cs.AI · 2026-07-31 · No. 70
Artificial Intelligence, 2026-07-31.
66 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
66 entries-
01
AISPA: User-Centric System Prompt Auditing for Large Language Model Applications
Xiangning Lin, Shenzhe Zhu, Shu Yang, Zhenyu Zhang, Haoqian Zhang, Yipeng Zhao, Chengxuan Qian, Tianwei Wang, Ziheng...
cs.AI · cs.CL · cs.CY · cs.HC
System prompts are instructions configured by developers to govern the behaviors of foundation models in AI applications. They are used throughout commercial AI products, but are rarely disclosed to the public or regulators, creating a serious trust and accountability gap in the wide deployment of AI systems. In this paper, we introduce Artificial Intelligence System Prompt Assurance (AISPA), a user-centric framework for systematically...
-
02
OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models
Qiushi Sun, Kanzhi Cheng, Yian Wang, Bowen Yang, Hang Yan, Liheng Chen, Fangzhi Xu, Zichen Ding, Nuo Chen, Jialin...
cs.AI · cs.CL · cs.CV
Computer-using agents (CUAs) are advancing rapidly across the digital world. A CUA trajectory records the agent's actions, states, and reasoning. Verifying whether it fulfilled the task instruction is central to CUA evaluation, data curation, and reinforcement learning. Neither human-written verifiers nor human annotators can provide such verification at scale, so the field increasingly turns to vision-language models (VLMs) as judges of CUA...
-
03
DualG-MRAG: Decoupling Macro-Reasoning and Micro-Matching for Multimodal Retrieval-Augmented Generation
Jiacheng Tao, Qingyun Sun, Haonan Yuan, Ziwei Zhang, Jianxin Li
cs.AI
While Multimodal Retrieval-Augmented Generation (MM-RAG) has shown promising results, it still struggles with complex multi-hop reasoning tasks. Existing methods primarily focus on independent instance-level matching, which often fails to capture explicit relationships across modalities and documents. Although Graph-enhanced methods introduce structural modeling, they face a fundamental challenge in multimodal scenarios: incorporating...
-
04
Rethinking Inference-Time Scaling in Local Computer-Use Agents: Failure Modes and Compute Tradeoffs
Woongkyu Lee, Jungwook Choi
cs.AI
Deploying autonomous computer-use agents (CUAs) locally is increasingly important for privacy, cost efficiency, and practical usability, yet improving their performance under strict hardware constraints remains challenging. While recent studies show that inference-time scaling can improve frontier computer-use agents through additional computation during execution, its effectiveness for resource-constrained local models remains poorly...
-
05
MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems
Mao-xun Huang, Jerry Wang, Yi-Cheng Lai, Zhengxin Zhang, Claire Cardie, Hen-Hsen Huang
cs.AI
Large language model-based multi-agent systems improve complex problem solving through task decomposition, agent specialization, information exchange, and intermediate validation. However, existing systems typically treat communication topology as a fixed design choice or an offline optimization target. We introduce MANTA, a framework for Multi-Agent Network Topology Adaptation that enables communication structures to self-evolve at inference...
-
06
Selective Credibility-Limited Belief Update
Theofanis Aravanis, Costas D. Koutras
cs.AI · cs.LO
Belief update concerns changes in an agent's beliefs induced by changes in the underlying world. Standard Katsuno-Mendelzon update assumes that an epistemic input can be incorporated from every initially possible world, whereas credibility-limited belief update restricts, for each source world, the successor worlds regarded as credible or reachable. Nevertheless, existing credibility-limited approaches treat the epistemic input as an...
-
07
InfoOps Bench: A live information operations safety benchmark
Dorian Quelle, Lisa-Maria Neudert, Jonathan Bright, John Gallacher
cs.AI
In this paper we present an active, constantly updated AI benchmark which measures the integrity of frontier language models against being co-opted for state-backed information operations. We draw on over 2,100 information operations from a live monitoring pipeline which tracks Russian, Chinese and Iranian state-backed information assets. Alongside this paper, we release a companion website that tracks the most prominent claims spread by...
-
08
SCOPE: Supply-Chain Operations through Coupled Policies for End-to-End Coordination
Yunhao Liang, Xianqi Cao, Pujun Zhang, Yuan Qu, Yongzhi Qi, Ningxuan Kang, Max Z. J. Shen
cs.AI · cs.LG
Can supply-chain AI move beyond isolated decision modules toward unified operational planning? A complete replenishment plan specifies which products each location carries, which upstream facility supplies it, how often it is replenished, and how deliveries are routed. These decisions are operationally coupled: the selected assortment changes the demand and load passed to later stages; source assignment and replenishment frequency reshape the...
-
09
A Fuzzy Rule-based Neuro-Symbolic Approach for Pipe Severity Prediction in Sewer Networks
Ngoc Thai Le, Thanh Ma, Umberto Straccia
cs.AI
Standard automated sewer pipe severity assessment relies on direct image classification, creating a "black box" where the link between visual defects and final severity scores remains implicit. This study introduces a modular, fuzzy rule-based neuro-symbolic framework that bridges this gap by decoupling neural perception from symbolic reasoning. The perception module utilizes a Swin Transformer to predict 14 multilabel inspection CODE degrees...
-
10
Towards Autonomous Aircraft Surveillance from Nanosatellites through On-Board Inference and Generative Data Augmentation
Antonio Delgado-Rosa, David Muñoz-Valero, Enrique Adrian Villarrubia-Martin, Juan Moreno-Garcia
cs.AI · cs.CV
Airborne surveillance from low Earth orbit is hindered by two interconnected bottlenecks: nanosatellites have a limited downlink budget, yet the conventional approach still transmits terabytes of raw imagery to the ground for processing, and open satellite datasets for aircraft are scarce and severely class-imbalanced. These limitations either delay timely decision-making or prevent standard detectors from learning robust representations of...
-
11
A report-grounded vision-language foundation model for colonoscopy from 280000 routine reports
Jia Yu, Yan Zhu, Yili He, Zilong Wang, Xinyang Jiang, Peiyao Fu, Ruijie Yang, Tianyi Chen, Siyuan Li, Zhihua Wang,...
cs.AI
Vision-language models remain underused in colonoscopy despite the rich expert descriptions recorded in routine reports. These reports document lesion appearance, size and location but summarise entire procedures rather than caption individual frames, leaving clinical findings only weakly linked to the corresponding images. Here we develop EndoCLIP, a colonoscopy vision-language foundation model trained on 125,756 lesion-level image-text...
-
12
LeanCSP: A Framework for Certifying Constraint Reformulation and Solving in Lean
Pablo Manrique, Stefan Szeider
cs.AI · cs.LO
Constraint programming is a core technology for solving complex combinatorial problems in scheduling, planning, configuration, and verification. Trusting its results therefore demands guarantees at two levels: that reformulations applied beforehand are semantics-preserving, and that solvers produce correct answers. In this work, we introduce a framework that addresses both verification levels in the Lean theorem prover: it can be used to...
-
13
SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute
Hongyu Chen, Liang Lin, Guangrun Wang
cs.AI · cs.CL
Scaling test-time computation can improve language-model reasoning, but uniform budgets waste computation on easy inputs, while verifier-guided refinement relies on external feedback. We introduce Self-Verifying Refinement (SVR), an oracle-free multi-turn reinforcement learning framework that learns to use self-verification as a compute-control policy. At each turn, the model produces a solution together with a discrete correctness verdict...
-
14
Metaphor Tracer: A Theory-Informed Analysis of Hidden States
Marc Heimann, Roxana Assadi Moghaddam, Olga Brovkina, Mark Pettifor, Lutz Goetzmann
cs.AI · cs.CL
What do a language model's hidden states say about the organization of a single text? From one forward pass, without training, we score every token position on two properties. The *aggregator* measures whether the position consolidates the whole text into a stable configuration. The *differentiator*, whether other tokens are transiently carried into its subspace as the model reads: metaphor in its root sense, transport. Constants were frozen...
-
15
A foundation model of numerical intelligence with cross-disciplinary generalization
Chenghan Wu, Zongmin Yu, Liu Yang
cs.AI
Intelligence is commonly understood as the ability to acquire and apply knowledge, adapt to unfamiliar situations and solve new problems. Large language models exhibit this capacity by inferring task-relevant knowledge from textual context and applying it to new tasks. Yet intelligence need not be confined to language. For scientific and social systems, we need models that acquire and apply knowledge from numerical context-an ability we call...
-
16
When Derived Measurements Mislead: Quantifying and Mitigating LLM Over-Trust with Privileged-Modality Reliability Evidence
Zongheng Guo, Tao Chen, Tianli Li, Mingzhe Cui, Yang Jiao, Lei Xie, Yi Pan, Xiao Hu, Manuela Ferrario
cs.AI
Derived measurements increasingly enter large language model (LLM) pipelines as direct facts despite their instance-dependent validity. We define derived-feature over-trust (DFOT) as the failure in which a downstream LLM assigns such a measurement the epistemic status of a direct fact or uses it outside its valid scope. Using physiological sensing as a case study, D1 tests acceptance of a PPG-derived rhythm contradicted by offline ECG,...
-
17
WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning
Haozhe Hu, Hao Wu, Peiran Yin, Chao Han, Yunpu Ma, Xiaoyu Shen
cs.AI · cs.CL · cs.LG
Pruning is a promising approach for improving the efficiency of LLMs. Existing static structured pruning methods are hardware-friendly and can deliver practical throughput gains, but their input-agnostic computation allocation often causes substantial accuracy degradation under aggressive sparsity. Recent dynamic sparsity methods improve quality retention by adapting computation to individual inputs, yet they remain largely limited to...
-
18
QuantWAMs: Calibrating at the Right Granularity for World Action Models
Jiacheng Zhou, Jinfan Lv, Ruixuan Li, Longtai Zhang, Yan Wang, Wenqiang Zhang, Lizhe Qi
cs.AI · cs.LG
World Action Models (WAMs) jointly predict future observations and actions, but their iterative denoising and closed-loop execution make efficient deployment costly. Existing post-training quantization (PTQ) methods are poorly suited to WAMs because they rely on open-loop objectives, homogeneous model assumptions, and calibration distributions that do not reflect deployment. We present QuantWAMs, a PTQ framework that aligns quantization...
-
19
GLM-RAG: Graph Language Models for Graph-Based Retrieval-Augmented Generation
Maya Arseven, Anette Frank, Beni Egressy, Johann Higl, Moritz Plenz
cs.AI · cs.CL · cs.IR
Retrieval-augmented generation (RAG) over knowledge graphs requires retrievers that can effectively capture both graph structure and semantic information. Recent approaches have explored graph neural network (GNN)-based retrievers to model graph topology in multi-hop reasoning tasks. In parallel, graph language models (GLMs) have emerged as a promising paradigm that integrates graph reasoning and the semantic capabilities of language models....
-
20
When Specifications Conflict: A Symmetry-Based Framework for Measuring LLM Preferences
Tairan Wang, Liang Zhou, Zikang Zhan, Pingchuan Yan
cs.AI
Large language models (LLMs) are increasingly required to integrate multiple sources of information that may be inconsistent or conflicting. However, there is still a lack of controllable and attributable methods for analyzing how models resolve conflicts between competing specifications. We propose a controlled experimental framework for studying model preferences under conflicting specifications. By constructing specifications with explicit...
-
21
HyperClaim: Fine-Grained Cross-Modal Hypergraph Reasoning for Video Misinformation Detection
Xiangbo Wang, Jiasheng Zhang, Xingtong Yu, Luoqiang Lei, Delvin Ce Zhang
cs.AI · cs.MM
Video misinformation detection is often approached through global multimodal fusion or free-form multimodal reasoning. Both paradigms can under-represent localized authenticity cues that arise from coupled interactions among query phrases, contextual text, and short temporal spans of frames. Because such interactions are inherently higher-order, pairwise graph formulations are insufficient to capture multi-way cross-modal dependencies,...
-
22
How Benchmarks Mis-Score Computer-Use Agents
Zihan Dong, Zhiyuan Ma, Zekun Wang, Yunqing Li, Zirou Liu, Ruixuan Deng, Qishi Zhan, Rui Qian
cs.AI
Computer-use agents (CUA) are being deployed to browse the web and operate desktop software, yet their benchmark scores are still commonly produced by brittle scripted oracles. A score is the output of a pipeline in which tasks can be stale, trajectories can omit decisive visual evidence, evaluators can reject valid alternatives, and aggregate reports can hide the cause of failure. We organize these problems into a reliability framework...
-
23
Correcting What You Cannot See: Credit Assignment for Perception Distillation in Multimodal Reasoners
Feng Xiong, Leyan Xue, Hongyu Lin
cs.AI
On-policy distillation provides dense supervision for multimodal reasoners, but its trajectory-level reward cannot determine whether a failed answer arose from perception or subsequent reasoning. Perception Success Rate (PSR), estimated from multiple reasonings sharing one perception, remains ambiguous because low success conflates perceptual insufficiency with reasoning difficulty. We introduce \textbf{Perception-Correction Distillation...
-
24
Paying for Honesty Without Knowing the Truth: Reputation-Penalty Design for LLM Marketplace Agents
Mingdai Yang, Shicheng Fan, Kejing Yu, Duohao Wang, Li Sun, Hao Peng, Philip S. Yu, Zhiwei Liu
cs.AI
LLM agents increasingly act as autonomous merchants that write their own product listings, and under competitive pressure, they fabricate attributes to win sales. Even under instructions to be honest, they fabricate attributes in a majority of listings across models. A platform's obvious remedy---verifying each claim against the truth---is unavailable, because it observes only a noisy, biased complaint signal, never the ground truth. We...
-
25
PathView-Bench: Can Multimodal Large Language Models Achieve Fine-grained Multiscale Understanding of Pathology Images?
Zongyi Chen, Yu Liang, Jie Lin, Liansheng Wang
cs.AI
Multimodal large language models (MLLMs) are increasingly used to analyze pathology images. However, dominant multimodal benchmarks in pathology mainly score final diagnostic answers, captions, or reports. These evaluations provide limited insight into whether a model understands the multiscale visual content needed for pathology reasoning and decision-making. We introduce PathVU, a vision-anchored benchmark for fine-grained and multiscale...
-
26
One Human, $N$ Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated Confidence
Cesare Zavattari, Alessandro Tommasi, Giuseppe Prencipe
cs.AI
A single human must audit $N$ LLM agents under a budget of $B \ll N$ audits per round, guided by self-reported confidence that may be adversarially miscalibrated and by correlated errors. We model this as budgeted noisy inspection over a two-level Gaussian copula and locate the miscalibration threshold $δ^*$ past which confidence-ranked auditing is \emph{worse} than random. Two a-priori expectations reverse: $δ^*$ \emph{rises} as the budget...
-
27
Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3
Jens Lehmann, Andrei Aioanei, Sahar Vahdati
cs.AI · cs.CV · cs.SC
ARC-AGI-3 turns abstraction into an interactive problem of skill acquisition. A player must infer an unfamiliar game's rules, hidden state, and goal while maintaining action efficiency because every move counts. We formalize these environments as parameterized rendered deterministic Moore machines and introduce Tycho, a coding-agent system that constructs and uses game-specific models during interaction. Tycho separates actionable...
-
28
MemHarness: Memory Is Reconstructed, Not Replayed
Rong Wu, Daocheng Fu, Licheng Wen, Xuemeng Yang, Shu Zou, Jianbiao Mei, Yuxin Wang, Hairong Zhang, Yu Yang, Tao Hu,...
cs.AI
Retrieving past experiences has become a common strategy to enhance large language model agents. However, most existing memory-augmented agents treat retrieved experiences as static records to be replayed verbatim, injecting them into the context regardless of whether they align with the agent's current situation. This ``replay'' paradigm ignores the gap between the abstract, general nature of stored experience and the concrete, ever-changing...
-
29
LLM-Guided Evolutionary Search for Constraint Model Reformulation to Improve Solver Efficiency
Kostis Michailidis, Dimos Tsouros, Nguyen Dang, Tias Guns
cs.AI
Combinatorial problems appear in numerous industrial applications. A common approach is to formulate these problems as declarative constraint models that can subsequently be compiled to and solved by a range of back-end solvers. Recent work shows that Large Language Models (LLMs) can produce correct models from natural language, but even a correct model can be expensive to solve because performance remains sensitive to modelling choices. In...
-
30
Operationally Guided Placement-Aware Learning for Industrial Online 3D Bin Packing
Dheeraj Poolavaram, Aanchal Rajesh Chugh, Sebastian Dorn
cs.AI
The online three-dimensional bin packing problem (3D-BPP) is a longstanding challenge in logistics and industrial palletizing. Recent learning-based methods use a learned policy to select among feasible candidate placements. Performance depends on the candidate generator and representation, especially in industrial settings where packings must be space-efficient, stable, compact, and balanced. However, prior work has mainly optimized the...
-
31
AI and Authenticity in Islamic Research: A Critical Evaluation of Generative AI Reliability, Hallucination, and Source Fidelity in Quranic, Hadith, and Fiqh Knowledge
Muhammad Sajjad Akbar
cs.AI
Generative Artificial Intelligence (AI) is increasingly used by Muslims for religious guidance, Qur'anic interpretation, Hadith explanation, jurisprudential rulings, and Islamic education. Despite its growing adoption, there is limited empirical evidence on whether current AI systems provide authentic, verifiable, and trustworthy Islamic knowledge suitable for high-trust religious contexts. This study evaluates six leading generative AI...
-
32
CDAE: Enhancing Perturbation Robustness in Pretrained Language Models with Contrastive Denoising
Sina Heydari, Amirreza Abbasi, Mohsen Hooshmand, Majid Ramezani
cs.AI · cs.CL
Pre-trained language models have significantly improved sentence representation learning, yet their embedding remain sensitive to semantic preserving textual perturbations such as synonym substitution, masking and word dropout. This work proposes a lightweight Contrastive Denoising Autoencoder (CDAE) that refines pre-trained BERT embedding by jointly optimizing contrastive and reconstruction objective to learn perturbation-invariant...
-
33
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents
Hanzhang Zhou, Panrong Tong, Xu Zhang, Quyu Kong, Chenglin Cai, Tianyu Xia, Gongjie Zhang, Jianan Zhang, Long Li,...
cs.AI · cs.CV
GUI agents have the potential to become a general purpose executor over existing digital devices. To advance them toward real-world use, we envision agents that operate reliably on real devices, execute workflows across platforms, combine GUI interaction with CLI execution, complete long-horizon tasks, proactively initiate useful services, and autonomously improve their capabilities with minimal human effort. Guided by this vision, we present...
-
34
Old Tricks, New Models: How Simple Image Transformations Break Modern AI-based Content Moderation
Marco Alecci, Francesco Marchiori, Iyiola Emmanuel Olatunji, Tegawendé F. Bissyandé, Jacques Klein
cs.AI · cs.CR · cs.SE
While automated content-moderation systems have become essential for screening harmful content at scale, conventional task-specific classifiers often provide limited policy cov- erage and contextual understanding. Recently, commercial multimodal moderation APIs built on large foundation models have been introduced with the promise of providing broader and more capable safety filters. In this work, we analyze whether this shift also yields...
-
35
AgenticASR: Refining Speech Recognition in Real-World Scenarios via an Agentic Approach
Zixuan Jiang, Binghao Qiang, Jiaying Chi, Yanqiao Zhu, Kai Yu, Xie Chen
cs.AI
Automatic speech recognition (ASR) has achieved substantial gains in transcription accuracy, yet verbatim transcription does not necessarily produce readily usable text. It retains fillers, repetitions, false starts, and self-corrections that increase reading effort, obscure the speaker's final intent, and propagate unresolved or abandoned content to downstream tasks. Existing spoken-to-written methods process completed audio or transcripts...
-
36
ConMem: Contribution-Aware Memory for Long-Horizon Manufacturing Inspection Logs
Bingchen Liu, Yuanyuan Fang, Lei Liu, Guangyuan Dong, Xing Fu, Yuanyuan Gao, Shuyue Wei, Xin Li, Xiangtian Meng
cs.AI
Long-horizon steel-equipment inspection requires reasoning over heterogeneous records accumulated across repeated inspection cycles. Existing retrieval-augmented generation systems treat historical logs as a static corpus and retain records without estimating their diagnostic value, failing to report early risk. To this end, we propose ConMem, a contribution-aware memory framework for LLM-assisted equipment inspection, supporting a...
-
37
BlueprintRepair: Typed Local Edits for Failed Lean Proof Blueprints
Ruslan Khrulev
cs.AI
LLM-based Lean proving systems increasingly organize a proof as a blueprint: a dependency graph of formal statements. We introduce BlueprintRepair, a repair interface that lets a model change this graph through ten schema-checked local operations. An operation names the node it edits, so the target theorem cannot be changed. Lean checks every applied change, and an accepted repair must declare every blueprint lemma its proof uses. We also...
-
38
Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training
Jiawen Tao, Miao Peng, Yaoming Li, Xiaokun Yuan, Mengzhou Wu, Wenhan Yu, Guoan Wang, Nuo Chen, Tong Yang, Maxm Pan
cs.AI
Synthetic textbook data has improved language model pre-training, but prior work largely treats the benefit as a property of generated content or local rewriting style. We study a different factor: whether related content is organized into coherent book-level documents. We contribute both a scalable synthesis pipeline and controlled evidence that this organization matters. The pipeline retrieves source material from a pre-training corpus,...
-
39
MIND: Lightweight and Effective Memory Injection Defense for LLM Agents via Intent-Aware Information Bottleneck
Dongyi Liu, Haixing He, Xiaobao Wu, Jia Li
cs.AI
Memory-augmented LLM-based agents are vulnerable to memory injection attacks: Agents may retrieve poisoned memory from attackers, which diverts their behavior from initial user intent and finally causes task failure. However, existing defense mechanisms either incur high computational cost or suffer from information redundancy in multi-turn contexts. To address these challenges, we propose Memory Intent-Aware Neural Denoising(MIND), a...
-
40
An Instrument to Evaluate Governance Proposals: AI Policy Analysis at Scale
Paulo Carvao, Claudio Mayrink Verdun, Isabel Adler, Jeffrey Zhou
cs.AI
This paper introduces a policy analysis framework for systematic, transparent assessment of AI governance proposals in an evolving and contested regulatory landscape. AI policy debates often collapse into binary positions that obscure underlying tradeoffs and normative assumptions. The framework structures policy analysis around multiple policy attributes, allowing users to surface priorities and tensions without prescribing outcomes. We use...
-
41
PerturbMap: Cross-Context Transfer of Single-Cell Perturbation Responses
Panpan Cui, Yiqi Liu, Wenhao Sun
cs.AI
Single-cell perturbation atlases rarely measure every intervention in every cellular context: a query perturbation is often observed in one or more source contexts but missing in the recipient context where its effect is needed. Ignoring those measured responses discards query-specific experimental evidence, whereas copying or weakly calibrating them across contexts risks transferring the wrong signal. We propose PerturbMap, which predicts a...
-
42
Diversifying Personalized Research Ideation against AI-Induced Homogenization
Rui Xu, Yunke Wang, Linwei Tao, Wenjie Xuan, Yong Luo
cs.AI
AI-assisted research ideation has emerged as a promising paradigm for accelerating scientific discovery, with systems now capable of generating research directions conditioned on papers, topics, or lightweight researcher contexts. Yet current systems largely optimize individual suggestions in isolation. This leaves two blind spots. First, coarse researcher representations may elicit mainstream directions that appear broadly feasible, but lack...
-
43
Distilling Answer Set Programming Theories from Large Language Models
Nelson Higuera Ruiz, Markus Hofmarcher, Claudiu Leoveanu-Condrei
cs.AI
Writing Answer Set Programming (ASP) theories from scratch is a difficult and time-consuming task. We take a neurosymbolic approach to study whether a model can distill complete and correct theories, given a fixed agent harness with the solver in the loop. The protocol is dataset-agnostic: with a single prompt and an empty file as the starting point the model is given a 1-hour time limit to derive a complete theory. We chose VQA as the...
-
44
Group-Reflective Self-Distillation for Agentic Reinforcement Learning
Binbin Zheng, Zijun Xie, Guanqun Zhao, Enlei Gong, Xing Ma, Xiaoliang Fu, Zeyu Chen
cs.AI · cs.LG
Reinforcement learning with verifiable rewards (RLVR) is effective for training large language model agents. However, terminal rewards provide only coarse trajectory-level supervision, leaving successful behaviors, recurring mistakes, and incidental choices entangled in the same outcome signal. Existing agentic self-distillation methods enrich sparse supervision with natural-language skills, but skills retrieved externally or extracted from a...
-
45
Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale
Yash Pandya, Sahil Gupta, Sarthak Harne, Archana Yadav, Kavyansh Chourasia, Hussein Mozannar, Vibhav Vineet, Sara...
cs.AI · cs.LG
Computer-use agents learn from what their actions change, so training one needs applications it can act on, break and reset. The applications that matter most are login-gated and stateful, so synthetic environments stand in for them. Recent pipelines generate such environments in bulk, which moves the bottleneck from how many exist to what is inside each one. The returns, we find, come from three properties: how much behavioural depth an...
-
46
SemPIC: Learning Semantic Position-Independent KV Caches
Hui Xie, Peng Xiao, Yutong Deng\textsuperscript, Shuoran Dou, Jian Yang, Jinyang Guo
cs.AI
Long-context retrieval and agentic workloads repeatedly reuse the same documents under changing instructions, histories, and document orders. Prefix caching cannot exploit this reuse, while position-independent caching (PIC) remains unreliable because independently compiled KV states lack the future context in which they will be consumed. Our diagnostics show that a learned boundary-conditioned baseline sharply reduces attention deviation...
-
47
IndustryForge-27B: A Domain-Enhanced Multimodal Foundation Model for Industrial CAD
Nianchen Deng, Jiaxin Ai, Tao Hu, Shu Zou, Yurui Dong, Siqi Li, Xinyu Cai, Xuemeng Yang, Licheng Wen, Hongbin Zhou,...
cs.AI
Automating industrial CAD design and manufacturing places distinctive demands on multimodal foundation models: the model must see engineering drawings and 3D geometry screenshots, write correct parametric-modelling scripts and Windows COM API code, and cover the full range from single parts to assemblies. General-purpose multimodal models fall short on these tasks, while single-task fine-tuning is too narrow to support the diverse calls that...
-
48
SKILL-KD: Contrastive Skill Distillation for LLM Agents
Qiming Shi, Yibo Dou, Jiawen Zhu, Yulong Tao, Linbo Jin, Zhaolu Kang, Yunfan Zhou, Di Weng
cs.AI
Skill-based prompting has become a practical mechanism for improving large language model (LLM) agents, yet existing skill acquisition methods often treat skills as experience summaries, memory entries, or direct summaries of successful demonstrations. This creates a mismatch for weaker student agents: when a student fails because it lacks task knowledge or operational strategy, its failed trajectory may not contain enough evidence to infer...
-
49
DataClawEval: A Benchmark for Data Engineering Agents in Real Industrial Harness
Debin Meng, Jiaming Yang, Zefang Zong, Tengyue Xu, Haining Xie, Yang Li, Peng Chen
cs.AI
Large language models (LLMs) and LLM-based agents are increasingly being deployed to automate complex workflows, promising to revolutionize data management and processing. However, existing benchmarks predominantly focus on simplified Text-to-SQL translation or data analysis, leaving the critical and complex domain of end-to-end data engineering largely unexplored. To bridge this gap, we introduce DataClawEval, the first comprehensive...
-
50
MUL-T: Decoding Spatial Cellular Architecture in Multiplexed Tissue Images
Farzaneh Seyedshahi, Kai Rakovic, Adalberto Claudio Quiros, John LeQuesne, Ke Yuan
cs.AI · cs.CV
Understanding tissue organisation in multiplexed imaging requires modelling both cellular phenotypes and their spatial context. Existing approaches typically rely on handcrafted features, such as marker intensity statistics or cell-type proportions, which often fail to scale or generalise across cohorts with heterogeneous marker panels. We introduce MUL-T, a lightweight transformer framework that reframes tissue architecture as a masked...
-
51
MMLDSum-LLM: Multimodal Long-Document Summarization with Visual-Alignment and Keyword-Aware
Xianpeng Zhang, Jiahua Yang, Dongyu Chen, Lei zhang, Jian Ma, Xu guohuan, Haonan Lu, Tianhuang Su, Chuangchuang...
cs.AI
Multimodal long documents are core carriers of professional knowledge, where critical evidence is sparsely distributed across paragraphs and modalities. This easily causes key information omission and cross-modal hallucinations in summarization by multimodal LLMs. These issues stem from attention drift in long-range dependency modeling and gaps in inter-modal alignment. To address this, we introduce MMLDSum-Bench, a high-quality benchmark for...
-
52
SKIMIX: Multi-Agent Harness-Time Scaling with Skill Mixture for Dynamic Harness Engineering
Jia Luo
cs.AI
AI agents increasingly rely on large skill libraries, but selecting, combining, and maintaining skills remains difficult. We propose SKIMIX, a multi-agent framework in which agents with different skill portfolios collaborate through iterative refinement. SKIMIX combines embedding-based skill retrieval, submodular anti-dilution routing, and adaptive skill evolution. Across six reasoning benchmarks, multi-agent collaboration substantially...
-
53
Share the Judge, Learn the Deferral: Where Specialization Helps LLM Evaluation
Weining Zhang
cs.AI
Agentic systems have widened the gap between producing candidate outputs and reviewing them. This paper asks a practical architectural question: should domain specialization be built into an evaluator's weights, or into the rule that decides when its judgment can be trusted? We study 99,952 public, rubric-conditioned examples. Supplying the correct rubric improves locked-test accuracy by 2.11 points over a response-only control; replacing it...
-
54
MARS-RA: Rank Aggregation for Credit Assignment via Multimodal Comparisons in Embodied Multi-Agent Cooperation
Dawei Wang, Di Zhao, Xinyuan Liu, Marci Chi Ma, Xiaoyang Liu, Chengming Zhou, Gary Ushaw, Richard Davison
cs.AI
Credit assignment is a fundamental challenge in cooperative multi-agent reinforcement learning, particularly in embodied AI settings characterized by limited and delayed feedback as well as dynamically changing numbers of active agents. We propose MARS-RA, a framework that reformulates credit assignment as a rank aggregation problem using contribution-based pairwise comparisons among agents generated by large multimodal models. This shift...
-
55
From Scoring to Acting: Outcome-Verified Comparative Self-Distillation for LLM Agents
Xu Xia, Jinghua Piao, Min Yang, Xiaochong Lan, Jiaju Chen, Yong Li
cs.AI
Recent work on LLM agents is shifting from external capability elicitation to capability internalization, enabling agents to retain useful skills without retrieval at inference time. On-policy self-distillation (OPSD) offers a promising direction, but many existing methods typically supervise students by scoring actions along student-generated trajectories. Such supervision has two limitations: teacher preferences are not validated by...
-
56
Shapes from Examples: Foundations of Shape Learning in Recursive SHACL
Bente Gortworst, Cem Okulmus, Magdalena Ortiz, Anni-Yasmin Turhan
cs.AI · cs.LO
SHACL shapes enable data graph validation, making automatic shape learning essential for knowledge graph applications. We investigate the well-known fitting approach to this task: given sets P and N of positive and negative example nodes from an input graph, compute a shape expression C, possibly using shape names defined in a recursive shape catalogue, that validates at every node in P and none in N. We focus on the case where C is written...
-
57
The Geometric Nature and a Free Proxy for Flow-Matching Uncertainty
Ziyang Rao, Yiren Zhao, Weiyu Guo, Ben Fei, Yandong Guo, Hui Xiong
cs.AI
Flow matching (FM) has become a popular action head paradigm for modern embodied models. However, as a conditional generative model, it does not explicitly expose its inherent uncertainty, producing faulty action chunks even when it misinterprets the scene or encounters out-of-distribution (OOD) inputs. Therefore, determining when an FM-generated action can be trusted is essential for safe deployment, yet existing uncertainty estimation...
-
58
Meta-Task: Turning Terminal Task Synthesis into a Terminal Task for Scalable Agent Training
Zhihong Pan, Jiyuan He, Kai Zhang, Yupeng Han, Ze Liu, Yuze Zhao, Yongcong Ye, Zhaohua Yang
cs.AI
Training terminal agents at scale requires diverse, verifiable terminal tasks and high-quality interaction trajectories, yet acquiring such data remains a significant challenge. Existing synthesis methods face two key limitations: (1) weak reliability caused by the disconnect between task generation and real execution, and (2) limited diversity and scalability due to dependence on existing repositories. We propose Meta-Task, a framework that...
-
59
One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs
Enyi Shi, Fei Shen, Chuancheng Shi, Linxia Zhu, Shuyi Miao, Jinhui Tang, Tat-Seng Chua
cs.AI
As large vision-language models (LVLMs) are deployed globally, the combination of multilingual instructions and visual information makes malicious attacks more covert and sophisticated than ever before. However, existing methods isolate language and modality defenses, which, coupled with the scarcity of safety data and high fine-tuning costs, makes it difficult for models to defend against compound attacks. To address this severe challenge,...
-
60
IFHierBench: Hierarchical Instruction Following for Large Language Models
Yuetian Mao, Chunyang Chen
cs.AI · cs.CL
Instruction-following ability is critical for deploying large language models in real-world applications, where downstream components depend on the output satisfying specific constraints. Modern deployments increasingly handle the full task in a single LLM call, with one prompt specifying a layered output whose overall artifact, structural sections, and nested fields must each satisfy concrete constraints. Existing instruction-following...
-
61
A Cross-Architecture Audit of Direction-Based Inference-Time Defences in Vision-Language Models
Xiangyu Yin, Tora Bodin, Rohan Menon, Chih-Hong Cheng
cs.AI
Inference time defences against vision language model jailbreaks often subtract a calibrated direction from the residual stream at a chosen decoder layer. We compare five defence candidates across 15 model and layer cells from four architectural families under a magnitude controlled protocol that matches the intervention size for each prompt and pairs every direction with a random control of the same norm. The candidates are the mean image...
-
62
MMHBench: A Multi-Perspective Benchmark for Mental Health Understanding in Long-Form Videos
Jinpeng Hu, Erqiang Wang, Shan Wang, Zhuo Li, Peipei Song, Xun Yang, Meng Wang
cs.AI · cs.CV
Mental health understanding in long-form videos requires nuanced reasoning over observable behavior, interpersonal context, and latent psychological states. Existing benchmarks largely reduce this task to coarse-grained classification, providing limited insight into whether models truly understand psychological phenomena or rely on superficial correlations. To address this limitation, we introduce MMHBench, a comprehensive multimodal...
-
63
Dynamic Spectral Filtering for Temporal Graph Learning: Learning Evolving Propagation Operators
Yan Kong
cs.AI · cs.LG
Temporal graph learning is commonly organized around the evolution of node states or the encoding of interaction histories. We study an underexplored, operator-centric question: should the graph propagation mechanism itself evolve over time? We introduce Dynamic Spectral Filtering (DSF), which represents propagation at snapshot t by a Chebyshev polynomial filter with vector-valued, time-dependent coefficients. DSF explicitly treats these...
-
64
Not All Tokens Deserve Equal Credit: Counterfactual Sensitivity Credit Reallocation for Long-CoT Reasoning
Qiangqiang He, Zhongheng Wu, ZiJian Wang
cs.AI
Reinforcement learning with verifiable rewards (RLVR) is central to improving long-CoT reasoning in large language models. Critic-free methods such as GRPO convert response-level rewards into advantages and uniformly broadcast them across tokens, overlooking their unequal contributions to the final outcome. On-policy self-distillation (OPSD) instead provides dense distributional supervision by minimizing the forward KL divergence between an...
-
65
An Empirical Study of Coordination Mode as the First-Class Citizen in From-Scratch Multi-Agent Coding
Yanyu Ren, Yunfeng Bai, Xizheng Wang, Li Chen, Dan Li
cs.AI
Multi-agent vibe coding promises to accelerate software development, yet existing benchmarks rely on synthetic environments that ignore practical time and monetary costs, conflate reasoning with communication, and reward only superficial completion. We introduce multi-agent from-scratch evaluation benchmark, MSEval, evaluating multi-agent coding on real-world tasks. Grounded in 10 authentic, full-stack projects across 10 domains, MSEval...
-
66
Search as Computation Allocation
Alexander Tuisov
cs.AI
Many algorithms spend an internal resource before returning a decision and are evaluated only by the quality of that terminal output. We formalize such procedures as terminal computation-allocation problems: costly computations produce observations, update beliefs about a latent environment, and matter only through terminal decision loss. Bellman equations characterize optimal allocation under fixed budgets, priced computation, and exact...
This edition is part of The Daily Abstract — cs.AI archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.