LLM Agent Self-Improvement

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

44 papers in the last four weeks, up 267% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 189

All topics

Agentic-TTT: Training test-time policy for test-time training
Oct 8, 2026Jiahao Lu, Mohan KankanhalliTest-Time Training LLM Agent Self-Improvement
NUS AI Institute National University of Singapore
AgentEvolver: System-Wide Self-Evolution Through Task Execution
Oct 8, 2026Wentao Zhang, Fuchao Yang, Yilei Zhao +2LLM Agent Self-Improvement Self-Evolving Agents
Who Verifies the Verifier? Co-Evolving Inspectable Graders with Self-Improving Agents
Oct 8, 2026Xing Zhang, Guanghui Wang, Yanwei Cui +4Automated Evaluation LLM Agent Self-Improvement
AWS Forward Deployed Engineering · HSBC Holdings Plc., HSBC Technology Center, China
RSIGym: A Flexible Environment for Recursive Self-Improvement
Oct 7, 2026Fanqing Meng, Lingxiao Du, Haocheng Lu +6LLM Agent Self-Improvement Recursive Self-Improvement
Evolvent AI · National University of Singapore
The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate
Oct 7, 2026Ravil AkhtyamovLLM Agent Self-Improvement AI Agent Governance
Digital Economy Lab
Self-Evolve With a Reference:Anchored Training of Tool-Integrated Agents
Oct 7, 2026Wenjie Liao, Liangjie Zhao, Zehong CaoLLM Agent Self-Improvement Self-Evolving Agents
Waseda University · Adelaide University
FreeEvolve: Learning to Evolve Beyond Fixed Loops
Oct 6, 2026Lecheng Kong, Like Hui, Nikos Kanakaris +3Self-Evolving Agents LLM Agent Self-Improvement
AWS AI Labs · Georgia Institute of Technology
Agent Plasticity: Measuring Self-Improvement Through Experience
Oct 6, 2026Harman Singh, Anton Bakhtin, Rulin Shao +8Self-Improving Agents LLM Agent Self-Improvement
UC Berkeley · Meta Superintelligence Labs · University of Washington +1
ServeLearnBench: How Well Can Agents Self-Improve from Serving Experience?
Oct 6, 2026Haizhong Zheng, Yizhuo Di, Ranajoy Sadhukhan +2Continual Learning for LLM Agents LLM Agent Evaluation
Carnegie Mellon University · Amazon
MESH-Harness: Self-Improving Agent Harnesses via Bandit-Guided Compositional Evolution
Oct 4, 2026Zhiwei Shang, Yu Huo, Mingrong Gong +6Agent Harness Optimization LLM Agent Workflow Optimization
The Chinese University of Hong Kong, Shenzhen · DeepWisdom · The Chinese University of Hong Kong +3
Mimir: Physics-Grounded LLM Agents for Long-Horizon Irrigation Control
Oct 1, 2026Yimeng Liu, Mi Zhang, Younsuk Dong +1Language Model-Based Control LLM Agent Self-Improvement
Michigan State University · Ohio State University
It Takes Workflows to Evolve Better Workflows
Oct 1, 2026Xuehang Guo, Haoyu Wang, Haifeng Chen +3LLM Agent Workflow Optimization Multi-Agent Collaboration
William & Mary · NEC Corporation of America · University of Illinois Urbana-Champaign
SkillSpec: Consensus-Gated Agent Skill Evolution via Representation Specialization
Sep 30, 2026Huancheng Chen, Xiaodi Sun, Zhaoqiong Huang +2LLM Agent Self-Improvement LLM Agent Skill Learning
Microsoft AI
Learning from Research: Toward Lifelong Agent Harness Evolution
Sep 30, 2026Jingbo Yang, Kwei-Herng Lai, Xiaowen Wang +3Large Language Model-Guided Optimization Lifelong Learning Agents
University of California, Santa Barbara · Microsoft
ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation
Sep 30, 2026Shengjie Jin, Hengbo Xu, Zelong Sun +2On-Policy Self-Distillation LLM Agent Self-Improvement
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China
Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents
Sep 30, 2026Kaixing Zhang, Changming Li, Yingdong Shi +5LLM Agent Self-Improvement LLM Agent Skill Learning
ShanghaiTech University · Meituan
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Sep 30, 2026Meijia Chen, Hao Li, Zheng Lu +12Agentic Search LLM Agent Self-Improvement
Rutgers University · Independent Researcher · University of California, San Diego +3
From Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs
Sep 29, 2026Kunal Jha, Max Kleiman-Weiner, Natasha JaquesLLM Agent Self-Improvement LLM Agent Skill Learning
Department of Computer Science, University of Washington, Seattle, WA 98195, USA.
Self-Evolving Harness on Multiple Tasks with the Agent as Its Own Optimizer
Sep 29, 2026Qiankai XuContinual Learning for LLM Agents AI Agent Evaluation
Nanjing University
AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation
Sep 29, 2026Rishabh Agrawal, Hejie Cui, Shasha Li +2Language Model Steering LLM Agent Self-Improvement
Google · University of Southern California
Video-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution
Sep 29, 2026Bingjun Luo, Jialin Guo, Siqi LiVideo Understanding Agent Harness Optimization
Tsinghua University · Harbin Engineering University
Harness Evolution as Learning: Approximation, Generalization, and Optimization Limits of Self-Improving Personal Agents
Sep 29, 2026Zeyu Gan, Zixuan Gong, Yong LiuAgent Harness Optimization LLM Agent Self-Improvement
Gaoling School of Artificial Intelligence Renmin University of China Beijing, China
WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents
Sep 29, 2026Bo Mao, Hang He, Linting Wang +17LLM Agent Self-Improvement LLM Post-Training
East China Normal University · Shanghai Innovation Institute · Fudan University +2
SAGE: A Statistical Acceptance Gate for Self-Evolving Agents
Sep 28, 2026Yihao Wang, Linhan Xia, Rui Liu +6LLM Agent Self-Improvement LLM Agent Skill Learning
Peking University · University of Oklahoma · Tencent +5
Shockingly Simple Self-retrospection Improves Agentic Models Without RL
Sep 28, 2026Jonathan Light, Christopher Zhang Cui, Jeonghye Kim +7Self-Training for Language Models LLM Agent Self-Improvement
RPI · Microsoft Research · UC San Diego +2
The Right Lesson at the Right Step: Deriving Control Updates for Self-Evolving Agents
Sep 28, 2026Yunhe Su, ZiYi Dong, Tong Yu +4LLM Agent Self-Improvement Self-Evolving Agents
Sun Yat-sen University · eunomia-bpf community · Tsinghua Shenzhen International Graduate School, Tsinghua University +3
From Weak Task Specifications to Scientific Extraction Agents: Optimizing Task Construction
Sep 28, 2026Zixiao Dong, Wei Yang, Zihao Liu +4LLM Agent Self-Improvement Automatic Prompt Optimization
School of Computer Science and Technology, University of Science and Technology of China · State Key Laboratory of Cognitive Intelligence · University of Science and Technology of China +1
Self-Evolving Agents via Likelihood-Guided Tool-Space Optimization
Sep 28, 2026Xuanqi Zhang, Ruinan Jin, Running Yang +4Continual Learning for LLM Agents LLM Agent Self-Improvement
University of British Columbia · Vector Institute · Columbia University
R $^2$ Flow: Recursive Self-Improvement via Recursive Skill Evolution
Sep 27, 2026Mingda Zhang, Qiang Huang, Yanjin Li +4LLM Agent Self-Improvement Generative Flow Networks
The Chinese University of Hong Kong, Shenzhen · Fudan University · University of Illinois at Urbana-Champaign +2
Self-Designed Evaluators and Warm Memory for Long-Horizon Agents
Sep 27, 2026Saeid Asgari, Emre Kiciman, Leonardo de Oliveira Nunes +1Language Model Generation Evaluation Long-Horizon Agent Evaluation
Microsoft

Oct 8, 2026, cs.LGJ/K move · Enter open · S save

Agentic-TTT: Training test-time policy for test-time training

Jiahao Lu, Mohan Kankanhalli

NUS AI Institute National University of Singapore

Test-Time Training LLM Agent Self-Improvement Agent Skill Learning

Open paper AskPDF arXiv

Test-time training (TTT) adapts an LLM's parameters using signals derived from test inputs, and can make striking improvements in pre-specified settings such as IMO competitions or designated open problems. By turning deployment experience into parameter updates, TTT provides a direct mechanism for model-level self-improvement. Yet TTT is not universally beneficial: each TTT algorithm works in different settings, and applying an ill-suited method could waste test-time compute or even damage model performance. Therefore, such parameter-level self-improvement requires agency: the model must decide when TTT is warranted, which algorithm to invoke, and whether an existing skill can be reused. To fill this gap, we introduce Agentic-TTT, which learns a test-time policy to govern those decisions. Agentic-TTT turns TTT procedures into callable tools, treats accumulated skills as an evolving deployment environment, and trains its policy using the observed utility gains from its decisions. On our benchmark, Agentic-TTT nearly doubles the utility over the backbone model, learns to trade off utility against compute, and generalizes to domains unseen during training. Together, these results point toward autonomous self-improvement: models that can decide how to learn from their own deployment experience.

Momentum

Related topics

Latest papers 189