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

Breaking the Environment Wall: A Unified Framework for Preparing and Evolving Agent-Native Environments
Sep 24, 2026Yukai Wu, Yuanjing Yang, Le Zhou +8LLM Agent Self-Improvement LLM Agent Training
Shanghai Jiao Tong University · Theseus Labs · Tencent Hunyuan
A Wrong Turn Does Not Ruin the Journey: Deviation-Guided Skill Self-Evolution for LLM Agents
Sep 24, 2026Yichun Feng, Jiawei Wang, Haozhe SunLLM Agent Self-Improvement LLM Agent Skill Learning
University of Chinese Academy of Sciences · University of Science and Technology of China · Meituan
TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent
Sep 23, 2026Jie Yang, Yan Zheng, Jiarui Sun +8Time Series QA LLM Agent Self-Improvement
University of Illinois at Chicago · Visa Research · University of Florida +2
Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity
Sep 22, 2026Zhening Li, Joshua Liu, Mateja Vukelic +7LLM Agent Memory LLM Agent Self-Improvement
MIT CSAIL · Independent Researcher
Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents
Sep 22, 2026Laizhen Li, Jiarui Li, Juanjuan Zhao +4Agent Harness Optimization LLM Agent Workflow Optimization
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Shenzhen University of Advanced Technology +1
Recursive self-improvement of AI research agents
Sep 22, 2026Dhruv Srikanth, Bingchen Zhao, Dixing Xu +2LLM Agent Self-Improvement Recursive Self-Improvement
Weco AI
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
Sep 21, 2026Peng Xia, Rujun Han, Zifeng Wang +11OOD Generalization Agent Harness Optimization
Google Cloud AI Research · UNC-Chapel Hill · Stanford University +1
TTSE: A Two-Track Online Self-Evolution Framework
Sep 21, 2026Ruimin Pei, Yongkang Wu, Shangyi Zheng +5LLM Agent Self-Improvement Agent Skill Learning
Poisson Lab, Huawei China
DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement
Sep 18, 2026Siyuan Liu, Fan Yu, Dongyu Ru +5LLM Self-Refinement AI Agent Evaluation
Fudan University · Meituan Longcat Team
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
Sep 17, 2026Haozhe Liu, Tian Ye, Sensen Gao +11Agent Harness Optimization LLM Agent Workflow Optimization
NVIDIA · NTU · MIT
FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA
Sep 17, 2026Yanzhang Ma, Zhenghan Tai, Hanwei Wu +25LLM Agent Self-Improvement LLM Agent Skill Learning
University of Toronto · McMaster University · University of California, Los Angeles +11
Self Improvement via Fast Tree-search
Sep 17, 2026Xinghong Fu, Aravinth Kulanthaivelu, Yutaro YamadaInference-Time Search AI Coding Agents
Massachusetts Institute of Technology · Sakana AI
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
Sep 15, 2026Shuhan Xue, Jianyuan Zhong, Ziyuan Nan +10Continual Learning for LLM Agents AI-Assisted Scientific Research
EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents
Sep 15, 2026Sehee Kim, Yumin Choi, Minki Kang +1LLM Agent Self-Improvement Prompt Optimization
KAIST
EvoOntology: A Self-Evolving Ontology Layer for Data Agents
Sep 14, 2026Meiduo Chong, Shaolei Zhang, Ju Fan +1LLM Agent Self-Improvement Self-Evolving Agents
Renmin University of China
RESKILL: Explicit Failure Attribution and Structured Repair for Interactive Language Agents
Sep 14, 2026Mengyi Deng, Xin Li, Duyi Pan +4LLM Agent Self-Improvement LLM Agent Skill Learning
1Information Hub, The Hong Kong University of Science and Technology (Guangzhou), China · 2The Hong Kong University of Science and Technology, Hong Kong SAR
SkillLift: Learning Dense Rubrics from Sparse Oracles for Efficient Skill Evolution
Sep 14, 2026Haoxiang Kang, Ming WenSurrogate-Assisted Optimization LLM Agent Self-Improvement
1Independent Researcher · 2Fudan University
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
Sep 14, 2026Sibo Zhu, Shicheng Fan, Xinyue Wang +3Multi-Agent LLM Systems LLM Agent Self-Improvement
Aether AI · University of California San Diego · ‡Work done during internship in Aether AI +1
EMR: Self-Evolving Medical Multi-Agent System via Experience Mining and Reuse
Sep 14, 2026Dongsheng Shi, Yue Li, Xin Yi +1Continual Learning for LLM Agents Multi-Agent LLM Systems
East China Normal University · City University of Hong Kong
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
Sep 14, 2026Siwei Wu, Jincheng Ren, Yizhi Li +11Coding Agents Agent Harness Optimization
University of Manchester · 3IQuest Research · 4M-A-P +3
SkillAdam: Stable and Efficient Skill Evolution for Agents
Sep 8, 2026Gaoyuan Li, Meihao Fan, Yizhe Liu +7Large Language Model-Guided Optimization LLM Agent Self-Improvement
Renmin University of China · Tencent
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
Sep 8, 2026NeoHorse Team, Guoliang Cao, Guohao Dai +34Agent Harness Optimization LLM Agent Self-Improvement
TokenRhythm
SQL-Zero: Self-Evolving Text-to-SQL
Sep 7, 2026Daniel Machado Pedrozo, Julia Soares Dollis, Bryan Lincoln Marques de Oliveira +3Reinforcement Learning Self-Play RL
Instituto de Informática, Universidade Federal de Goiás Goiânia, GO, Brazil
Aspire: Can Models Self-Evolve from Vague Goals?
Aug 31, 2026Yuhao Wu, Jingyuan Zhang, Jiajun Shi +18LLM Agent Self-Improvement AI Agent Benchmarks
S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?
Aug 31, 2026Jiajun Shi, Siyuan Tao, Yuhao Wu +18LLM Agent Evaluation Language Model Self-Assessment
ByteDance Seed
EvoUndo: Recoverability-Constrained Self-Evolution for LLM Agent Harnesses
Aug 28, 2026Tanmay Sah, Dolly Sah, Harshul Jain +1LLM Agent Self-Improvement LLM Agent Harnesses
Independent Researcher
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution
Aug 26, 2026Guibin Zhang, Leo Lu, Fangzhou Xie +15Tool-Augmented Language Model Agents Agent Harness Optimization
JIT-Agent Team
TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents
Aug 24, 2026Wenhao Wu, Menghao Zhang, Xin Wang +3Tool-Augmented Language Model Agents LLM Agent Orchestration
Xiaomi Inc. · Nanjing University · Tsinghua University
SPADE: Self-Play in Adaptive Synthetic Executable Environments
Aug 19, 2026Bo Liu, Simon Yu, Yiding Jiang +15Self-Play RL LLM Agent Self-Improvement
University of Washington · Stanford University · Northeastern University +6
What is Missing from AI Post-Training AI: An Empirical Analysis
Aug 19, 2026Joy Jia Yin Lim, Xin Huang, Hao Peng +5AI Agent Evaluation LLM Agent Self-Improvement
Tsinghua University · University of Electronic Science and Technology of China · Renmin University of China

Sep 24, 2026, cs.AIJ/K move · Enter open · S save

Breaking the Environment Wall: A Unified Framework for Preparing and Evolving Agent-Native Environments

Yukai Wu, Yuanjing Yang, Le Zhou, Shaokun Han+7

Shanghai Jiao Tong University · Theseus Labs · Tencent Hunyuan

LLM Agent Self-Improvement LLM Agent Training

Open paper AskPDF arXiv

Many real-world tasks (e.g., office workflows, scientific experimentation) require LLM agents to interact repeatedly with their environments for context-dependent operations. However, such environments are often not agent-ready. First, information is often scattered and fragmented across the environment. Second, relevant evidence in the environment is often mixed with misleading information and conflicting versions. Third, environments evolve over time, introducing new noise and more challenging tasks. These challenges can substantially degrade performance for state-of-the-art AI agents (e.g., from 83.9% to 57.6%). To address these challenges, we propose Env-Rethink (a system with 27B post-trained model) that supports three main capabilities: (1) It adaptively builds Collection Maps (for organizing related files) and Event Logs (for contextualizing cross-data relationships) to supplement necessary context; (2) It further leverages the post-trained model (through offline trajectory learning) to identify underlying noise issues in the environment; (3) It ultimately evolves environments through virtual event histories that alter environmental states and evidence relationships, producing more tricky ones for further agent improvement. Experiments show that Env-Rethink can effectively improve downstream task performance (with a 15.1 percentage-point increase in mean rubric pass rate across nine models on 30 tasks).

Momentum

Related topics

Latest papers 189