method · first seen 8 Oct 2026
reflection in language agents
Also: self-repair, self-refinement, self-reflection, reflection trees, agentic self-correction, reflection-based self-correction, reflection-driven self-evolution
Having an LLM review past outcomes and feedback to improve its subsequent outputs or prompts.
Mentions per week
PapersCodeDiscussion
Earliest sources
- ReTeach: Building a Self-Teacher through Multi-Round Reflection and RetryPapers · 8 Oct 2026 · Yafeng Tang, Hao Li, Hongsheng Yu, Qiang Fu
- Meta-Reflective Evolution Effectively Improves Production AI SystemsPapers · 8 Oct 2026 · Seung Won Wilson Yoo, Chang Zeng, Aditi Somayajula, Sahithi Ankireddy, Rohan Kos…
- Reflect After Failure: Brain-Inspired Self-Evolving Agents for Embodied Spatial IntelligencePapers · 14 Oct 2026 · Xin Li, Xiaohuan Gu, Yifan Wang, Shaobin Ling, Tianli Shi, Jingao Xu, Zhimeng Yi…
- NL2SQL with Iterative Self-RefinementPapers · 16 Oct 2026 · Anjali Vemula, Akshat Dasula
- Think More or Read More? A Token-Budget Theory of Reasoning with Shared ContextPapers · 16 Oct 2026 · Manh Nguyen, Sunil Gupta, Hung Le
- GraphEvoResearcher: A Cost-Matched Mechanism Analysis of Explicit Reasoning Graphs in Training-Free Self-ReflectionPapers · 19 Oct 2026 · Suxing Liu, Byungwon Min, Zhijian Zheng, Jiahao Wang
Latest sources
- Reflection Is Not Always Worth It: Budgeted Reflection Allocation for Recommendation AgentsPapers · 15 Nov 2026 · Jinfeng Xu, Zheyu Chen, Ziyue Peng, Jianheng Tang, Zheng Lin, Wenhao Yuan, Jian…
- Rethinking Self-Repair in Code-as-Policy Agents: What Drives Retry Success?Papers · 4 Nov 2026 · Siddharth Aphale, Ayushman Singh
- Finding the Pivots to Repair Broken Source-Test Evolution Using LLMsPapers · 2 Nov 2026 · Xiao Chen, Songqiang Chen, Jialun Cao, Yun Peng, Chun Yong Chong, Shing-Chi Cheu…
- EvoRec: A Unified Self-Evolving Agentic Recommender with Dynamic Reflection TreesPapers · 1 Nov 2026 · Mengting Li, Long Zhang, Hao Jiang, Sheng Yu, Fei Pan, Peng Jiang
- SAVIER: Source-Anchored Visual Inspection and Evidence-Guided Repair for Vietnamese Cultural Text-to-Image GenerationPapers · 31 Oct 2026 · Gia-Huy Thai, Duc-Tien Khong, Trung-Nghia Le
- Beyond Passing Tests: A Systematic Review and Controlled Re-evaluation of Techniques for Improving the Quality of LLM-Generated CodePapers · 28 Oct 2026 · Prashank Kadam
- Cycle-of-Thought: Self-Evaluative Iterative Reasoning for Table Visual Question Answering in Document ImagesPapers · 23 Oct 2026 · Somraj Gautam, Gaurav Harit
- Don't Forget What You Just Learned: Self-Directed Repair Turns Agent Mistakes Into Lasting LessonsPapers · 22 Oct 2026 · Yuval Kansal, Karen Ullrich, Polina Kirichenko, Ilia Kulikov, Niraj K. Jha, Moha…
- Governed Self-Evolution for Autonomous Investing: A Multi-Agent LLM System with an Invariant CorePapers · 22 Oct 2026 · Yebo Feng, Jingyang Dai, Liangrui Pan, Nelson Lau, Jiahua Xu, Yang Liu
- GraphEvoResearcher: A Cost-Matched Mechanism Analysis of Explicit Reasoning Graphs in Training-Free Self-ReflectionPapers · 19 Oct 2026 · Suxing Liu, Byungwon Min, Zhijian Zheng, Jiahao Wang
- Think More or Read More? A Token-Budget Theory of Reasoning with Shared ContextPapers · 16 Oct 2026 · Manh Nguyen, Sunil Gupta, Hung Le
- NL2SQL with Iterative Self-RefinementPapers · 16 Oct 2026 · Anjali Vemula, Akshat Dasula