Experience Learning for LLM Agents

LLM: Large Language Model

Latest papers

28 papers9 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents
Oct 25, 2026Haoyu Zhao, Sitian Tu, Yuxuan Huang +16Experience Learning for LLM Agents Continual Learning for LLM Agents
ReGE: Stronger Agents through Experience Synthesis
Oct 24, 2026Jiarong Liang, Yubo Wang, Zijie Liu +3Experience Learning for LLM Agents LLM Agent Self-Improvement
University of Waterloo · University of North Carolina at Chapel Hill · University of British Columbia
REM: What to Store, When to Recall, What to Forget in Experience Memory for Coding Agents
Oct 19, 2026Xinyi Lisa Chen, Pedro Herrero-Vidal, Xiaohan Chen +6Memory Management for LLM Agents Agent Memory
Yale University · Amazon
MetaExp: Learning to Self-Improve through Experience via Verifiable Cross-Task Environment Scaling
Oct 15, 2026Renhao Li, Xinjie Shen, Yang Su +4Experience Learning for LLM Agents LLM Agent Self-Improvement
University of Macau · Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences · Georgia Institute of Technology +1
XferAgent: Cross-Agent Experience Transfer for Self-Improving LLM Agents
Oct 14, 2026Weihao Li, Jun Bai, Shijie Chen +3LLM Agent Self-Improvement Experience Learning for LLM Agents
McCormick School of Engineering, Northwestern University · School of Computer Science, McGill University · Mila – Quebec AI Institute +1
Beyond Outcome Feedback: Trajectory-Quality-Guided Experience-based Learning
Oct 10, 2026Bingjie Zhang, Yibo Yang, Qiantong Liu +3Experience Learning for LLM Agents LLM Agent Training
School of Artificial Intelligence, Jilin University · School of Artificial Intelligence, Shanghai Jiao Tong University · King Abdullah University of Science and Technology
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
Oct 6, 2026Yibo Li, Jinhang Qiu, Zhi Zheng +4Experience Learning for LLM Agents LLM Agent Evaluation
National University of Singapore
ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience
Oct 4, 2026Haodong Lu, Dong GongContinual Learning for LLM Agents Test-Time Training
University of New South Wales (UNSW Sydney)
Learn Now, Use Next, Trust Later: Prequential Test-Time Learning for LLM Agents
Sep 28, 2026Tong Zhao, Reed Li, Yuyang Hu +5Continual Learning for LLM Agents Test-Time Training
Renmin University of China · Tencent
Learning to Coach for Experiential Learning
Sep 14, 2026Guanheng Chen, Tianzhu Ye, Li Dong +3RL for Language Models RL for Language Model Reasoning
Microsoft Research
Break It Down, Pass It On: Cross-Task Skill Transfer in LLM Agents
Aug 20, 2026Yiyang Feng, Biddut Sarker Bijoy, Niranjan Balasubramanian +1LLM Agent Skill Learning Experience Learning for LLM Agents
Computer Science Department, Stony Brook University, Stony Brook, USA
Towards Improving Sequential Decision-Making in LLM Agents via Experience Memory
Aug 4, 2026Jakub Rada, Viliam LisýGame-Playing Agents LLM Agents
AI Center, Department of Computer Science, Faculty of Electrical Engineering, Czech Technical University in Prague · AI Center, Department of Computer Science, FEE, Czech Technical University in Prague
Sample-Efficient Learning from Agent Experience
Jul 23, 2026Chenhui Gou, Haoqin Tu, Yunhao Fang +2In-Context RL Language Model Distillation
Monash University · ByteDance Seed
Hierarchical Experimentalist Agents
Jun 28, 2026Abhranil Chandra, Utsav Dhanuka, Varun Gandhi +2LLM Agent Skill Learning AI Agent Benchmarks
University of Massachusetts Amherst
Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning
Jun 23, 2026Shiding Zhu, Yudi Qi, Yajie Wang +6LLM Agents Experience Learning for LLM Agents
Zhejiang University · Shenzhen International Graduate School, Tsinghua University · Independent Researcher +3
LatentGym: A Testbed For Cross-Task Experiential Learning With Controllable Latent Structure
Jun 13, 2026Daksh Mittal, Tommaso Castellani, Thomson Yen +7Continual Learning for LLM Agents Lifelong Learning Agents
1Columbia University · 2Oumi
DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Trees
Jun 2, 2026Haoran Tan, Zeyu Zhang, Zhicheng Cao +2Continual Learning for LLM Agents LLM Agent Memory
Gaoling School of Artificial, Renmin University of China, Beijing, China · Beijing Key Laboratory of Research on Large Models and Intelligent Governance · Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE +1
ExpWeaver: LLM Agents Learn from Experience via Latent RAG
May 31, 2026Tao Feng, Tianyang Luo, Jingjun Xu +5Retrieval-Augmented Generation Agentic RAG
Department of Computer Science, University of Illinois Urbana-Champaign, Urbana, IL, USA · Meta Monetization AI, USA
ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents
May 29, 2026Tao Feng, Chongrui Ye, Tianyang Luo +8Continual Learning for LLM Agents LLM Agent Skill Learning
University of Illinois Urbana-Champaign · 2Nanyang Technological University · 3Meta Monetization AI
Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents
Apr 17, 2026Xing Zhang, Guanghui Wang, Yanwei Cui +4LLM Agent Memory LLM Agent Skill Learning
AWS Generative AI Innovation Center · HSBC Holdings Plc., HSBC Technology Center, China.
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
Apr 6, 2026Chenxi Wang, Zhuoyun Yu, Xin Xie +8LLM Agent Skill Learning LLM Agents
1Zhejiang University · 2Ant Digital Technologies, Ant Group.
Decocted Experience Improves Test-Time Inference in LLM Agents
Apr 6, 2026Maohao Shen, Kaiwen Zha, Zexue He +6Experience Learning for LLM Agents LLM Context Management
Massachusetts Institute of Technology · Stanford University · MIT-IBM Watson AI Lab +2
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Mar 26, 2026Jingwei Ni, Yihao Liu, Xinpeng Liu +7LLM Agent Skill Learning Experience Learning for LLM Agents
ETH Zürich · University of Zurich · Peking University +2
Experiential Reflective Learning for Self-Improving LLM Agents
Mar 25, 2026Marc-Antoine Allard, Arnaud Teinturier, Victor Xing +1Experience Learning for LLM Agents Self-Improving Agents
Illuin Technology
AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling
Mar 22, 2026Liang DingHindsight Experience Replay LLM Agent Training
The University of Sydney
Memento-Skills: Let Agents Design Agents
Mar 19, 2026Huichi Zhou, Siyuan Guo, Anjie Liu +14Agentic AI LLM Agent Skill Learning
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
Internalizing Agency from Reflective Experience
Mar 17, 2026Rui Ge, Yichao Fu, Yuyang Qian +4Experience Learning for LLM Agents LLM Agent Training
University of California San Diego · Shanghai Jiao Tong Univsersity · Nanjing University

Oct 25, 2026J/K move · Enter open · S save

Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents

Haoyu Zhao, Sitian Tu, Yuxuan Huang, Huichi Zhou+15

Experience Learning for LLM Agents Continual Learning for LLM Agents Long-Horizon Agent Evaluation AI Agent Benchmarks LLM Agent Training

Open paper AskPDF arXiv

Continual learning is the ability of LLM agents to improve over time by acquiring, refining, and applying knowledge from experience while retaining useful prior knowledge. It is essential for agents learning over long time horizons, yet current evaluations largely assess individual task performance rather than improvement through accumulated experience. We introduce Continual Learning Exam (CLE), a large-scale benchmark developed by 50+ domain experts to measure experience-driven improvement in realistic professional workflows. CLE comprises 120 human-authored tasks, each organised as a five-level ladder, yielding 600 levels spanning 89 professional roles across 12 occupational domains. Agents must pass each level to unlock the next, with later levels building on experience accumulated during earlier assignments. An evaluation agent assesses each submission against human-authored rubrics. We compare a single-submission setting with one that provides diagnostic feedback after failure and allows one revision. Across 17 harness-model configurations using frontier LLMs, feedback and revision yield a median completion gain of 5.3 percentage points. Yet the best-performing system clears only 47.7% of levels and completes all five levels in just 23.3% of tasks, highlighting the difficulty of sustained learning from experience for existing frontier LLMs. As such, the dataset can also be used to post-train LLMs to strengthen their continual learning capabilities.