Product
Help
Pricing
About
Jobs
Log in
Get started
Keyword
Add to collection
self-improving agents
Description:
Artificial agents that autonomously modify or learn their capabilities, strategies, or architecture to improve performance on tasks over time.
Related topics:
Reinforcement Learning in Robotics (16%),
AI-based Problem Solving and Planning (11%)
OpenAlex ID:
keywords/self-improving-agents
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
2024
·
Snell, Charlie
, Lee, Jaehoon
, et al.
·
International Conference on Learning Representations
·
2,540
OS-Copilot: Towards Generalist Computer Agents with Self-Improvement
2024
·
Wu, Zhiyong
, Han, Chengcheng
, et al.
·
arXiv (Cornell University)
·
303
PDF
Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization
2024
·
Wenqi Zhang
, Ke Tang
, et al.
·
Proceedings of the conference - Association for Computational Linguistics. Meeting
·
153
PDF
Self-Harness: Harnesses That Improve Themselves
2026
·
Zhang, Hangfan
, Zhang, Shao
, et al.
·
arXiv (Cornell University)
·
150
PDF
Reinforcement Learning for Self-Improving Agent with Skill Library
2026
·
Jiongxiao Wang
, Qiaojing Yan
, et al.
·
Proceedings of the conference - Association for Computational Linguistics. Meeting
·
134
PDF
LLM Agents Making Agent Tools
2025
·
Georg Wölflein
, Dyke Ferber
, et al.
·
Proceedings of the conference - Association for Computational Linguistics. Meeting
·
109
PDF
A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents
2026
·
Wei, Tianxin
, Li, Ting-Wei
, et al.
·
Transactions on machine learning research
·
104
QuantAgent: Seeking Holy Grail in Trading by Self-Improving Large Language Model
2024
·
Wang, Saizhuo
, Yuan, Hang
, et al.
·
RePEc: Research Papers in Economics
·
77
PDF
Continual Harness: Online Adaptation for Self-Improving Foundation Agents
2026
·
Karten, Seth
, Zhang, Joel
, et al.
·
arXiv (Cornell University)
·
67
PDF
A Comprehensive Overview and Survey of Recent Advances in Meta-Learning
2020
·
Peng, Huimin
·
arXiv (Cornell University)
·
66
PDF
Endless Terminals: Scaling RL Environments for Terminal Agents
2026
·
Gandhi, Kanishk
, Garg, Shivam
, et al.
·
arXiv (Cornell University)
·
63
PDF
SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
2025
·
Wanjia Zhao
, Mert Yuksekgonul
, et al.
·
neural information processing systems
·
63
PDF
Self-improving Reactive Agents: Case Studies of Reinforcement Learning Frameworks
1991
·
Long-Ji Lin
·
The MIT Press eBooks
·
50
From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws
2026
·
Chen, Mengzhuo
, Wang, Junjie
, et al.
·
arXiv (Cornell University)
·
45
PDF
UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents
2025
·
Han Xiao
, Guozhi Wang
, et al.
·
neural information processing systems
·
41
PDF
Self-Improvements in Modern Agentic Systems: A Survey
2026
·
Ren, Zhe
, Chen, Yimeng
, et al.
·
arXiv (Cornell University)
·
37
PDF
Useful Memories Become Faulty When Continuously Updated by LLMs
2026
·
Zhang, Dylan
, Lin, Yanshan
, et al.
·
arXiv (Cornell University)
·
35
PDF
Incremental Self-Improvement for Life-Time Multi-Agent Reinforcement Learning
1996
·
Jieyu Zhao
, Jürgen Schmidhuber
·
The MIT Press eBooks
·
34
Depression Diagnosis Dialogue Simulation: Self-improving Psychiatrist with Tertiary Memory
2024
·
Lan, Kunyao
, Jin, Bingrui
, et al.
·
arXiv (Cornell University)
·
32
PDF
The Red Queen Gödel Machine: Co-Evolving Agents and Their Evaluators
2026
·
Iacob, Alex
, Jovanović, Andrej
, et al.
·
arXiv (Cornell University)
·
31
PDF
GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training
2026
·
Cao, Yuan
, Ran, Dezhi
, et al.
·
arXiv (Cornell University)
·
26
PDF
Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes
2008
·
Schmidhuber, Juergen
·
arXiv (Cornell University)
·
26
PDF
WebSynthesis: World-Model-Guided MCTS for Efficient WebUI-Trajectory Synthesis
2025
·
Gao, Yifei
, Ye, Junhong
, et al.
·
arXiv (Cornell University)
·
23
PDF
Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance
2025
·
Yufei He
, Ruoyu Li
, et al.
·
Conference on Empirical Methods in Natural Language Processing (EMNLP)
·
23
PDF
Truly Self-Improving Agents Require Intrinsic Metacognitive Learning
2025
·
Liu, Tennison
, van der Schaar, Mihaela
·
arXiv (Cornell University)
·
20
PDF
Show more works
View as search
Works count:
187
Citation count:
4,827
Year
Topic
Type