emerging yet still fragmented form of AI
auditing: few existing measures target integration-specific risks; large gaps remain in meeting traditional audit expectations; and access to necessary information and resources significantly influences audit design. Nonetheless, integration can be categorized across three sites (inter-component, system-environment, and multi-system), each serving the functions of risk exploration, risk determination, coordination, and procedural regularity. Deviating from other types of evaluations, these audits assess qualities specific to system integration, including compatibility, completeness, and oversight. This review calls on the AI community to prioritize system integration as a core strategy for addressing AI risk, and to develop audit practices capable of capturing failures across components, environments, and systems beyond the reach of component-level evaluation.
Read the full abstract ▾
Artificial Intelligence
When Shared Rollouts Fail in Defensive Driving Evaluation: A NAVSIM Score Basis Audit
Ziang Wei, Minjun Yu, Zheyuan Lai et al. (+2 more)
Defensive driving scores are useful only when they preserve distinctions between policies that observe surrounding actors and those that do not. Re-simulation
benchmarks may use reference-conditioned forgiveness, under which an
agent receives credit when the logged human reference fails a compliance channel. When
agent and reference share an unstable rollout transformation, this rule can propagate shared reference failures into broad compliance credit. We audit this risk in NAVSIM v2.2 original scene single-stage scoring. Under the affected documented-stack condition on the audited numerical backend, the route-blind Ignore-All probe and a route-aware actor-blind probe outrank human replay and PDM-Closed over the complete 12,146-
token navtest split. A fresh installation following the public specification reproduces rollout divergence on a fixed 32-
token diagnostic set. A same-source dependency stack control and an exact-input diagnostic isolate dependency-sensitive numerical behavior in the shared velocity refit. On a 450-
token control pool, replacing only the solver eliminates rollout divergence and restores blind-last ordering while keeping forgiveness enabled. Thus, the numerical instability is the direct trigger. Reference-conditioned forgiveness propagates the resulting shared reference failures into compliance credit. We contribute an audit protocol requiring score basis and stack disclosure, blind probes, overwrite reporting, and rollout stability tests before using such scores for defensive driving claims.
Read the full abstract ▾
All authors Ziang Wei, Minjun Yu, Zheyuan Lai, Mingjie Pang, Wei Li
Artificial Intelligence · Cross-listed from cs.CR
When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs
Jiaming Cheng, Subhransu Das and Rajiv Ramnath
Multi-
agent LLM systems relay key-value caches instead of text and credit their gains to exchanged "latent thoughts". That credit is a claim about which example's cache is relayed, not merely that one is. We audit it causally in released systems. The cache is replaced with deranged (mismatched-example), zeroed, and moment-matched random counterparts, under two regimes defined by whether the receiver needs the sender's private information. Where it does, the battery reads ceiling: 100% against 23-25% for answer-irrelevant relays on the primary backbone, a contrast replicated across three families, five checkpoints, and a prose document-QA surface. Where it does not, a pre-registered five-seed protocol establishes equivalence within 2.8 points, a margin anchored to the audited system's reported gain, under Holm-corrected TOST on GSM8K and ARC-Challenge across three Qwen3 scales and on MedQA at 8B (one
cell shows a small detected advantage inside the margin); a second family shows no detected advantage. A large cache effect need not be a pairing effect. In one natural
cell, zeroing the relay costs 14.7 points; a mismatched cache, 0.4. Nor is need sufficient: under the same test, delivered channels span ceiling (LatentMAS's native relay), partial (KVComm's layer subset), and no detected example-specific transfer (C2C's released projector).
Benchmark deltas do not by themselves establish latent-thought transmission; establishing it takes a mismatched-cache audit, which we release.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination
Wenxiao Zhao, Dong Liu, Kaiyi Xu et al. (+9 more)
Symbolic regression aims to discover closed-form equations from data, but existing LLM-guided methods often rely on a unified proposal loop that compresses heterogeneous search failures into a scalar score and a single
prompt. We propose A-SR, a self-evolving agentic framework that shifts the control unit from expression edits to role-conditioned evidence views. A-SR coordinates formula discovery through routing among coordination protocols, an online evaluator-reward role policy, and state-routed process
memory. During search, evaluator feedback characterizes reliability and productivity, updates role-level utilities, and routes elite motifs, failure traces, and validity diagnostics to different
agents. The framework self-evolves at two timescales: within a run, it adapts the search process without updating LLM parameters; across runs, recorded trajectories can be distilled into open-source LLMs as role-conditioned proposal priors. Averaged over the four LSR-Synth scientific domains in LLM-SRBench, A-SR improves Acc@0.01 over baselines from 25.79% to 48.30% with Llama3.1-8B, while A-SR-LoRA improves the corresponding Qwen3-4B result from 24.58% to 38.29%. On four real-world scientific discovery tasks, A-SR obtains the best in-distribution or out-of-distribution normalized mean squared error on 7 of 8 reported metrics.
Read the full abstract ▾
All authors Wenxiao Zhao, Dong Liu, Kaiyi Xu, Feng Liu, Zhen Zhao, Fei Ben, Shu Wang, Wenhao Li, Ying Nian Wu, Fenghua Ling, Haobo Li, Lei Bai
Artificial Intelligence · Cross-listed from cs.CV
Towards a satellite image manipulation and deepfake localization benchmark dataset
Jacob Arndt, Debvrat Varshney, Philipe Dias et al. (+1 more)
Verifying the authenticity of satellite imagery has become increasingly critical given advances in generative artificial intelligence. Highly realistic synthetic imagery produced for malicious purposes (deepfakes) can have major consequences in the remote sensing domain, where this data is a fundamental source of information for science applications, planning, logistics, and monitoring. The remote sensing community lacks high-quality, fine-grained manipulation
datasets suitable for training and evaluating detection and image forensics
algorithms. Existing
datasets are lacking and those that do exist either provide no ground truth masks for evaluating manipulation localization, or consist of entire images generated by GANs or
diffusion models, which are inadequate for measuring localization performance. To address this gap, we describe a preliminary
dataset construction process and prototype
benchmark dataset for satellite image manipulation detection and localization. The
dataset contains 60 images total, with 30 images carefully manipulated using three manipulation types including copy-paste splicing and
diffusion model inpainting, and 30 authentic images. Each image is accompanied by a ground-truth mask and acquisition metadata, enabling both pixel-level localization metrics, image metadata studies, and analyses of how manipulation detection performance relates to image collection parameters. We describe the
dataset construction process and present this initial release to support further research in image forensics and geospatial deepfake detection. The prototype
dataset can be downloaded at https://huggingface.co/
datasets/geodf/fmow-fake-small.
Read the full abstract ▾
All authors Jacob Arndt, Debvrat Varshney, Philipe Dias, Nivedita Nukavarapu
Artificial Intelligence
ContextWeave: A Real-World Workflow Benchmark
Bo Wang, Yuqian Yao, Enxi Wang et al. (+25 more)
Memory is essential as
language agents move from isolated tasks to long-horizon, stateful workflows, yet existing evaluations often reduce it to
retrieval or question answering. We introduce ContextWeave, a longitudinal
benchmark that evaluates whether recalled experience improves downstream
agent performance in realistic office-work streams. ContextWeave reconstructs
privacy-preserved, multi-month workflows of 14 participants into 1,005 executable tasks, including 568 core evaluation tasks, with instructions, containerized environments, trajectories, and task-specific rubrics. It measures workspace quality and
alignment with participant-specific preferences, complemented by diagnostics of relevance, continuity, solvability, and robustness to misleading recall. Across six
memory components under a fixed model, the strongest configuration raises Workspace Score from 68.08 to 78.20 and Preference Score from 41.50 to 70.60. With a fixed
memory component, recall improves both outcomes for all five tested base models, although gains vary substantially. Our analysis shows that actionable, experience-rich
memory supports workflow continuation and reduces redundant exploration more effectively than compact summaries, while it can also be more susceptible to misleading recall. These findings motivate
memory systems that optimize not only
retrieval relevance but also reliable use during execution.
Read the full abstract ▾
All authors Bo Wang, Yuqian Yao, Enxi Wang, Luozhijie Jin, Yang Liu, Yiran Suo, Yuxuan Cai, Enyu Zhou, Yufei Gao, Honglin Guo, Tianyu Huai, Li Ji, Zhikai Lei, Bufan Li, Lizhi Lin, Jinxiu Liu, Jie Yang, Jiazheng Zhou, Maosen Zhou, Pengfang Qian, Shichun Liu, Guanshan Liu, Hao Zheng, Yunhao Yu, Hang Yan, Jihua Kang, Xinchi Chen, Xipeng Qiu
Artificial Intelligence · Cross-listed from cs.SE
Scrouting: Cost-Aware Routing of Coding Agents by Scouting the Repository First
Ishaan Bhola, Adithyan Krishnan and Mukunda NS
Frontier
language models can resolve repository-level software issues, but each attempt is expensive, and existing routers select a model from the issue text alone. We present SuperScout, which routes after scouting the repository: a 7B searcher, SuperScout-7B, first explores the repository and produces a structured handoff whose reproduction claims are sandbox-verified, with false claims stripped before delivery. The searcher's hidden states, together with the task text, then feed a resume-based router that dispatches the task to one of four frontier fixers. Adding a new fixer requires no retraining. On the full Python slice of SWE-bench Pro (266 tasks) under the
benchmark's official capped budget tier, SuperScout matches the best single model's solve rate (159 of 266 for SuperScout, 158 for the best model) at about a fifth of the total cost per solve, and the reported configuration sits above the random traffic-splitting baseline. A no-router ablation, always the cheapest fixer with the handoff, ties the routed system on this
benchmark, so the handoff rather than the routing decision carries the result. A paired calibration study points to the mechanism: the handoff appears to redistribute rather than add solving ability, lifting the three cheaper fixers while slightly hurting the strongest, though at $N=99$ the per-fixer effects are directional only; the searcher's hidden states improve cost routing on the calibration labels while the handoff's own text does not. The searcher's compute adds less than half a cent of GPU time per task.
Read the full abstract ▾
Artificial Intelligence
Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation
Sarthak Harne, Chinmay Karkar, Yash Pandya et al. (+2 more)
Self-
distillation (SD) has emerged as a compute-efficient alternative to reinforcement learning with verifiable rewards: a self-teacher, conditioned on privileged information (PI) about the answer such as a reference solution, supplies dense per-
token supervision to a student that never sees it. Reported gains, however, come almost exclusively from narrow, low-difficulty settings, leaving open a basic question: as a lone objective, with no reward term, does SD teach anything? We reproduce SDPO's reported gains in its easy setting, then apply the identical setup to difficult tasks and find that it does not. Across question answering, mathematics, coding, and multi-turn agentic tool use, across
reasoning modes, model sizes, and forms of PI, and under both the SDPO and OPSD recipes, the per-
token loss falls steadily while validation accuracy does not improve and typically degrades. We explain this failure through a single causal chain from the loss to the model it produces. The chain begins with PI bias: having seen one particular reference solution, the teacher's per-
token target is pulled toward that trajectory rather than toward correctness in general, an effect we quantify with a PI Bias Score. Trained to match this target everywhere, the student's objective becomes nearly blind to whether a rollout is correct, and the loss it assigns falls mostly on low-information
tokens like stopwords, punctuation, uncertainty markers, rather than those that determine the answer; within correct rollouts the exploratory
tokens incur the highest divergence, so it penalizes the hesitation that
reasoning requires. The result is a flatter, less decisive student that is no better at
reasoning: as a lone objective, SD optimizes a signal decoupled from task success.
Read the full abstract ▾
All authors Sarthak Harne, Chinmay Karkar, Yash Pandya, Ahmed Awadallah, Akshay Nambi
Artificial Intelligence · Cross-listed from cs.LG
Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation
Yi Yang, Cong Qin, Xiaodan Liu et al. (+8 more)
Large
language model
agents are commonly trained through reinforcement learning with sparse trajectory-level rewards, which offer limited guidance on how strongly individual
tokens should be updated. On-Policy Self-
Distillation (OPSD) addresses this by re-scoring generated
tokens under a privileged replay view to obtain dense,
token-level supervision. However, we identify a confounding issue: the resulting support may reflect both the privileged information contained in the replay view and score shifts induced by the replay scaffold, making it difficult to attribute the support specifically to that information. This issue is especially pronounced when future environment observations serve as privileged information, since replaying them requires reconstructing an extended scaffold that itself perturbs
token scores. To resolve this confounding, we propose Observation-Calibrated Self-
Distillation (OCSD), which contrasts two structurally matched replay views, Full and Observation-Ablated, differing only in whether the actual future observation is present, to derive an observation residual that discounts score changes shared by the replay scaffold. OCSD then applies this residual to modulate
token-level GRPO updates at high-uncertainty steps, while preserving the trajectory-level update direction. Experiments on ALFWorld, WebShop, and Search-QA across three Qwen3 model scales show that OCSD consistently outperforms strong baselines. Diagnostic analyses further confirm that the calibrated residual aligns better with local environment feedback. Our code is publicly available at https://github.com/yiy1x/OCSD.
Read the full abstract ▾
All authors Yi Yang, Cong Qin, Xiaodan Liu, Chishui Chen, Qing Dong, Yan Zhang, Cao Liu, Zhao Yang, Lu Pan, Jiaye Lin, Yi Feng
Artificial Intelligence · Cross-listed from cs.SE
RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists
Yuexi Yang, Alyssa Wu, Ji Luo et al. (+4 more)
The integration of Large
Language Models (LLMs) into software engineering has shifted the focus from function-level generation to repository-scale assistance. However, existing
benchmarks largely rely on bug reports from GitHub Issues, which often allow models to bypass genuine understanding via pattern matching on error logs. This misalignment under-measures Edit Bias, which refers to premature generation, where models prematurely propose code modifications instead of understanding the existing repository architecture. Furthermore, current LLM-as-a-Judge scalar scoring suffers from high variance and low interpretability. This work introduces RepoProbe, a novel
benchmark for evaluating repository-level code understanding through open-ended Q&A using GitHub Discussions, which focuses on open-ended architectural inquiries rather than defect reporting. To ensure rigorous evaluation, we propose a Checklist-Based Verification Protocol that decomposes answers into atomic, verifiable facts, thereby replacing subjective ratings with objective verification. Our evaluation of state-of-the-art (SOTA) LLMs reveals a persistent gap between high clarity and evidencegrounded technical correctness. It also quantitatively confirms the prevalence of edit bias, in which models prioritize code generation instead of architectural analysis. Finally, we demonstrate that our verification protocol significantly improves evaluation reliability compared to traditional evaluations with scalar scoring.
Read the full abstract ▾
All authors Yuexi Yang, Alyssa Wu, Ji Luo, Richeng Xuan, Zhichao Hu, Yuhong Liu, Zhen Qin
Artificial Intelligence · Cross-listed from cs.LG
IMFACT: Counterfactual Explanations for Time Series via Intrinsic Mode Function Substitution
Udo Schlegel, Julian Rakuschek, Thomas Seidl et al. (+3 more)
Oscillatory signals, such as vibration, carry class-discriminative information in specific frequency bands; perturbing them in raw feature space for counterfactual analysis easily destroys their temporal structure and produces physically implausible results. In this work, we introduce IMFACT (IMF-based counterfACTuals), a model-agnostic framework for generating plausible counterfactual explanations for time series classifiers that operates in the decomposition space of Empirical Mode Decomposition. An input signal is split into Intrinsic Mode Functions (IMFs), and selected IMFs are progressively substituted with those of a Nearest Unlike Neighbour (NUN) until the classifier flips to the target class. We evaluate six IMF-selection strategies and a multi-NUN cycling extension on two UCR
benchmarks (FaultDetectionA, FruitFlies). The variance-based strategy with three NUNs outperforms two prominent baseline techniques on reliability and plausibility metrics, while cycling across three NUNs yields the best proximity across both
datasets.
Read the full abstract ▾
All authors Udo Schlegel, Julian Rakuschek, Thomas Seidl, Andreas Holzinger, Tobias Schreck, Javier Del Ser
Artificial Intelligence
NSF-HRPT: Neural Semantic Field meets Hierarchical Risk Perception Tree for Safety-Critical Scenario Assessment
Yu Zhao, Jiangyu Pan, Tao Hu et al. (+4 more)
The ability to accurately assess and anticipate risks in safety-critical scenarios is crucial for autonomous driving systems. While existing research has made progress in collision prediction, accurately quantifying risk levels from
monocular vision inputs remains challenging due to the complex dynamics of multi-
agent interactions and the inherent uncertainty in real-world environments. To address these challenges, we present NSF-HRPT, a novel framework that combines learning-based perception with structured
reasoning for quantitative risk assessment. Our approach features a Neural Semantic Field (NSF) that learns to model scene semantics, trajectory predictions, and probabilistic Time-to-Collision (TTC) distributions from simulation data. During inference, the pre-trained NSF serves as a prior for our Hierarchical Risk Perception Tree (HRPT), which enables efficient parallel computation and spatial
reasoning about multi-
agent risks. Additionally, we introduce a Sim2Real enhancement strategy that improves real-world applicability without retraining by incorporating priors from foundation models. Extensive evaluations demonstrate that our framework achieves state-of-the-art performance on synthetic
benchmarks and delivers competitive, near-state-of-the-art results on real-world
datasets for both TTC estimation accuracy and risk localization precision. The proposed method provides an effective solution for real-time risk awareness from
monocular camera inputs.
Read the full abstract ▾
All authors Yu Zhao, Jiangyu Pan, Tao Hu, Ming Yin, Fan Yang, Jiangfan Liu, Xiubo Liang
Artificial Intelligence · Cross-listed from cs.CL
Guideline-as-Oracle: Zero-Annotation Training of an Ophthalmic Telephone Triage Agent
Chenyu Wang, Yi Liu, Baoqing Li et al. (+2 more)
Scaling supervision for multi-turn medical
agents is difficult because expert dialogue annotation is costly and clinical conversations are
privacy-restricted. We introduce Guideline-as-Oracle (GAO), which compiles American Academy of Ophthalmology guidance into a 70-row operational rule table and uses it as the sole source of instance-level supervision for 3,000 training dialogues, reserving human labeling for evaluation. Because converting rules into dialogues is itself a design problem, we catalog eight construction strategies, including cited-row tier assignment, one-fact boundary pairs, metadata-only repair, and label repair, and characterize the evidential status of each: labeling mechanism, null, confounded, or evaluated only as a package. Fine-tuning a 9B backbone on this corpus yields GAO-Triage, improving agreement with a 201-case operational reference from 61.7% to 74.1% (exact McNemar p=0.0046) and emergent-case recall from 9.5% to 69.0%; the gains persist across a second seed and patient simulator. None of the seven general-purpose systems we test dominates GAO-Triage on both metrics, and GAO-Triage requires no frontier model at inference time. Permuting label-dialogue assignments collapses the model to a constant-routine predictor, indicating that the signal lies in guideline-derived assignment rather than dialogue surface form. Label repair coincides with the disappearance of a late-training safety degradation.
Read the full abstract ▾
All authors Chenyu Wang, Yi Liu, Baoqing Li, Min Tu, Diping Song
Artificial Intelligence
Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning
Qiyuan Zhu, Dezhi Li, Pengyu Cheng et al. (+8 more)
Large
Reasoning Models (LRMs) excel on complex tasks through long chain-of-thought (CoT)
reasoning, but their lengthy intermediate steps cause severe overthinking that inflates inference cost. KV-cache compression is a common solution, yet existing
reasoning-oriented methods apply a uniform policy across the trajectory and judge compression only by what it removes from the cache. Two observations point the other way. First, a
reasoning state's tolerance to context loss varies along the trajectory, and process reward tracks it: deleting
tokens at high-reward steps preserves accuracy far better than deleting the same budget at random. Second, compression is not free on the generation side, since a smaller cache leads the model to generate more
tokens, partly canceling the saving. Together these motivate coordinating both sides under a single process reward. We propose ReCo (Reward-Coordinated Compression), a step-wise framework in which a lightweight process-reward
estimator scores each completed step and drives three components: (1) reward-adaptive KV-cache compression that shrinks the retained cache harder at high-reward steps and less at low-reward ones, (2) a reward-banded penalty on reflection
tokens that curbs redundant generation, and (3) confidence-based early stopping that triggers when the
reasoning is reliable. Across three
reasoning models and six
benchmarks, ReCo reduces generated
tokens by 37%-65% and end-to-end latency by 2.08x-2.35x over Full CoT, all while largely preserving accuracy.
Read the full abstract ▾
All authors Qiyuan Zhu, Dezhi Li, Pengyu Cheng, Tianle Chen, Jiacheng Wang, Ruijie Shen, Hao Gu, Sida Lin, Zirui Liu, Jiacheng Liu, Sirui Han
Artificial Intelligence · Cross-listed from cs.CV
FUSEP: A Multi-Center Benchmark for Diverse Tasks in Early Pregnancy Fetal Ultrasound Screening
Bin Pu, Jiewen Yang, Liwen Wang et al. (+9 more)
A large number of infants with congenital anomalies are born each year globally, especially in areas with underdeveloped medical resources. Currently, fetal ultrasound screening is the most common modality for early pregnancy anatomy detection. This modality can detect anomalies earlier and provide opportune treatment advice. However, the lack of an ultrasound
dataset on early fetal gestation has slowed down the development of automated assisted diagnosis. In this work, we present a
benchmark dataset for Fetal Ultrasound Screening in Early Pregnancy to facilitate intelligent ultrasound examination and assisted diagnosis called FUSEP. Our
dataset consists of two ultrasound views recommended by the international guideline, i.e., Crown-rump Length (CRL) and Nuchal Translucency (NT) views in three hospitals, totaling 4,017 ultrasound images, with 45,820 box-level expert-level annotations. Our
dataset and baseline present the following three contributions: 1) Our medical experts annotated a total of 14 key anatomical structures in two views using a box-level format; 2) Our data is collected extensively from different sonographers, devices, scanning angles, hospitals, etc; 3) We report the performance of the semi-supervised learning, fully supervised learning, unsupervised domain adaptation (UDA), and source-free UDA in ultrasound images multi-object detection. To the best of our knowledge, this is the first publicly available
dataset and
benchmark for fetal early pregnancy ultrasound screening. We believe that FUSEP and
benchmark can contribute to the medical community in the development of multiple tasks such as standard plane recognition, quality control on ultrasound images, automated assisted diagnostics in early fetal pregnancy, medical multi-object detection, domain adaptation for object detection, etc.
Read the full abstract ▾
All authors Bin Pu, Jiewen Yang, Liwen Wang, Ying Tan, Guannan He, Xingbo Dong, Qika Lin, Jiarong Guo, Lixian Yang, Zuozhu Liu, Shengli Li, Kenli Li
Artificial Intelligence · Cross-listed from cs.RO
Houze Xu, Jizhong Li and Ziyi Ye
Vision-
language-action (VLA) models provide a unified paradigm for connecting visual perception,
language understanding, and robotic control. However, existing VLA models still face major challenges in long-horizon tasks: sparse expert demonstrations constrain cross-task compositional generalization; the non-Markovian nature of long-horizon tasks makes it difficult for policies conditioned only on current observations to maintain temporal consistency; limited closed-loop error correction allows execution errors to accumulate; and end-to-end action fine-tuning may weaken the high-level semantic representations of
vision-
language model (VLM) backbones. To address these issues, we propose a hierarchical long-horizon VLA architecture with an explicit
language-
memory module. The central idea is to convert discrete temporal observations into a coherent textual
memory sequence with temporal logic. The system is decoupled into a high-level VLM and a low-level VLA: the high-level VLM performs semantic
reasoning through a visual question answering training paradigm, while the low-level VLA executes precise continuous control conditioned on subtask instructions and visual observations. The high-level VLM recursively updates both
language memory and subtask instructions using the previous
memory as a contextual anchor, enabling persistent temporal tracking and dynamic correction during long-horizon execution. We evaluate the proposed method in multiple simulation environments and conduct sim-to-real experiments on a real robotic platform. The results demonstrate that explicit
language memory improves the success rate and robustness of VLA models on complex long-horizon tasks while providing an interpretable semantic account of the decision process.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
InsightEmb: Learning Action-Intent Embeddings for Agentic Insight Retrieval
Tsz Ting Chung, Jiangnan Li, Jie Zhou et al. (+1 more)
Self-improving
agents accumulate reusable insights from prior trajectories, making
retrieval increasingly important for turning accumulated experience into actionable guidance. At each decision step, retrieving the right insight can help the
agent progress toward its goal, a setting we refer to as agentic insight
retrieval. However, existing
retrieval methods primarily model semantic similarity, while overlooking whether a retrieved insight resolves the
agent's current decision bottleneck. We propose InsightEmb, a contrastive
embedding framework that learns transferable progress-oriented
retrieval geometry using only mathematical
reasoning data. InsightEmb jointly learns to align concrete situations with abstract heuristic rules and to cluster
reasoning trajectories with similar progress structures. We evaluate InsightEmb on dynamic
agent tasks and a static skill-
retrieval benchmark. Without any environment-specific training, InsightEmb improves over all these evaluations, surpassing the performance of existing
reasoning embedding models. These results suggest that the geometry of state-insight matching can transfer across domains, enabling effective training from publicly available
reasoning data without expensive environment-specific supervision.
Read the full abstract ▾
All authors Tsz Ting Chung, Jiangnan Li, Jie Zhou, Mo Yu
Artificial Intelligence · Cross-listed from cs.CR
PURPOSE: Poisoning Conflict Resolution in RAG via Proxy-Fact-Grounded Updates
Zijian Wang, Yubo Zhu, Muzhi Dong et al. (+7 more)
In
Retrieval-Augmented Generation (RAG), post-
retrieval conflict resolution arbitrates among noisy or contradictory retrieved passages. However, the robustness of this safeguard against knowledge poisoning has not been adequately studied. Existing black-box poisoning methods all assert the target answer in frontal contradiction with what the resolver treats as settled, the very signal these methods are built to detect. We propose PURPOSE, a strict black-box poisoning attack that reframes the injection as an update that minimizes conflict, rather than as a counter-claim. PURPOSE extracts query-related facts approximating the resolver's possible reference, then grounds a pivot event in them to keep the injection consistent with what the resolver might verify while steering the generator toward the target answer. Across three QA
benchmarks, five generators, and three conflict-resolution methods, PURPOSE attains the highest attack success rate (ASR) in 35 of 45 settings and exceeds the strongest prior attack with +9.7 mean ASR points. These results show that our poisoning method is effective against conflict resolution in RAG and identify non-contradicting injection as a practical mode to enhance poisoning attack.
Read the full abstract ▾
All authors Zijian Wang, Yubo Zhu, Muzhi Dong, Yanjun Lou, Yisheng Li, ZiLiang Zhang, Wei Tong, Yuan Zhang, Jingyu Hua, Sheng Zhong
Artificial Intelligence
EviGraph: Evidence-Guided Autonomous Research Agents
Zhenjiang Ren, Ruiji Li, Xujing Zhang et al. (+3 more)
Autonomous research
agents can generate hypotheses, execute experiments, and draft manuscripts, yet their outputs often contain unsupported claims and inconsistencies between research questions, experiments, results, and conclusions. We argue that this problem is partly architectural: existing systems organize research as sequential pipelines but do not explicitly maintain or validate the evolving claim-evidence structure across stages. In this paper, we introduce EviGraph, an autonomous research framework that represents the research process as a typed evidence graph containing Problem, Gap, Hypothesis, Experiment, Finding, and Claim nodes. The graph serves as the operational state of the
agent rather than a post-hoc record. EviGraph inspects evidence chains for missing dependencies, semantic misalignment, and result-claim inconsistencies, localizes the earliest weak node, and regenerates its affected downstream subgraph. Graph checkpointing prevents unsuccessful repairs from corrupting previously validated evidence. Manuscripts are generated only after every retained claim is grounded in a validated evidence chain. Experiments on ARC-Bench-ML and NanoResearch-20 show that EviGraph outperforms the compared end-to-end research-
agent baselines in overall research performance, improves Claim Support Rate by 40.19% over the strongest baseline, and achieves 87.73% Experimental Data Consistency. These results demonstrate the value of explicit evidence-state maintenance for reliable autonomous research.
Read the full abstract ▾
All authors Zhenjiang Ren, Ruiji Li, Xujing Zhang, Ziliang Pang, Shuo Ren, Jiajun Zhang
Artificial Intelligence
Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings
Agatha Duzan and Asa Cooper Stickland
Chain-of-thought (CoT) monitoring is increasingly treated as an important safety layer for frontier
reasoning models. Most monitorability evaluations study explicit-influence settings: setups where the
prompt directly incentivizes the model to hide something, e.g., by instructing it to perform a hidden side-task. A complementary axis for CoT-monitor evaluations is implicit-influence settings, where the
prompt contains no instruction to hide, but the model's behavior is still shaped by features of the task or context, e.g. an irrelevant detail about a candidate that biases a hiring rating. We introduce the first
benchmark that directly compares CoT monitorability under the two regimes. We test how model behavior changes in the presence of a nudge to choose a particular option. The nudge is delivered either as a casual aside (implicit), or as a direct instruction to act on the nudge and to conceal having done so (explicit). The
benchmark spans four task formats (binary choice, numeric rating, multiple-choice QA, open-ended coding) and seven frontier extended-thinking models. Under explicit influence, a CoT monitor detects 60-94% of behavior shifts: even models instructed to conceal it leak the instruction into their CoT. Under implicit influence, the same factors still shift behavior, but detection falls by 41-46 percentage points in two of our four settings. Realistic system-
prompt additions (of the kind a developer might deploy to reduce off-topic bias) lower implicit detection further, to as low as 5%, while preserving the behavioral influence itself. These results suggest that monitorability estimates obtained in explicit-influence settings may over-estimate monitorability, and that monitorability can be further decreased by well-intentioned deployment choices. Our
benchmark and code are available at https://github.com/agatha-duzan/implicit-vs-explicit-influence
Read the full abstract ▾
Artificial Intelligence · Cross-listed from eess.SY
Toward Integrating Adaptive Experience Replay and Online Uncertainty Estimation in Safe Actor-Critic Optimal Control
Mahshad Rastegarmoghaddam, Davoud Nikkhouy and Shima Samadzadeh
Safe actor-critic control often treats barrier filtering, uncertainty estimation, and experience replay as separate modules, even though each changes the data used for learning and control. We develop an integrated architecture in which the uncertainty estimate updates the obstacle geometry used by a control barrier function, filter interventions and estimation residuals determine replay priority, and the critic learns from the executed rather than nominal action. We instantiate the architecture on a two-dimensional
robot-
navigation task with corrupted obstacle measurements and compare six component-matched configurations under common training budgets, random seeds, sensor streams, exploration, and disturbances. Evaluation includes a moderate post-training test, an eleven-level perception-noise sweep, and an exploratory extreme-stress test at multiplier $6.0$. In the extreme test, the integrated configuration recorded no contacts and reached the goal in all five evaluation seeds. Its mean cost was $7.63\pm0.44$ and its obstacle-belief root-mean-square error was $3.52\pm0.55$ cm. The uncertainty-estimation ablation also recorded no contacts but reached the goal in four of five seeds, with mean cost $8.96\pm2.08$ and belief error $11.08\pm1.23$ cm. A finite-training bound clarifies replay exposure, and a robust barrier condition states the required estimation-error and feasibility assumptions. The results support coupling estimation, safety filtering, and replay on this
benchmark; broader safety and convergence claims require further study.
Read the full abstract ▾
Artificial Intelligence
Yongxin Wang, Ruizhe Zhou, Yueling Tang et al. (+4 more)
Multimodal large
language models increasingly reason over screenshots and documents where the task itself may be written in pixels. Yet
benchmarks usually place questions in text, leaving it unclear whether models use the same instruction equally well across channels. We introduce Visualized Task Semantics (VTS), a controlled intervention that moves the question into the image while keeping the source problem and answer fixed. Across six MLLMs and four
benchmarks, accuracy drops in all 24 model-task pairs, by 17.8 points on average. Models often transcribe the visual question correctly yet fail to use it, exposing a semantic channel gap beyond OCR. To reduce this gap, we present
prompt-region grounding, whose core design aligns the question region with typed semantics and recovers its clean representation from a masked view. At matched training cost, our method raises four-
benchmark VTS accuracy from 58.0 to 66.3 while preserving accuracy on the original interface, and requires no OCR or region metadata at inference. Reading task-bearing text and grounding it as an instruction for
reasoning are distinct capabilities.
Read the full abstract ▾
All authors Yongxin Wang, Ruizhe Zhou, Yueling Tang, Yingying Zhu, Xuemin Zhao, Xiaojun Chang, Xiaodan Liang
Artificial Intelligence
Diagnosing Tool-Selection Reasoning in LLM Agents with Canary Tools
Atul Anand and Sourav Chattaraj
Agent evaluations tell us that a model picked the wrong tool, but rarely why. We introduce canary tools: diagnostic probe tools planted in an
agent's Model Context Protocol (MCP) tool set, each engineered to probe one specific tool-selection weakness. A six-type taxonomy (semantic decoys, parameter traps, capability mirages, prerequisite blindness, temporal decoys, and granularity traps) turns a single "wrong tool" outcome into a multi-dimensional profile of how a model reasons about tools. We evaluate eight models – six hosted and two 8B open-weight – spanning three capability tiers, on 120 tasks across three canary-density conditions and three seeds (8,640 runs), plus a 2,880-run subtlety ablation. Task success is graded by a provider-independent judge, corroborated by a second independent judge (Cohen's kappa = 0.75). We report three findings. First, susceptibility drops sharply as models get more capable: the per-task canary susceptibility rate (CSR) ranges about 36x across models, lowest for Claude Opus 4.8 and highest for Llama 3.1 8B. Second, capability tier alone does not predict safety: the most susceptible hosted model is mid-tier, and within a provider the cheaper model can be the safer one. Third, the taxonomy is capability-stratified: capability mirages most reliably trap frontier models, while the other types are largely inert on strong models but fire on small open models, so they discriminate by capability rather than being weak. Softening each canary's give-away phrase leaves frontier CSR essentially unchanged, evidence that the probes measure
reasoning, not phrase-spotting. Susceptibility also predicts task failure (Spearman rho = -0.34), while the most robust models are not significantly degraded by canary pressure. We release the framework, canary schemas, tasks, and logs.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
What We Observe as LLM Behavior Can Be a Side-effect of Inference Backend
Shahed Masoudian, Passant Shafaei, Monorama Swain et al. (+1 more)
Benchmark scores are reported as properties of a model, yet the inference framework used to produce them, such as HuggingFace, vLLM, or Ollama, are considered non-influential and their names and versions are almost never disclosed. In this work we investigate how much this choice can influence the model output. In a fully-crossed study (three instruction-tuned models x five inference frameworks x six
benchmarks x four generation modes) we investigate how different tools (wrappers/backend) influence
benchmark scores and how their score changes is influenced by generation hyper-parameters. We find backend to be a non-negligible factor where even under greedy, sampling-noise-free decoding, changing the backend can significantly alter models performance and this effect is structural and strongly model-dependent. Decomposing the variance according to generation mode reveal that considerable portion of the variability (roughly 39%) a practitioner sees out-of-the-box can stem from the backend, while the remaining stems from sampling noise and each framework's default generation parameters, both of which are avoidable by disclosing and matching the generation configuration. These divergences are more pronounced on factual than on social-bias
benchmarks. Overall,
benchmark numbers are not backend-agnostic therefore, we recommend disclosing the backend, its version, and the full generation configuration, also using deterministic decoding for cross-backend comparison.
Read the full abstract ▾
All authors Shahed Masoudian, Passant Shafaei, Monorama Swain, Markus Schedl
Artificial Intelligence · Cross-listed from cs.LG
A 6G Integrated Sensing and Communication Framework for Railway Intrusion Detection and Collision Prediction
Ajeet Kumar Yadav, Sankaran Balasubramaniam, Aritra Chatterjee et al. (+3 more)
Integrated Sensing and Communication (
ISAC) combines sensing and communication to efficiently utilize wireless resources and is emerging as a key paradigm for next-generation wireless networks. By leveraging the wide bandwidth, high frequencies, and massive
antenna arrays of 5G-Advanced and 6G systems,
ISAC enables physical-layer sensing using Channel State Information (CSI). The 3rd Generation Partnership Project (3GPP) Release 19 identifies 32 potential
ISAC use cases, with particular emphasis on detecting and tracking moving objects. In this work, we address the Sensing for Railway Intrusion Detection use case, where intruders, including wildlife, entering a railway track can pose serious collision risks. We generated 22,695 CSI
matrices with corresponding ground truth using a 3D-rendered railway environment and the Sionna
radio simulator. We developed a machine learning model combining a three-dimensional Convolutional Neural Network (3D CNN) and Bidirectional Long Short-Term
Memory (BiLSTM) network to detect intruders in the track danger zone and estimate their real-time position relative to the train, velocity, and time to collision. On synthetic CSI data, the model achieves 99.57% intruder-detection accuracy on a balanced test set and a combined Mean Absolute Error (MAE) of 0.4240 for position, velocity, and time-to-collision prediction. These results demonstrate the potential of CSI-based
ISAC sensing with machine learning for reliable railway intrusion detection. The complete codebase for CSI generation, preprocessing, and model development is publicly available at https://github.com/EdgeIntelligenceLab/6g-
isac-railway-intrusion-detection.
Read the full abstract ▾
All authors Ajeet Kumar Yadav, Sankaran Balasubramaniam, Aritra Chatterjee, Vinod Aduru, Yogesh Simmhan, Pandarasamy Arjunan
Artificial Intelligence · Cross-listed from cs.LG
Design Choices That Matter: A Functional ANOVA Analysis for Remote Sensing Multi-Label Classification
Maryam Gholami Shiri, Eva Tuba, Sašo Džeroski et al. (+2 more)
Benchmarking deep learning (DL) models for multi-label classification (MLC) of remote sensing images (RSI) typically yields rankings that do not generalize beyond the evaluated
datasets. In this work, we move beyond rankings by employing functional analysis of variance (fANOVA) to systematically quantify the contributions of individual design choices and their interactions to performance variability. We conduct two empirical analyses covering 48 and 20 DL models, respectively, spanning design choices such as network architecture, fine-tuning strategy, learning strategy, and initialization. By applying fANOVA across seven MLC RSI
datasets, we construct
dataset meta-representations that capture design-choice sensitivity profiles. Hierarchical clustering of these meta-representations reveals that
datasets naturally group according to how they respond to design decisions, with patterns strongly linked to intrinsic
dataset properties such as scale, spatial resolution, and label space complexity. Our findings show that for large-scale
datasets, fine-tuning strategy and architecture are dominant factors, while in data-limited regimes, initialization becomes decisive. For intermediate regimes, the interaction between architecture and learning strategy governs performance.
Read the full abstract ▾
All authors Maryam Gholami Shiri, Eva Tuba, Sašo Džeroski, Tome Eftimov, Ana Nikolikj
Artificial Intelligence · Cross-listed from cs.CV
Teaching MLLMs to Say No: Generalized Referring Expression Comprehension via Refusal Calibrated GRPO
Xuzheng Yang, Jun Ling, Tao Huang et al. (+2 more)
We tackle the challenging yet underexplored task of Generalized Referring Expression Comprehension (GREC), which requires a model to localize the object described by a textual expression when it exists (positive sample) and to refuse output when it does not (negative sample). Although
Multimodal Large
Language Models (MLLMs) excel at localizing existing objects, they often fail to reject nonexistent ones due to the absence of negative samples during training, producing hallucinated bounding boxes. Existing post-training approaches such as supervised fine-tuning (SFT) and reinforcement learning (RL) enhance refusal behavior but usually degrade localization accuracy on positive samples, undermining the model's core competence. To address this, we propose Refusal-Calibrated Group Relative Policy Optimization (RC-GRPO), a calibrated RL strategy that strengthens the refusal ability of MLLMs while preserving localization performance. It enforces "None" outputs in rollouts for valid advantage estimation on negative samples and applies a penalty to prevent over-refusal on positives, achieving a balanced trade-off between accuracy and reliability. A second-stage
reasoning reinforcement further consolidates causal understanding and interpretability. Experiments on three GREC
benchmarks demonstrate that RC-GRPO attains superior localization accuracy while maintaining strong refusal capability.
Read the full abstract ▾
All authors Xuzheng Yang, Jun Ling, Tao Huang, Caiyan Qin, Peng Wang