LLM Agent Training

LLM: Large Language Model

LLM agent training studies how to make language models act reliably over multiple steps, using tools, software, websites, or simulated worlds to complete tasks. Common approaches combine supervised fine-tuning on interaction traces with reinforcement learning from execution-verified outcomes, alongside distillation, preference learning, and feedback on individual steps. Researchers build executable environments and benchmarks such as SWE-bench, WebArena, Terminal-Bench, and τ²-Bench to provide repeatable practice and test tool use, coding, search, and long-horizon workflows. A central challenge is transferring gains beyond training environments while balancing task success with efficiency, safety, and robustness to changing tools and users.

Latest papers

590 papers130 papers in the last four weeks, up 132% on the four weeks before. 0.8% of all new papers.

Asymmetric Actor-Critic for Multi-turn LLM Agents
Mar 31, 2026Shuli Jiang, Zhaoyang Zhang, Yi Zhang +3Asynchronous Advantage Actor-Critic LLM Agent Reliability
AWS Agentic AI
MemFactory: Unified Inference & Training Framework for Agent Memory
Mar 31, 2026Ziliang Guo, Ziheng Li, Bo Tang +2LLM Agent Memory Agent Memory Management
MemTensor
GraphWalker: Agentic Knowledge Graph Question Answering via Synthetic Trajectory Curriculum
Mar 30, 2026Shuwen Xu, Yao Xu, Jiaxiang Liu +4Knowledge Graph Question Answering LLM Agent Training
School of Artificial Intelligence, University of Chinese Academy of Sciences · The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences · Department of Electronic Engineering, Tsinghua University
Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design
Mar 30, 2026Bin Zhu, Qianghuai Jia, Tian Lan +6Deep Research Agents LLM Agent Training
Alibaba International Digital Commerce
KAT-Coder-V2 Technical Report
Mar 29, 2026Fengxiang Li, Han Zhang, Haoyang Huang +43AI Coding Agents Agentic Code Generation
Can AI Models Direct Each Other? Organizational Structure as a Probe into Training Limitations
Mar 27, 2026Rui LiuMulti-Agent Coding LLM Agent Orchestration
Independent Researcher
UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience
Mar 25, 2026Zichuan Lin, Feiyu Liu, Yijun Yang +9Mobile GUI Agents LLM Agent Training
Tencent Hunyuan
Experiential Reflective Learning for Self-Improving LLM Agents
Mar 25, 2026Marc-Antoine Allard, Arnaud Teinturier, Victor Xing +1Self-Improving Agents LLM Agent Training
Illuin Technology
A Context Engineering Framework for Improving Enterprise AI Agents based on Digital-Twin MDP
Mar 23, 2026Xi Yang, Aurelie Lozano, Naoki Abe +6LLM Agents LLM Agent Training
IBM Software Innovation Lab, Yorktown Heights, New York, USA
EnterpriseLab: A Full-Stack Platform for developing and deploying agents in Enterprises
Mar 23, 2026Ankush Agarwal, Harsh Vishwakarma, Suraj Nagaje +1Enterprise AI Agents Synthetic Data Generation for LLM Agents
Fujitsu Research India.
AgenticRec: A Recommendation-Oriented Agentic Framework with Progressive Tool-Integrated Reasoning Optimization
Mar 23, 2026Tianyi Li, Zixuan Wang, Guidong Lei +2Recommender Systems Large Language Model-Based Recommendation
Xiamen University, Xiamen, China
AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling
Mar 22, 2026Liang DingHindsight Experience Replay LLM Agent Training
The University of Sydney
Teaching an Agent to Sketch One Part at a Time
Mar 19, 2026Xiaodan Du, Ruize Xu, David Yunis +2Generative Modeling LLM Agent Training
TTI-Chicago · University of Chicago · MIT CSAIL
ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents
Mar 19, 2026Hao Zhang, Mingjie Liu, Shaokun Zhang +10LLM Agent Training LLM Agent Harnesses
Retrieval-Augmented LLM Agents: Learning to Learn from Experience
Mar 18, 2026Thomas Palmeira Ferraz, Romain Deffayet, Vassilina Nikoulina +2Fine-Tuning LLM Agent Training
NAVER LABS Europe, Meylan, France
Adapting Technical-Service LLM Agents with Latent Logic Augmentation, Robust Noise Reduction, and Hybrid Reward Modeling
Mar 18, 2026Junzhuo Ma, Chenghuang Shen, Yi Yu +15LLM Agent Training LLM Post-Training
School of Mathematical Sciences, Fudan University, Shanghai, China · Alibaba Group, Hangzhou, China · Shanghai Center for Mathematical Sciences, Fudan University, Shanghai, China +3
ML-AutoResearch: Training Machine Learning Research Agents with Automatically Generated Environments
Mar 17, 2026Ziyang Cai, Amir Saeidi, Harkirat BehlAutonomous Research Agents LLM Agent Training
Arizona State University · Microsoft Research
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Mar 17, 2026Zhuofeng Li, Dongfu Jiang, Xueguang Ma +7Deep Research Agents LLM Agent Trajectory Synthesis
Texas A&M University · University of Waterloo · UC San Diego +3
Internalizing Agency from Reflective Experience
Mar 17, 2026Rui Ge, Yichao Fu, Yuyang Qian +4LLM Agent Training Self-Improving Agents
University of California San Diego · Shanghai Jiao Tong Univsersity · Nanjing University
Learning to Present: Inverse Specification Rewards for Agentic Slide Generation
Mar 17, 2026Karthik Ragunath Ananda Kumar, Subrahmanyam ArunachalamLLM Agent Training Tool-Augmented Language Model Agents
Tavus Inc. · University of Texas at Dallas · Texas A&M University
SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding
Mar 17, 2026Songcheng Cai, Zhiheng Lyu, Yuansheng Ni +13AI Agent Benchmarks Software Engineering Benchmarks
University of Waterloo · University of Toronto · The Hong Kong University of Science and Technology +2
MAC: Multi-Agent Constitution Learning
Mar 16, 2026Rushil Thareja, Gautam Gupta, Francesco Pinto +1Prompt Optimization LLM Agent Training
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · Indraprastha Institute of Information Technology Delhi (IIIT Delhi) · Google DeepMind
OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
Mar 16, 2026Yuwen Du, Rui Ye, Shuo Tang +4Deep Research Agents Web Search Agents
Shanghai Jiao Tong University
Shopping Companion: Benchmarking and Training LLM Agents for Long-Horizon Preference-Grounded E-Commerce Tasks
Mar 16, 2026Zijian Yu, Kejun Xiao, Huaipeng Zhao +2LLM Agent Training AI Agent Benchmarks
Alibaba International Digital Commercial Group
OpenHospital: A Thing-in-itself Arena for Evolving and Benchmarking LLM-based Collective Intelligence
Mar 16, 2026Peigen Liu, Rui Ding, Yuren Mao +7LLM Agents AI Agent Benchmarks
School of Software Technology, Zhejiang University · Laboratory for Statistical Monitoring and Intelligent Governance of Common Prosperity, Zhejiang Gongshang University · Tongyi Lab, Alibaba Group +1
daVinci-Env: Open SWE Environment Synthesis at Scale
Mar 13, 2026Dayuan Fu, Shenyu Wu, Yunze Wu +11Software Engineering LLM Agent Training
SII · GAIR · SJTU
Safe and Scalable Web Agent Learning via Recreated Websites
Mar 11, 2026Hyungjoo Chae, Jungsoo Park, Alan RitterWeb Agents LLM Agent Training
School of Interactive Computing, Georgia Institute of Technology
DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use
Mar 10, 2026Aili Chen, Chi Zhang, Junteng Liu +11Tool-Augmented Language Model Agents LLM Tool Use
Fudan University · MiniMax · Independent
Meissa: Multi-modal Medical Agentic Intelligence
Mar 9, 2026Yixiong Chen, Xinyi Bai, Yue Pan +2Medical AI Agents Medical LLMs
Johns Hopkins University, Baltimore, MD, USA · Cornell University, Ithaca, NY, USA
Agentic Critical Training
Mar 9, 2026Weize Liu, Minghui Liu, Sy-Tuyen Ho +5LLM Agent Training Imitation Learning
University of Maryland, College Park

Mar 31, 2026J/K move · Enter open · S save

Asymmetric Actor-Critic for Multi-turn LLM Agents

Shuli Jiang, Zhaoyang Zhang, Yi Zhang, Shuo Yang+2

AWS Agentic AI

Asynchronous Advantage Actor-Critic LLM Agent Reliability Actor-Critic Methods LLM Agent Training

Open paper AskPDF arXiv

Large language models (LLMs) exhibit strong reasoning and conversational abilities, but ensuring reliable behavior in multi-turn interactions remains challenging. In many real-world applications, agents must succeed in one-shot settings where retries are impossible. Existing approaches either rely on reflection or post-hoc evaluation, which require additional attempts, or assume fully trainable models that cannot leverage proprietary LLMs. We propose an asymmetric actor-critic framework for reliable conversational agents. A powerful proprietary LLM acts as the actor, while a smaller open-source critic provides runtime supervision, monitoring the actor's actions and intervening within the same interaction trajectory. Unlike training-based actor-critic methods, our framework supervises a fixed actor operating in open-ended conversational environments. The design leverages a generation-verification asymmetry: while high-quality generation requires large models, effective oversight can often be achieved by smaller ones. We further introduce a data generation pipeline that produces supervision signals for critic fine-tuning without modifying the actor. Experiments on

τ

-bench and UserBench show that our approach significantly improves reliability and task success over strong single-agent baselines. Moreover, lightweight open-source critics rival or surpass larger proprietary models in the critic role, and critic fine-tuning yields additional gains over several state-of-the-art methods.