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

Better, Faster, Stronger: Programmatic Skill Learning Best Reduces Agent Cost
Aug 11, 2026Zixi Huang, Xiheng Wang, Andrew Wang +4LLM Agent Self-Improvement LLM Agent Skill Learning
Johns Hopkins University
Emotion2Skill: Model-Internal Emotion Signals for Adaptive Skill Selection and Evolution
Aug 10, 2026Bohan Lin, Hejia Geng, Xinyi Xie +5LLM Agent Self-Improvement LLM Agent Skill Learning
University of Science and Technology of China (USTC) · 2Suzhou Institute for Advanced Research, USTC · University of Oxford +2
SiriusDeliver: Automating Data Warehouse Delivery at Tencent
Aug 10, 2026Haining Xie, Xiaokai Zhou, Jiaming Yang +12LLM Agent Orchestration LLM Agent Self-Improvement
TEG, Tencent Inc. · Wuhan University
Social Gym and SPaRTan: Benchmarking and Improving LLM Social Reasoning via Multi-Agent Game Tournaments
Aug 10, 2026Keyu He, Xuhui Zhou, Maarten SapGame-Playing Agents LLM Agent Evaluation
Carnegie Mellon University
Tree-of-Experience: Hierarchical Experience Management for Self-Evolving Agents
Aug 10, 2026Zihao Deng, Yining Zhu, Leiming Wang +6Continual Learning for LLM Agents LLM Agent Self-Improvement
Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses
Aug 9, 2026Tailin ZhouAgent Harness Optimization LLM Agent Self-Improvement
HKUST
Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution
Aug 8, 2026Anton Razzhigaev, Andrei Gritsaev, Andrei Kaznacheev +3AI Coding Agents Agent Harness Optimization
1Lomonosov Moscow State University · 2Skolkovo Institute of Science and Technology · 4FusionBrain Lab at AIRI +2
SkillSmith: Enhancing Locally Deployed Agents via Automatic Skill Construction and Evolution
Aug 8, 2026Xinle Jiang, Remy Xie, Ming TangLLM Agent Self-Improvement LLM Agent Skill Learning
Southern University of Science and Technology, China · AOE Tech Labs Ltd., Hong Kong
Towards Researcher Agents for Knowledge-Graph Question Answering
Aug 7, 2026Tommaso Soru, Abdulsobur OyewaleLLM Agent Self-Improvement Knowledge Graph Question Answering
1Liber AI Research, London, United Kingdom
SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent
Aug 7, 2026Mingxuan Zheng, Yujin Zhou, Chuxue Cao +6LLM Agent Self-Improvement LLM Agent Skill Learning
Hong Kong University of Science and Technology · Macau University
Mendel Gödel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution
Aug 7, 2026Changzhi Liu, Yilun Liu, Sikuan Yan +2Coding Agents Genetic Programming
University of Electronic Science and Technology of China · Ludwig Maximilian University of Munich · Munich Center for Machine Learning
SkillHEX: Improving Agent Skills via Hypothesis-Driven Autonomous Exploration and Exploitation
Aug 6, 2026Yuru Feng, Yaoqi Chen, Beidi Zhao +7Test-Time Adaptation LLM Agent Self-Improvement
Microsoft · University of California, San Diego · University of Science and Technology of China +1
Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks
Aug 5, 2026Boxiu Li, Zimo Wen, Yijia Fan +24LLM Agent Orchestration LLM Agent Self-Improvement
Argus Team
EvolveNet: Collaborative Harness Evolution for Agent Self-Improvement
Aug 5, 2026Jun Nie, Yonggang Zhang, Qianshu Cai +3Agent Harness Optimization Multi-Agent Collaboration
Hong Kong Baptist University · The Hong Kong University of Science and Technology · University of Science and Technology of China
Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories
Aug 3, 2026Shuai Shao, Kangning Zhang, Qingyao Li +7Agent Harness Optimization LLM Agent Self-Improvement
Shanghai Jiao Tong University · Xiaohongshu Inc. · Southeast University
Learning What to Remember and What to Internalize in LLM Self-Evolution via Adaptive Memory-Parameter Coordination
Aug 2, 2026Tianyun Ji, Zhenya Huang, Jiayu Liu +3Continual Learning for LLM Agents Agent Harness Optimization
University of Science and Technology of China Hefei, Anhui, China · City University of Hong Kong Hong Kong, China · Hefei Normal University Hefei, Anhui, China +1
DarwinX: Evolving Agent Harnesses Through Natural Selection
Jul 31, 2026Yifan Zhang, Yutong Dai, Juntao Tan +9Evolutionary Optimization Agent Harness Optimization
1Salesforce AI Research · 2Salesforce Agentforce
Self-Supervised Skill Optimization
Jul 30, 2026Siran Peng, Cuiyu Yang, Tianyu Fu +9Large Language Model-Guided Optimization LLM Agent Self-Improvement
1MAIS, CASIA · 3Mininglamp Technology · 2SAI, UCAS +2
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents
Jul 30, 2026Hanzhang Zhou, Panrong Tong, Xu Zhang +13Mobile GUI Automation Computer-Use Agents
MAI-UI Team Alibaba Token Hub, Alibaba Group
VeriSkill: A Self-Evolution Framework for Program Verification Skills
Jul 30, 2026Changguo Jia, Tianqi Zhao, Zhiyou Xiao +2LLM Agent Self-Improvement Formal Verification
Peking University, Beijing, China · Zhongguancun Laboratory, Beijing, China · Shanghai Jiao Tong University, Shanghai, China
SkillMentor: LLM Agent Self-Evolution via Learning Blind-Spot Diagnosis
Jul 29, 2026Xiaoyi Bao, Yuanzhen Xie, Yunzhi Tan +5Agent Failure Analysis LLM Agent Self-Improvement
The Hong Kong Polytechnic University · Work done during an internship at Tencent. · Platform and Content Group, Tencent +1
RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement
Jul 28, 2026Fanqing Meng, Lingxiao Du, Qiguang Chen +4LLM Agent Evaluation LLM Agent Self-Improvement
1Evolvent AI · 2National University of Singapore
Self-Authored Verification Is Unreliable in Heuristic Self-Improving Agents
Jul 27, 2026Diandian Guo, Cong Cao, Fangfang Yuan +3AI Agent Evaluation LLM Agent Self-Improvement
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China
AgentOmnia: Scaling Agentic Models for Full-Scenario Applications
Jul 25, 2026Hao Jiang, Gangtao Xin, Yingdi Huang +35Tool-Augmented Language Model Agents Agentic RL
Huawei Cloud Post-Training Team
From Agent Failures to Text Policies: What Works and What Breaks
Jul 22, 2026Jaideep Ray, Ankit GoyalPolicy Optimization LLM Agent Self-Improvement
Independent Researcher
Verifiable Self-Evolution for Open-Ended Dialogue Skills via Future-Feedback Prediction
Jul 21, 2026ChaoJin Zhao, Xuan JiangLLM Agent Self-Improvement LLM Agent Skill Learning
ByteDance
Self-Modifying Lean Proof Agents with Verifier-Grounded Benchmark Coevolution
Jul 19, 2026Yuqing Li, Zeguan Wu, Yu Gan +1LLM Agent Self-Improvement Lean Theorem Proving
University of Pittsburgh
AgentBrew: Lifelong Knowledge Brewing from Strong Teachers to Weak LLM Agents
Jul 18, 2026Yangqin Jiang, Chao HuangLLM Agent Self-Improvement LLM Agent Skill Learning
The University of Hong Kong
Recursive Harness Self-Improvement
Jul 17, 2026Hyunin Lee, Jinglue Xu, Jeffrey Seely +3Continual Learning for LLM Agents Agent Harness Optimization
1Sakana AI, 2UC Berkeley
Reward-Free Evolving Agents via Pairwise Validator
Jul 15, 2026Minghao Liu, Yu Wang, Jiayun Wang +1Pairwise Preference Evaluation LLM Agent Self-Improvement
Accenture

Aug 11, 2026, cs.CLJ/K move · Enter open · S save

Better, Faster, Stronger: Programmatic Skill Learning Best Reduces Agent Cost

Zixi Huang, Xiheng Wang, Andrew Wang, William Jurayj+3

Johns Hopkins University

LLM Agent Self-Improvement LLM Agent Skill Learning Embodied AI

Open paper AskPDF arXiv

Recently, the practice of augmenting LLM agent capability with skills has gained prevalence. We explore the cost effective adaptation of agents to novel domains by means of learning skills. Existing works focus on performance gain over cost effectiveness. As a result, little is known about what skill learning strategies save cost. We argue that among all the different skill learning methods, those that view skills as programs can achieve the best cost reduction. By executing sequences of actions deterministically, a program-augmented agent can reliably and cheaply achieve goals that would otherwise require trial and error and risk degenerate behavior over long horizons. An agent can learn at inference time by incrementally discovering these programs and equipping them for future tasks. We hypothesize that past trajectories contain enough signal to guide skill learning, even without replay or validation, provided the agent can learn to analyze them. To test our claims, we propose SpeedRunner, a coding agent that analyzes trajectories and refactors skills for better performance on future tasks. Across three different embodied environments, we show that SpeedRunner consistently achieves the frontier in learning and cost reduction while remaining robust against distribution shifts and environmental randomness.

Momentum

Related topics

Latest papers 189