AI agents

Tool use, function calling, orchestration and the protocols that let models act rather than only answer.

7,971 stories · RSS feed

arXiv AI

Jul 14

AutoVSR: Automatic Visual-to-Symbolic Reasoning for Symbolic Expression Generation from Circuit Schematic

arXiv:2607. 11338v1 Announce Type: new Abstract: Symbolic expressions can effectively characterize and predict circuit behavior, but deriving them directly from circuit schematics is challenging.

By Zhe Xiao, Longfei Li, Xu He, Haoying Wu, Zixing Zhang, Mingyu Liu

llms agents multimodal benchmarks

arXiv AI

Jul 14

LLM-Driven Collaborative Model for Untangling Commits via Explicit and Implicit Dependency Reasoning

arXiv:2507. 16395v3 Announce Type: replace Abstract: Atomic commits, which address a single development concern, are a best practice in software development.

By Bo Hou, Xin Tan, Kai Zheng, Fang Liu, Yinghao Zhu, Li Zhang

llms agents

arXiv Machine Learning

Jul 14

EvoClawBench: Can Agents Learn Reusable Skills from Their Own Runs?

arXiv:2607. 09711v1 Announce Type: new Abstract: Existing agent benchmarks primarily test task completion, tool use, or skill utility, but do not isolate whether a runtime can convert evidence from its own runs into reusable skills that improve fresh executions after authoring overhead.

By Zhiyuan Peng, Xin Yin, Chenhao Ying, Zhe Cui, Zixiang Ding, Zhenhua Liu, Jiang Wu, Yuan Luo

llms agents nlp benchmarks

arXiv Machine Learning

Jul 14

Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directions

arXiv:2601. 15353v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has achieved remarkable success in real-world decision-making across diverse domains, including gaming, robotics, online advertising, public health, and natural language processing.

By Asim H. Gazi, Yongyi Guo, Daiqi Gao, Ziping Xu, Kelly W. Zhang, Susan A. Murphy

agents nlp reinforcement-learning robotics

arXiv Machine Learning

Jul 14

Paradoxes of Game Theoretic Equilibria and Price of Anarchy

arXiv:2607. 11752v1 Announce Type: cross Abstract: For decades, static solution concepts (Nash, Correlated, and Coarse Correlated Equilibria) and the Price of Anarchy (PoA) have formed the bedrock of algorithmic game theory, with no-regret learning proving fast convergence to such game-theoretic equilibria.

By Georgios Piliouras, Ian Gemp, Siqi Liu, Luke Marris

agents

arXiv AI

Jul 14

MAG: A Web-Agent Benchmark and Harness for Multimodal Action and Guide Generation

arXiv:2607. 10079v1 Announce Type: new Abstract: Digital Adoption Platforms (DAPs) are embedded overlays widely used on web systems to guide users through operations inside a page, helping them get started with unfamiliar interfaces quickly.

By Chengguang Gan, Hanjun Wei, Yunhao Liang, Zhixi Cai, Qinghao Zhang, Shiwen Ni

llms agents multimodal benchmarks

arXiv AI

Jul 14

Measuring AI Ability to Complete Long Software Tasks

arXiv:2503. 14499v4 Announce Type: replace Abstract: Despite rapid progress on AI benchmarks, the real-world meaning of benchmark performance remains unclear.

By Thomas Kwa, Ben West, Joel Becker, Amy Deng, Katharyn Garcia, Max Hasin, Sami Jawhar, Megan Kinniment, Nate Rush, Sydney Von Arx, Ryan Bloom, Thomas Broadley, Haoxing Du, Brian Goodrich, Nikola Jurkovic, Luke Harold Miles, Seraphina Nix, Tao Lin, Chris Painter, Neev Parikh, David Rein, Lucas Jun Koba Sato, Hjalmar Wijk, Daniel M. Ziegler, Elizabeth Barnes, Lawrence Chan

llms agents benchmarks

arXiv AI

Jul 14

Distributed Denial of Science: How Indirect Data Poisoning of AI Systems Can Industrialize Scientific Fraud

arXiv:2607. 10712v1 Announce Type: cross Abstract: Scientific fraud is the instrument of doubt that malicious entities can use to establish controversy in science.

By B\'alint Gyevn\'ar, Atoosa Kasirzadeh, Nihar B. Shah

llms agents safety

arXiv AI

Jul 14

Learning in Blocks: A Multi Agent Debate Assisted Personalized Adaptive Learning Framework for Language Learning

arXiv:2604. 22770v2 Announce Type: replace-cross Abstract: Most digital language learning curricula rely on discrete-item quizzes that test recall rather than applied conversational proficiency.

By Nicy Scaria, Silvester John Joseph Kennedy, Deepak Subramani

llms agents benchmarks

arXiv AI

Jul 14

MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents

arXiv:2607. 11818v1 Announce Type: cross Abstract: We introduce MM-ToolSandBox, a benchmark and evaluation framework for visually grounded tool-calling agents.

By Kaixin Ma, Di Feng, Alexander Metz, Jiarui Lu, Eshan Verma, Afshin Dehghan

agents benchmarks

arXiv AI

Jul 14

A Low-Latency Fraud Detection Layer for Detecting Adversarial Interaction Patterns in LLM-Powered Agents

arXiv:2605. 01143v2 Announce Type: replace Abstract: Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning.

By Sheldon Yu, Yingcheng Sun, Hanqing Guo, Qianqian Tong

llms agents benchmarks safety

arXiv Machine Learning

Jul 14

CTFusion: A CTF-based Benchmark for LLM Agent Evaluation

arXiv:2605. 11504v2 Announce Type: replace Abstract: Recent advances in Large Language Models (LLMs) have enabled agentic systems for complex, multi-step tasks; cybersecurity is emerging as a prominent application.

By Dongjun Lee, Ga-eun Bae, Insu Yun

llms agents benchmarks

arXiv AI

Jul 14

Cross-Layer Misalignment Detection in Agent Skills: A Progressive Loading-Aware Contrastive Learning Approach

arXiv:2607. 10534v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly extended through Agent Skills, reusable artifacts that package natural-language metadata, procedural instructions, and execution-time resources for runtime use.

By Chengjun Zhang, Yang Gao, Jianna Hur, Jingjing Zhang, Sagar Samtani

llms agents

arXiv AI

Jul 14

Can Agentic Trading Systems Pay for Their Own Intelligence?

arXiv:2607. 10286v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used in trading systems, where model reasoning, tool use, and continual decisions incur costs that are expected to produce trading value.

By Qiqi Duan, Changlun Li, Chen Wang, Fan Zhang, Mengxiang Wang, Dayi Miao, Peixian Ma, Jiangpeng Yan, Liyuan Chen, Shuoling Liu, Preslav Nakov, Yuyu Luo, Nan Tang

llms agents

arXiv AI

Jul 14

Mini Amusement Parks (MAPs): A Testbed for Modelling Business Decisions

arXiv:2511. 15830v2 Announce Type: replace Abstract: Despite rapid progress in artificial intelligence, current systems struggle with the interconnected challenges that define real-world decision making.

By St\'ephane Aroca-Ouellette, Ian Berlot-Attwell, Panagiotis Lymperopoulos, Abhiramon Rajasekharan, Tongqi Zhu, Herin Kang, Kaheer Suleman, Sam Pasupalak

llms agents benchmarks

arXiv AI

Jul 14

A Glimpse into Long-term Physical Coexistence with Intelligent Robots

arXiv:2607. 11377v1 Announce Type: cross Abstract: Long-term physical coexistence with intelligent robots requires more than capable robot policies.

By Weiqi Jin, Peijun Tang, Kuncheng Luo, Baifu Huang, Binyan Sun, Haotian Yang, Shangjin Xie, Jianan Wang

agents robotics

arXiv AI

Jul 14

The Hidden Footprint: Making Storage a First-Class Metric for LLM Agent Evaluation

arXiv:2607. 11149v1 Announce Type: new Abstract: LLM agent benchmarks measure task completion, reliability, and inference cost, but not the persistent data an agent run leaves on disk, including logs, context snapshots, checkpoints, and debug traces.

By Chenglin Yu, Hongquan Gui, Ying Yu, Hongxia Yang, Ming Li

llms agents benchmarks

arXiv AI

Jul 14

GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning

arXiv:2604. 02721v2 Announce Type: replace Abstract: Competitive programming remains one of the last few human strongholds in coding against AI.

By DeepReinforce Team, Xiaoya Li, Guoyin Wang, Songqiao Su, Chris Shum, Jiwei Li

llms agents nlp reinforcement-learning

arXiv AI

Jul 14

ActiveFly-Bench: Aligning Embodied Question Answering with Vision-Language-Action for Aerial Embodied Perception

arXiv:2607. 10180v1 Announce Type: cross Abstract: We introduce ActiveFly-Bench, the first benchmark to bridge cyberspace reasoning and physical-world interaction for UAV embodied perception.

By Weichen Zhang, Shiquan Yu, Yinan Zhu, Peizhi Tang, Shilong Ji, Zhiyuan Deng, Tianyi Lyu, Haoyang Wang, Xin Zeng, Chen Gao, Yong Li, Xinlei Chen

agents nlp robotics multimodal benchmarks

arXiv AI

Jul 14

Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos

arXiv:2607. 11523v1 Announce Type: cross Abstract: When should an intelligent assistant speak up without being asked?

By Gong Sitong, Tianyu Yan, Caixin Kang, Bo Zheng, Xiang Ruan, Huchuan Lu, Kaipeng Zhang, Yoichi Sato, Yifei Huang

rag agents benchmarks safety

Get the daily briefing