cs.AI · 2026-08-28 · No. 98
Artificial Intelligence, 2026-08-28.
53 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
53 entries-
01
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
Liyan Tang, Cyrus Rashtchian, Chun-Sung Ferng, Andrew Tomkins, Da-Cheng Juan, Tu Vu
cs.AI · cs.CL
Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent experience, which enables agents to progressively adapt through interaction. However, the insights that guide skill development typically remain scattered across optimization histories, limiting their systematic reuse across iterations. We introduce WikiSkill, a...
-
02
Mechanistic Reaction Prediction via Discrete Flow Matching on Graph-Structured Electron Occupation
Nguyen Xuan-Vu, Octavian Susanu, Daniel Armstrong, Philippe Schwaller
cs.AI
Chemical reactions are fundamentally transformations in electron space, yet most machine learning approaches model them either through \textit{de novo} generation of product molecules or through heuristic graph edits that operate directly on molecular topology. We introduce MAELLE (\textbf{M}ech\textbf{A}nistic \textbf{E}dit f\textbf{L}ow-matching on e\textbf{L}ectron r\textbf{E}arrangements), which instead models reactions as discrete flow...
-
03
Learning a Continuous Sepsis Severity Score Without Hour-by-Hour Supervision: A Two-Site Retrospective Study
Kevin Zhu, Ryan Zhang, Baraa Abed, Tilendra Choudhary, Malvern Madondo, Mehak Arora, Yixuan Yang, Alasdair Gent,...
cs.AI · cs.LG
Currently used sepsis severity indices rely on fixed variables and weights established decades ago, which are coarsely discretized and calibrated to a cohort that no longer reflects contemporary critical care. No alternative learned directly from patient trajectories is in routine use. We conducted a retrospective two-cohort study on a total of 29,116 and 7,691 adult patients meeting Sepsis-3 criteria from two hospital systems in...
-
04
CorporateBench: Large-Scale Q&A Benchmarking with Temporal Knowledge Bases
Sil Hamilton, Albert Yu Sun, Oscar J. Romero, Carl-Leander Henneking, David Mimno, Bishan Yang, Igor Labutov
cs.AI · cs.CL · cs.IR · cs.LG
LLMs are increasingly able to answer complex questions about enterprise-scale document collections. But evaluation is hard: companies don't want to share internal communications, and synthetic datasets have been overly simple. We present CorporateBench (CB), a human-validated multi-task Q&A benchmark whose scale approaches the conditions LLMs encounter in corporate communication networks, with evaluation corpora surpassing 230,000 documents....
-
05
Sophistication in GenAI Use: Field Evidence from a Large Firm
Nicholas J. Hallman, Zachary T. Kowaleski, Anu Puvvada, Jaime J. Schmidt
cs.AI · econ.GN
We study how sophistication in generative AI (genAI) use varies among the back-office workforce of a large firm. Using proprietary data, we observe 713,564 employee prompts and their corresponding large language model responses from nearly 4,000 back-office employees across 15 functional areas over eight months in 2025. We document three main findings. First, senior employees exhibit more sophisticated genAI use, consistent with domain...
-
06
Not All Eval-Awareness Is Equal: Capabilities Framing Predicts Compliance
Allison Zhuang, Santiago Aranguri
cs.AI
Steering interventions targeting eval-awareness, a model's recognition that it is being tested, are increasingly used in safety evaluation pipelines, where evaluation-awareness is treated as a single quantity to be suppressed. We show that verbalized eval-awareness in chain-of-thought can be identified as capabilities-flavored ("the user is testing my ability to follow instructions"), safety-flavored ("the user is testing my boundaries"),...
-
07
Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification
Jinghan Xu, Yikai Zhang, Aili Chen, Weiyuan Li, Jiaqing Liang, Deqing Yang
cs.AI
Agent harnesses shape how language-model agents use instructions, tools, and runtime components, but adapting these harnesses requires costly verification. Existing propose-and-verify methods typically score every candidate on a fixed task set, wasting rollouts on unrelated behaviors and allowing aggregate scores to obscure specific regressions. We introduce HarnessLens, a budget-aware framework for automated harness evolution. HarnessLens...
-
08
LLMs Can Design Near-Optimal OR Algorithms
Jackie Baek
cs.AI · cs.LG
We ask whether large language models (LLMs) can design effective algorithms for well-specified operations research (OR) problems. We study inventory control, queueing network control, and assortment optimization. We evaluate two levels of LLM use: at level 1, the model receives one problem instance and returns a solution for that instance; at level 2, it receives only the problem class description and broad parameter ranges, and returns an...
-
09
BrailleBench: Investigating Multi-Criteria Braille Comprehension in Large Language Models
Jinghan Zhang, Fengran Mo, Zhiyu Chen, Xiaoyan Han, Kunpeng Liu, Chang-Tien Lu
cs.AI · cs.CL · cs.HC
Although Large language models (LLMs) mediate access to knowledge and computational assistance, their capabilities should benefit vulnerable groups in the same way. However, it is unclear whether existing AI systems are inclusive enough for blind and deafblind users to access the same functionality through Braille, whose indicators, contractions, and digital representations introduce distinct requirements for model comprehension. To this end,...
-
10
Naive Prompt Optimization: Rethinking the Need for Complex Prompt Search
Yuan Chang, Xiaoqi Chen
cs.AI · cs.CL
Efficiently improving autonomous agents across diverse tasks is central to accelerating recursive self-improvement (RSI) in agentic AI, with prompt optimization emerging as a promising approach capable of delivering performance gains comparable to those achieved by fine-tuning model weights, while reducing computational costs in both optimization and serving. However, recent developments increasingly favor unnecessarily complex prompt...
-
11
What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents
Xingshan Zeng, Zishan Xu, Boju Zhang, Yuzhou Wu, Lingzhi Wang, Jianghao Lin, Liangyou Li, Yasheng Wang, Lifeng...
cs.AI · cs.CL
LLM agents increasingly rely on generated interaction data to learn how to interact with external environments. Agentic data generation must maintain consistency among environments, tasks, interactions, and success signals while producing experience that is useful rather than merely abundant. Existing work spans many agent domains, but domain-centered organization and heterogeneous evaluation often obscure common generation mechanisms and...
-
12
Calibrated Enough to Know, Not Calibrated to Act: Fabricated Evidence Makes LLM Agents Commit to the Unknowable
Pranav Aggarwal
cs.AI · cs.CL
An LLM agent shown a professional-looking market panel commits to a directional call on a provably unpredictable question far more often than one asked the bare question: across 12 frontier models, commitment rises from 6.5% to 54.0% as evidence is escalated. It commits just as readily when every number on the panel is invented: fabricating the entire display, so nothing the model can see is true except the question itself, still lifts...
-
13
BPMN4CAI: A BPMN Extension for Modeling Dynamic Conversational AI
Björn-Lennart Eger, Daniel Rose, Barbara Dinter
cs.AI
Conversational AI systems, such as chatbots and virtual assistants, are becoming increasingly important to digital business processes. However, the established Business Process Model and Notation (BPMN) standard faces challenges when representing dynamic, context-sensitive interactions. This paper addresses this methodological and practical research gap by developing a standard-compliant BPMN extension (BPMN4CAI). Using Design Science...
-
14
Thomson: Continual Learning of Frontier Models for SovereignAI
Shengzhuang Chen, Jerrod Parker, Yejin Bang, Andrew M. Bean, Nabeel Seedat, Stefan Winzeck, Daniil Glazko, Jannik...
cs.AI
The development of frontier models is commonly perceived to be the exclusive remit of a small number of heavily funded players, creating an information, economic and power asymmetry between developers and the diverse user base of modern AI. Recent public discourse acknowledges this concern, calling for SovereignAI (an organisation's capability to independently build, deploy and govern AI use), but offers little concrete advice on how this can...
-
15
When Tool Outputs Become Commands: Separating Action Induction from Runtime Authorization in Tool-Augmented LLM Agents
Xiaokun Guo, Zhen Xu, Dongdong Huo, Yanqiu Zhang, Wei Wang, Qinfu Yang, Dongjin Yu, Yu Wang
cs.AI · cs.SE
Tool-augmented LLM agents must rely on untrusted runtime Observations to complete open-ended tasks; however, when tool outputs no longer merely provide data but begin to specify concrete actions, they effectively become ``commands'' that can drive real-world side effects beyond user intent. We argue that this risk arises from conflating action induction with execution authorization. To address this distinction, we propose SARA, which treats...
-
16
Feature Transformation Enhanced Jacobi Polynomial Graph Filtering for Graph Anomaly Detection
Xiang Wang, Zhijun Cheng, Zhenyu Meng
cs.AI
In recent years, graph anomaly detection (GAD) based on frequency-domain filtering have achieved promising results. However, existing approaches still face three major challenges: First, they use static basic function to constructed graph filter which cannot effectively adapt to the frequency-domain distribution of graph data. Second, they fail to adequately consider the importance information of each attribute in the node feature vector,...
-
17
GRAIN: Bridging Name and Narrative Shifts in Real-World Graph Reasoning through Invariance-Rewarded Agentic RL
Zike Yuan, Han Zhang, Jianzhi Yan, Le Liu, Cai Ke, Huozhi Zhou, Jian Xie, Jiran Yin, Yukun Cao, Yue Yu, Hui Wang,...
cs.AI
Despite their potential in standardized graph tasks, Large Language Models (LLMs) remain brittle to real-world shifts in node identifiers and task formulation. While deterministic graph tools are invariant to such shifts, extracting topological structures from noisy text is highly fragile for LLMs, which often overfit to surface patterns. Moreover, mitigating these parsing failures via multi-agent systems incurs prohibitive latency. To...
-
18
TransMeme: A Multi-Agent Framework for Cross-Cultural Meme Transcreation
Jingyi Zheng, Yule Liu, Zifan Peng, Tianyi Hu, Yuemeng Zhao, Xinhu Zheng, Xinlei He
cs.AI
Internet memes are a pervasive form of multimodal online communication; however, such communication often involves users from diverse linguistic and cultural backgrounds. Therefore, adapting memes across cultures and languages is a central challenge for enabling mutual understanding in online communication. Unlike ordinary translation or standalone text rewriting, cross-cultural meme transcreation must jointly preserve communicative intent,...
-
19
LAAF: A Layered Accountability Architecture Framework for LLM Applications
Prachi Chaturvedi, Shahnawaz Ahmad, Ehsan Nowroozi, Muhammad Waqas, George Loukas, Alireza Jolfaei, Lucas Cordeiro,...
cs.AI · cs.CR
Large Language Models (LLMs) operate in hospitals, courtrooms, banks, and public service desks, where fluent, confident outputs are treated as authoritative even when ungrounded or incorrect. When such an output contributes to harm, who is answerable, and through what mechanisms can responsibility be traced, explained, and acted upon? Following PRISMA guidance, five databases were searched from January 2022 to March 2026 against four review...
-
20
pro-team at LLMs4OL 2026 Tasks Flagship and Reuse: Retrieval-Augmented Generation and Vocabulary-Constrained Filtering for Ontology Learning
Shivam Mishra, Dhannu Ram Meena, Muneendra Ojha, Krishna Pratap Singh, Kuldeep Singh
cs.AI
Ontology learning from text remains challenging despite significant progress in Large Language Models (LLMs), which can hallucinate domain terms, produce inconsistent formats, and favor hierarchical over associative relations. In the LLMs4OL 2026 Challenge, we address both the End-to-End Flagship Task (Task A) and Ontology Extension Reuse Task (Task B) using an offline retrieval-augmented few-shot prompting pipeline. Our system employs...
-
21
A Contract-Centered Architecture for Scalable and Manageable Agentic Runtimes
Yaxiao Liu, Pengbo Liu, Yiwen Liu, Yihua Guan, Zhenghe Hou, Jiaxing Song
cs.AI · cs.MA · cs.SE
Enterprise AI deployment is a coordination problem across business units, application and AI teams, testing, platform engineering, infrastructure, security, operations, and data governance. Use-case benchmarks show whether one agent completes one task, but not how changing capabilities, models, runtime mechanisms, capacity, and enterprise data should be owned, changed, admitted, or evidenced together. We present four responsibility objects as...
-
22
Omni-Interactive Universal Embedder
Wei-Yao Wang, Kazuya Tateishi, Shuyang Cui, Christian Simon, Takashi Shibuya, Shusuke Takahashi, Yuki Mitsufuji
cs.AI · cs.CV
Multimodal representation learning has been shifting from traditional two-tower architectures to large language model (LLM)-based embedders due to their strong instruction-following capabilities. Despite this progress, existing approaches primarily focus on language and image modalities, which also remain the dominant modalities for user-conditioned interactions in current embedders. In this paper, we propose the first Omni-Interactive...
-
23
A Multi-Modal AI Framework for Real-Time Queue Prediction, Management and Optimisation in Intelligent Border Control Systems
Varvara Mama, Eleni Veroni, Nikolaos Kapsalis, Christos D. Nikolopoulos, Anargyros T. Baklezos
cs.AI
In the present work an efficient border control management procedure is proposed. Compared to operational queue management systems, whose operations are based on mostly static data, the proposed work takes into account dynamic traffic conditions, thus enabling optimal performance, even in cases of uncertainty. To this end, we are proposing a multi-modal Artificial Intelligence (AI) framework, tailored to th needs of border control systems,...
-
24
ASIL: Replacing Screenshot-and-Click with Structured State and Semantic Actions
Rui Xie, Lu Chen
cs.AI
Powerful code agents can execute scripts, call tools, and manage files, yet many important applications remain accessible primarily through graphical user interfaces. We argue that screenshot-and-click is an inefficient interface for software-operating agents: screenshots are state-incomplete, and GUI actions are brittle, semantically weak, and poorly matched to long-horizon planning. We introduce ASIL (Agent-Software Interaction Layer), an...
-
25
DSA: Evidence-Aware LLM-Agent Orchestration for Multi-Market Stock Research
Linsen Zhu, Yi Shi
cs.AI · cs.MA
Large language models can summarize financial information, but an operational stock-research system must first assemble heterogeneous evidence, expose unavailable data and model capabilities, and control how generated opinions affect a final report. We present DSA, an evidence-aware orchestration framework for multi-market stock research with large language model (LLM) agents. DSA organizes the workflow into evidence acquisition, structured...
-
26
GraphMemix: Query-Aware Evidence Forests for Long-Term Multimodal Agent Memory
Geng Li, Yuhao Wang, Dong Li, Jianye Hao, Yuxin Peng
cs.AI
Organizing long-term memory for multimodal agents remains challenging because existing methods either suffer from expensive question-agnostic offline summaries or naive embedding similarity matching that introduces incomplete and redundant context. To address these issues, we propose GraphMemix, a combinatorial-optimization graph memory framework that models memory organization as query-aware evidence-forest construction. Specifically, our...
-
27
From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities
Jiayi Kuang, Yinghui Li, Yunze Song, Keyu Chen, Zhifeng Shen, Yangning Li, Yidong Wang, Di Yin, Ruizhi Qiao, Xing...
cs.AI · cs.CL
Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to integrating agentic intelligence. However, most existing math benchmarks evaluate only final answers. This outcome-oriented evaluation provides limited diagnostic value for identifying process-level failures or rigorous logic, failing to guide the transformation of LLMs into robust agents. To bridge this gap, we present a process-level benchmark...
-
28
A Table Is Worth 64 Tokens: Pixel-level Compression for Multi-Table Document Question Answering
Iñigo Alonso, Mirella Lapata
cs.AI
Answering questions over real-world documents requires processing long inputs that interleave text with tables. Optical context compression, which represents context as images, promises to reduce token cost, but its effect on table understanding remains unclear. We study pixel-level table compression for question answering over documents with multiple tables, evaluating five VLMs across two benchmarks and five visual-token budgets....
-
29
Counterfactual Bias Testing for Application Tracking System
Sai Yashwant, Shruti Bansal, Anurag Dubey, Samaroha Chatterjee, Satyam Kumar, Shreyash Gupta, Gantala Thulsiram
cs.AI
Automated candidate-job matching systems are increasingly classified as high-risk AI under emerging regulation, yet auditing them for demographic bias is expensive: classical correspondence-audit studies require hand-crafted resumes and manual submission, which does not scale to fast pipeline retraining cycles. This paper presents a general, reusable methodology that (1) uses task-specialized LLM agents to synthesize identity-neutral base...
-
30
AI agents in Algorithmic Electricity Markets: On the Emergence of Tacit Collusion
Jakub Seredyński, Georgios Tsaousoglou
cs.AI · cs.GT · cs.MA · eess.SY
As electricity market participants increasingly adopt learning-based agents for their bidding strategies, electricity markets are becoming algorithmic. Evidence from algorithmic markets in other domains shows that tacit collusion can arise purely through independent learning. Moreover, electricity markets are typically oligopolistic and feature repeated interaction among a small number of participants, making them structurally susceptible to...
-
31
Learning-Augmented Online Allocation under Unreliable Advice: Robustness, Exposure Fairness, and Distribution Shift
Fredy Pokou
cs.AI
Learning-augmented algorithms improve online decisions using predictions, but unreliable advice may harm efficiency and fairness. We study an online allocation problem with finite candidate sets, irreversible decisions, and exposure constraints. We propose a robust and fair rule combining advice with a conservative fallback and fairness correction. Under bounded-error assumptions, we prove consistency and robustness with loss proportional to...
-
32
Evaluating human and LLM screening workflows in a conceptually complex scoping review: Recall--workload trade-offs and run-to-run consistency
Nikol Figalová, Lynn Huestegge, Anne Böckler-Raettig
cs.AI · cs.HC · cs.SE
Background. Large language models (LLMs) are increasingly used for screening in evidence synthesis, where false negatives can remove relevant studies before full-text assessment. We compared human and LLM title-and-abstract screening workflows in a preregistered study embedded in a conceptually complex scoping review. Methods. After a conservative title-only screen, 1,131 records were screened by one review lead, four trained assistants...
-
33
C-Unseen: Weak Signal Detection in Dynamic Temporal Knowledge Graphs via LLM Reasoning
Yassir Lairgi, Ludovic Moncla, Khalid Benabdeslem, Rémy Cazabet, Pierre Cléau
cs.AI · cs.CL · cs.SI
Weak signals are early, low-visibility indicators that precede significant changes before those changes become established. Existing detection methods, based on keyword frequency, topic modeling, or untyped graph topology, fail to capture the semantic and relational structure through which such signals manifest. In this paper, we propose C-Unseen, a self-interpretable framework for weak signal detection in Dynamic Temporal Knowledge Graphs...
-
34
BekchiAI: Measuring, Observing, and Controlling LLM Agents in One Click
Mesut Toruk
cs.AI
Large language model agents reason, call tools, and act autonomously over many steps, but their agentic skills-correctly sequencing tools, planning under dependencies, judging untrusted inputs, and grounding generated arguments-are hard to measure with accuracy-only leaderboards. We present BekchiAI, which addresses both sides: a benchmark for measuring agentic skill and a platform for observing and controlling live agents. The...
-
35
LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems
Jiaqi Xu, Yiran Qiao, Jing Chen, Qiwei Zhong, Xiang Ao, Xueqi Cheng
cs.AI · cs.CY · cs.MA
User behavior simulation with large language models~(LLMs) is increasingly used to support multi-agent ecosystem simulation. Existing simulators typically rely on static user profiles inferred from historical observations, which become inadequate in socially intensive environments such as live streaming where interaction dynamics continuously reshape user behavior. We propose \textbf{LiveSim}, an LLM-based framework for live-stream ecosystem...
-
36
SymbolLKG: Towards Verifiable Logical Reasoning via Logical Knowledge Graph and Symbolic Solvers
Haizhao Fan, Yuchi Xiong, Jize Wang, Xinping Guan, Xinyi Le
cs.AI · cs.CL
Large Language Models (LLMs) have demonstrated remarkable proficiency in natural language understanding, yet they struggle with strict multi-step reasoning, frequently suffering from hallucinations and inconsistency. Existing solutions like Chain-of-Thought (CoT) lack rigorous verification mechanisms, while standard Retrieval-Augmented Generation (RAG) often misses the complex, structural dependencies inherent in logical tasks. To bridge this...
-
37
Decoupling Planning and Control for Instructable Agents
Zineng Tang, Kelsey R. Allen, Sjoerd van Steenkiste, Ishita Dasgupta, Alane Suhr
cs.AI · cs.CL · cs.MA · cs.RO
Recent work shows that pre-trained, instruction-tuned vision-language models (VLMs) perform well at mapping from instructions and observations to high-level plans, but struggle to realize such plans as reliable low-latency action sequences in unfamiliar environments. At the same time, world-model controllers excel at fast observation-to-action control, but lack open-ended task guidance. In this work, we combine these strengths into a single...
-
38
AI Control Scientist: LLM-driven Agentic System for Automated Control Design
Haiteng Wang, Weihao Li, Jing Zhang, Lei Ren
cs.AI
Control system design is critical for modern industry, such as chemical process temperature regulation and aero-engine control. However,traditional control design workflows rely heavily on expert knowledge and extensive manual parameter tuning, resulting in limited efficiency and scalability. To this end, this paper proposes AI Control Scientist (AICS), the first large language model (LLM)-driven agent capable of automatically generating...
-
39
Categorizer Automata for Discounted-Sum Payoffs
Nathalie Bertrand, Pranav Ghorpade, Senthil Rajasekaran, Sasha Rubin, Moshe Vardi
cs.AI · cs.FL
Categorizing continuous data into discrete bins is a fundamental operation in artificial intelligence. We introduce the categorizer automaton, a deterministic automaton that reads an infinite sequence of rewards and identifies which of finitely many bins contains its discounted sum. Categorizer automata generalize comparator automata, the special case of two bins, which have already proven useful in quantitative synthesis. Our main technical...
-
40
DEEPCHART: How Far are LLMs from Faithful Data-Science Chart Generation?
Jiahui tang, Kuicai Dong, Dexun Li, Hongchao Gu, Haocheng Yu, Wei Han, Chen Zhang, Yong Liu, Hao Wang, Enhong Chen
cs.AI
Faithful chart generation in real-world data-science workflows requires grounding visualizations in scattered evidence, computing chart-ready quantities, and rendering them accurately. Modern LLMs can produce visually plausible, instruction-compliant charts, yet data-level hallucinations remain difficult to detect in long, noisy, and multimodal contexts. To measure this gap, we introduce DEEPCHART, an expert-annotated benchmark of 1,482...
-
41
Discovering Relationships in Data Lakes Using Large Language Models: An Industrial Case
Ahlame Diouan, Eric Ferey, Sabine Loudcher, Jérôme Darmont
cs.AI
Data lakes rely on metadata to remain usable, yet this meta data is often limited or weakly informative for column relationship discovery, especially in ERP-derived datasets with coded or abbreviated schema labels. We propose ColRel, a two-stage method that builds column embeddings from metadata and data available at ingestion time. In difficult cases, such as coded schemata, business dictionaries help better interpret column names and...
-
42
AgentFold: Closed-Loop Agentic Search for Protein Folding Model Design
Mingquan Liu, Jiangyu Chen, Hanqun Cao, Xujun Zhang, Pengsen Ma, Xiangru Tang, Shuting Jin, Zhuo Yang, Tianfan Fu,...
cs.AI
Scientific LLM agents have shown promise in literature reasoning, tool use, and experiment planning, but it remains unclear whether they can autonomously improve large, tightly coupled scientific machine-learning systems through executable code changes and computationally expensive validation. We study this question in protein folding, where progress requires coordinated architectural modifications, multi-objective evaluation, and...
-
43
Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget Seeds
Waqas Khan, Tabinda Sarwar, Jingyue Cong, Xun Yi, Estrid He
cs.AI
Enterprises fine-tune language models on proprietary data that may later require removal due to privacy, contractual, or compliance obligations. Selective unlearning removes requested knowledge while preserving model utility, offering a practical alternative to full retraining, but existing methods treat the explicitly identified forget examples as the complete deletion scope. This is insufficient when target knowledge remains recoverable...
-
44
Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training
Tingyun Li, Wenfeng Feng, Weiqing Li, Abudukelimu Wuerkaixi, Guohua Liu, Yuewei Zhang
cs.AI
Large language models offer broad capabilities, but adapting them to evolving domains, tools, and requirements often entails repeated post-training. Autonomous systems automate parts of this process by proposing updates, training candidates, and using evaluation feedback to select subsequent proposals. As evidence accumulates, a central problem emerges: which past update evidence remains actionable after subsequent training has changed the...
-
45
Style as a Confound: False Positives in AI Detection of Non-Native Academic Writing
Hyeonchu Park, Gahye Jeong, Bugeun Kim
cs.AI
AI text detectors are increasingly employed in academic settings, but it remains unclear whether their outputs reflect AI authorship itself or broader linguistic features associated with polished academic English. Previous studies have reported high false-positive rates (FPRs) for non-native English writing, but population-level comparisons confound authorship with differences in topic, domain, and writing style. Professional editing provides...
-
46
Accelerating Scientific Research with Gemini in the Real-World
Samuel Schmidgall, Xiaokai Zhu, Marian Shaw, Lin Yang, Valentin Liévin, Jingyun Yang, Yuchen Zhuang, Tim Strother,...
cs.AI
We present an extension and comprehensive real-world validation of Co-Scientist, a Gemini-based multi-agent system designed to accelerate end-to-end scientific research across hypothesis generation, experimentation, and manuscript generation. Moving beyond in silico hypothesis generation, this specialized configuration transitions Co-Scientist into an execution-grounded research partner advancing closed-loop scientific workflows across...
-
47
Five Primitives for Governing Autonomous AI Agents at Runtime
Jiten Oswal, John Cadeddu
cs.AI · cs.CR · cs.SE
Enterprise deployments of autonomous AI agents inherit a control model built for human users and long-lived services, and the fit fails in three specific ways: agent principals are ephemeral, appearing and vanishing faster than provisioning; their actions are selected by a model rather than programmed, so the set of things they may attempt is not known in advance; and the population is discovered rather than provisioned, because anyone who...
-
48
Relational Over-Regularization: Graph-Based AI-Generated Text Detection via Sentence Transition Deviation
Hyeonchu Park, Bugeun Kim
cs.AI
Detecting AI-generated text (AIGT) remains challenging because existing approaches rely on token-level statistical signals or independent stylometric features, causing them to overfit to specific generators and fail under distribution shift. We identify a structural signal at the sentence-pair level: LLMs produce inter-sentence transition variance that deviates from human writing through inflated variance driven by recurring similarity bursts...
-
49
SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregation
Li Mingqian
cs.AI · cs.LG · cs.MA
Cooperative multi-agent reinforcement learning (MARL) faces significant challenges in maintaining robust coordination under noisy observations. Although observation disturbances are often introduced independently across agents, their downstream effects on cooperative decision-making can become structured through underlying cooperation structures. We characterize this phenomenon as structured noise effects, where noise-induced decision effects...
-
50
AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-Calling
Abhigya Verma, Amit Kumar Saha, Seganrasan Subramanian, Sai Harshitha Aluru
cs.AI
LLM judges are widely used to evaluate agentic tool-calling systems, yet their reliability on structured, dependency-driven workflows remains largely unexamined. We present AgentJudgeBench, the first benchmark to systematically study LLM-as-a-judge reliability for agentic tool-calling over workflow DAGs, as distinct from the broader LLM-as-a-judge task of open-ended text or preference evaluation. The benchmark comprises 3,808 instances...
-
51
DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows
Zechun Niu, Yukun Zhao, Jiaxin Zhang, Xu Shen, Jinhua Si, Han Tian, Can Xu, Yunfan Song, Jiaxin Mao, Yansong Gao,...
cs.AI · cs.CL
Autonomous agents are increasingly adopted to complete complex, multi-tool workflows in real-world settings. However, existing benchmarks typically separate tasks by application or capability and evaluate agents in environments that are cleaner and more stable than those encountered in practice. We introduce DuMateBench, a real-session benchmark reconstructed from anonymized and privacy-screened user sessions collected from a large-scale...
-
52
Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation
Kaichao Jiang, Changtao Miao, Baiqi Wu, Zhiyuan Lu, Kang Yang, Peiwei Zhao, Junchi Chen, Yunfeng Diao, He Liu, Qi...
cs.AI
Audio-video generation is rapidly moving from prompt-driven synthesis toward multimodal conditioning, where text, images, audio, and video can jointly shape the generated output. This shift changes the nature of safety evaluation: harmful intent may no longer reside in any single input, but instead emerge from how otherwise benign or weakly harmful conditions interact across modalities and time. Existing safety benchmarks, however, remain...
-
53
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents
Yang Xiao, Yusong Sun, Haoyi Wu, Wenyang Hui, Wen Da, Zhaokai Luo, Mu Chuan, Yao Hu, Wenjie Li, Chengyue Jiang
cs.AI
Long-horizon agent runs generate experience that can improve both the current run and future work. Most self-improvement methods process this experience only after execution ends, so they cannot redirect the active run or immediately apply and validate lessons learned from it. We argue that self-improvement should instead be live, using emerging experience both to redirect the active run and to update the persistent harness. Existing agent...
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.