LLM Agents

LLM: Large Language Model

LLM agents combine language models with tools, memory, and execution environments to pursue goals through sequences of decisions rather than producing a single response. Common approaches include ReAct-style planning and tool use, retrieval and reusable skill libraries, reflection and verification, multi-agent coordination, and training with supervised trajectories or reinforcement learning; runtime harnesses also manage state, permissions, and model routing. They are tested on interactive web and coding tasks, tool-use and long-horizon benchmarks, domain workflows, and simulations of social or physical settings. A central challenge is making agents reliable and safe when tasks, instructions, and environments change while controlling cost and evaluating performance beyond narrow benchmark success.

Latest papers

711 papers129 papers in the last four weeks, up 59% on the four weeks before. 0.7% of all new papers.

CaveAgent: Transforming LLMs into Stateful Runtime Operators
Jan 4, 2026Maohao Ran, Zhenglin Wan, Cooper Lin +21LLM Agent Memory LLM Agents
HKUST · HKBU · NUS +8
Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation
Dec 18, 2025Yuxuan Qiao, Dongqin Liu, Hongchang Yang +2LLM Agent Security LLM Agents
Institute of Information Engineering, Chinese Academy of Sciences · School of Cyber Security, University of Chinese Academy of Sciences
Achieving Olympiad-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning
Dec 11, 2025Haiteng Zhao, Junhao Shen, Yiming Zhang +7LLM Agents Reinforcement Learning
1Shanghai AI Laboratory · 2Shanghai Jiao Tong University · 3Peking University +2
Rethinking Query Optimization for Multi-Agent Systems [Vision]
Dec 10, 2025Zoi Kaoudi, Ioana GiurgiuMulti-Agent System Optimization Multi-Agent Orchestration
IT University of Copenhagen · IBM Research Europe
Evolving Excellence: Automated Optimization of LLM-based Agents
Dec 9, 2025Paul Brookes, Vardan Voskanyan, Rafail Giavrimis +18Large Language Model-Guided Optimization LLM Agent Workflow Optimization
TurinTech AI, London, UK · University of Surrey, Guildford, United Kingdom · University of Leeds, Leeds, UK +4
REMSA: Foundation Model Selection for Remote Sensing via a Constraint-Aware Agent
Nov 21, 2025Binger Chen, Tacettin Emre Bök, Behnood Rasti +2Model Selection Geospatial Foundation Models
Humboldt-Universität zu Berlin, Berlin, Germany · 5U AI, Munich, Germany · Technische Universität Berlin & BIFOLD, Berlin, Germany
Domain-Specific Agents for Cherenkov Telescope Array Control Software and Gamma-Ray Data Analysis
Oct 1, 2025Dmitriy Kostunin, Elisa Jones, Vladimir Sotnikov +3High-Energy Physics LLM Agents
Deutsches Elektronen-Synchrotron DESY, 15738 Zeuthen, Germany · JetBrains Limited, 8046 Paphos, Cyprus · JetBrains GmbH, 80639 München, Germany +1
Reasoning or Rambling? Exploring the Effect of Thinking on Agent Persuasion
Sep 25, 2025Haodong Zhao, Jidong Li, Zhaomin Wu +4LLM Agents Persuasion in Language Models
School of Computer Science, Shanghai Jiao Tong University · 2National University of Singapore · 3Inner Mongolia Research Institute, Shanghai Jiao Tong University
Are LLM Agents Behaviorally Coherent? A Latent Profiling Approach for Social Simulation
Sep 3, 2025James Mooney, Josef Woldense, Zheng Robert Jia +4Behavioral Consistency of LLM Agents LLM Agent Evaluation
Department of Computer Science and Engineering, University of Minnesota · Department of African American & African Studies, University of Minnesota · Department of Sociology, University of Chicago +1
LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios
Aug 25, 2025Bingxi Zhao, Lin Geng Foo, Ping Hu +3Multi-Agent LLM Systems LLM Agents
LinkAnchor: An Autonomous LLM-Based Agent for Issue-to-Commit Link Recovery
Aug 17, 2025Arshia Akhavan, Alireza Hoseinpour, Abbas Heydarnoori +2Software Engineering LLM Agents
Bowling Green State University, Department of Computer Science, Bowling Green, USA · University of Nebraska-Lincoln, School of Computing, Lincoln, USA · University of Zurich, Department of Informatics, Zurich, Switzerland
InqEduAgent: Adaptive AI Learning Partners with Gaussian Process Augmentation
Aug 5, 2025Wen-Xi Yang, Tian-Fang Zhao, Guan LiuAI in Education Generative AI in Education
Guangdong Institute of Smart Education, Jinan University, Guangzhou, China · School of Journalism and Communication, Jinan University, Guangzhou, China
Towards Mitigation of Hallucination for LLM-empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitor
Jul 21, 2025Siyuan Liu, Wenjing Liu, Zhiwei Xu +3LLM Hallucination Mitigation Hallucination in Language Models
College of Computer Science, Nankai University · College of intelligent Science and Technology, Inner Mongolia University of Technology · Institute of Computing Technology, Chinese Academy of Sciences +3
AutoMind: Adaptive Knowledgeable Agent for Automated Data Science
Jun 12, 2025Yujie Luo, Yixin Ou, Jingsheng Zheng +9Data Analysis Agents LLM Agents
Zhejiang University · Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph · Ant Group
Small Language Models are the Future of Agentic AI
Jun 2, 2025Peter Belcak, Greg Heinrich, Shizhe Diao +5Small Language Models LLM Agents
NVIDIA Research · Georgia Institute of Technology
Agent-Environment Alignment via Automated Interface Generation
May 27, 2025Kaiming Liu, Xuanyu Lei, Ziyue Wang +2LLM Agents AI Alignment
College of AI, Tsinghua University, Beijing, China · Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China · Dept. of Comp. Sci. & Tech., Institute for AI, Tsinghua University, Beijing, China
Towards LLM Agents for Earth Observation
Apr 16, 2025Chia Hsiang Kao, Wenting Zhao, Cheryl Lam +10Code Generation LLM Agent Evaluation
Cornell University · Columbia University
AgentRM: Enhancing Agent Generalization with Reward Modeling
Feb 25, 2025Yu Xia, Jingru Fan, Weize Chen +7Reward Modeling LLM Agents
Department of Computer Science and Technology, Tsinghua University · Gaoling School of Artificial Intelligence, Renmin University of China
How Well Can Modern LLMs Act as Agent Cores in Radiology Environments?
Dec 12, 2024Qiaoyu Zheng, Chaoyi Wu, Weike Zhao +5Healthcare LLM Agent Evaluation
Shanghai Jiao Tong University, Shanghai, China · Department of Radiology, Renmin Hospital of Wuhan University, Wuhan, China
LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals
Nov 15, 2024Joon Sung Park, Carolyn Q. Zou, Jonne Kamphorst +8Personality Modeling in Language Models Human Behavior Simulation
1Computer Science Department, Stanford University; Stanford, CA, 94305, USA. · Department of Communication Studies, Northwestern University; Evanston, IL 60208, USA. · 7CDSP and CEE, Sciences Po; Paris, 75007, France. +4
A Taxonomy of Architecture Options for Foundation Model-based Agents: Analysis and Decision Model
Aug 6, 2024Jingwen Zhou, Qinghua Lu, Jieshan Chen +4LLM Agents Agentic AI
School of Computer, Data and Mathematical Sciences, Western Sydney University, Sydney, Australia · CSIRO’s Data61, Australia · University of New South Wales, Sydney, New South Wales, Australia +1

Jan 4, 2026J/K move · Enter open · S save

CaveAgent: Transforming LLMs into Stateful Runtime Operators

Maohao Ran, Zhenglin Wan, Cooper Lin, Yanting Zhang+20

HKUST · HKBU · NUS+8

LLM Agent Memory LLM Agents Long-Horizon LLM Agents LLM Context Management

Open paper AskPDF arXiv

LLM-based agents are increasingly capable of complex task execution, yet current agentic systems remain constrained by text-centric paradigms that struggle with long-horizon tasks due to fragile multi-turn dependencies and context drift. We present CaveAgent, a framework that shifts tool use from LLM-as-Text-Generator'' to LLM-as-Runtime-Operator.'' CaveAgent introduces a dual-stream architecture that inverts the conventional paradigm: rather than treating the LLM's text context as the primary workspace with tools as auxiliary, CaveAgent elevates the persistent Python runtime as the central locus of state, with a lightweight semantic stream serving as its orchestrator. Beyond leveraging code generation to resolve interdependent sub-tasks (e.g., loops, conditionals) in a single step, CaveAgent introduces Stateful Runtime Management: it injects, manipulates, and retrieves complex Python objects (e.g., DataFrames, database connections) that persist across turns, unlike existing code-based approaches that remain text-bound. CaveAgent further provides a runtime-integrated skill management system that extends the Agent Skills open standard, enabling ecosystem interoperability through executable skill injections. This persistence mechanism serves as a high-fidelity external memory that reduces context drift in multi-turn interactions and preserves processed data for downstream applications without information loss. Evaluations show consistent improvement across challenging benchmarks, enabling CaveAgent to handle data scales that cause context overflow in both JSON-based and code-based agents. The accessible runtime state further provides programmatically verifiable feedback, enabling automated evaluation and reward signal generation without human annotation and establishing a structural foundation for future research in Reinforcement Learning with Verifiable Rewards (RLVR).