Self-Reflection in Language Model Agents

Latest papers

36 papers7 papers in the last four weeks, up 75% on the four weeks before. 0.0% of all new papers.

AllPath: Layered Verification for a Deployed, Self-Revising LLM Trading Agent under Human-Gated and Autonomous Regimes
Oct 19, 2026Tian Zhang, Meng LiLLM Agent Verification LLM Agents
Independent Researcher USA
CoMem: Learning to Anticipate Failures from Retrieved Experience
Oct 19, 2026Yun Shen, Ming Shen, Tianjun YaoMemory-Augmented Language Model Agents Self-Reflection in Language Model Agents
The Ohio State University · Shenzhen Loop Area Institute · Shanghai Jiaotong University
InteractAgent: Agentic Human Motion Interaction with Memory-Augmented Reflection
Oct 19, 2026Tao Zhang, Senhe Zhang, Zeyu Zhang +2Long-Horizon Agent Tasks Multimodal Agents
AI Geeks · UNSW Sydney
Self-Reflective Chain-of-Thought (SRCoT): Evidence-Based Text Generation via a Closed-Loop Retrieve--Reflect--Revise Pipeline on Edge LLMs
Oct 16, 2026Fabian Broszio, Michael Hoffmann, Adrian PaschkeEvidence-Grounded Generation Self-Reflection in Language Model Agents
Department of Mathematics and Computer Science, Freie Universität Berlin, Arnimallee 14, Berlin, 14195, Germany.
Federation over Harness
Oct 15, 2026Dixi Yao, Tahseen Rabbani, Tian LiAgent Harness Optimization LLM Agent Self-Improvement
University of Chicago
Agent-Reflex: Teaching Language Agents to Act Reflectively
Oct 13, 2026Guanting Dong, Xinyu Yang, Jiajie Jin +9LLM Agent Training Self-Reflection in Language Model Agents
Gaoling School of Artificial Intelligence, Renmin University of China · National University of Singapore
Counterfactual Regret for Reflective Agents with Lean-Verified Guarantees
Oct 10, 2026Zhongnian Li, Shi Xu, Mengting Xu +2Self-Reflection in Language Model Agents Counterfactual Regret Minimization
School of Computer Science and Technology / School of Artificial Intelligence China University of Mining and Technology Xuzhou, China
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Sep 29, 2026Hongjin Qian, Chaofan Li, Kun Luo +11LLM Self-Refinement LLM Agent Training
Beijing Academy of Artificial Intelligence (BAAI)
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
Nudgeability: Reasoning Models Follow Confidence Signals Without Tracking Their Own Competence
Sep 28, 2026Rohit Saxena, Utkarsh UpadhyayLanguage Model Self-Assessment LLM Tool Use
Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments
Sep 16, 2026João Meneses dos Santos, Arlindo L. OliveiraCognitive Architectures for AI Agents Self-Reflection in Language Model Agents
Instituto Superior Técnico, Universidade de Lisboa, Portugal · INESC-ID, Lisboa, Portugal
Self-Emergence Agent Architecture:Behavior-Inertia HMM, Reflexive Metacognition,and Social-Contrastive Self-Modeling
Sep 15, 2026Xiaoyang LiuSelf-Evolving Agents Cognitive Architectures for AI Agents
Independent Researcher
Strangers to Themselves: What Language Models Say About Themselves Is Generic
Sep 9, 2026Phil Blandfort, Urja PawarLanguage Model Self-Assessment Metacognition in Language Models
Predictably Weird · Independent
Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems
Sep 2, 2026Yihang Chen, Yuxiang Chen, Yuxuan Huang +3Self-Reflection in Language Model Agents Multi-Agent LLM Systems
1UCL Centre for Artificial Intelligence · University of Liverpool · 3Huawei
ReflectFact: Self-Reflective Agents for Improving Comprehension and Reasoning in Multi-Hop Fact Verification
Aug 13, 2026Runze Zhao, Zixin Tang, Xiaoshuai Hao +4Self-Reflection in Language Model Agents Automated Fact-Checking
Institute of Information Engineering, Chinese Academy of Sciences · 1Zhongguancun Laboratory · 3Xiaomi EV
LoongReflect: Boosting Long-Horizon Reflection in Search Agents via Global Perspective Distillation
Aug 12, 2026Zhixin Zhang, Xinke Jiang, Zhibang Yang +5LLM-Guided RL LLM Agents
School of Computer Science, Peking University, Beijing, China · National Engineering Research Center for Software Engineering, Peking University, Beijing, China · Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China +2
Autoreflection: How Agentic Strange Loops Turn Human Culture into AI Infrastructure
Aug 4, 2026Holly LewisLLM Agents Self-Evolving Agents
Southern Illinois University Carbondale · Department of Philosophy, Southern Illinois University Carbondale
Reflection or Re-Generation? Why LLM Revision Fails Where Human Revision Succeeds
Jul 31, 2026Yefan Tao, Gerald Friedland, Madhusudhanan Chandrasekaran +1LLM Self-Correction LLM Self-Refinement
Amazon
Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B
Jul 30, 2026Iliya MirzaeiLanguage Model Self-Assessment LLM Self-Refinement
Department of Computer Science Stony Brook University
Procedural Memory Distillation: Online Reflection for Self-Improving Language Models
Jul 1, 2026Ye Liu, Srijan Bansal, Bo Pang +6Self-Reflection in Language Model Agents Language Model Distillation
Salesforce AI Research
Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking
Jul 1, 2026Chia-Hsuan Lee, Sihui Dai, Mingyang Zhou +4Reasoning Trace Analysis Overthinking in Language Models
Capital One
ManimAgent: Self-Evolving Multimodal Agents for Visual Education
Jun 29, 2026Wenjia Jiang, Zongyuan Cai, Yuanhang Shao +7Continual Learning for LLM Agents LLM Agent Self-Improvement
University of Alberta · Southeast University · Virginia Tech +2
Retrospective Progress-Aware Self-Refinement for LLM Agent Training
Jun 12, 2026Xinbei Ma, Congmin Zheng, Jiyang Qiu +11Reward Shaping LLM Agent Training
Shanghai Jiao Tong University · OPPO Research Institute
Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL
Jun 12, 2026Yinglun ZhuLLM Agent Evaluation Language Model Calibration
University of California, Riverside
Honest Lying: Understanding Memory Confabulation in Reflexive Agents
May 28, 2026Prakhar Dixit, Sadia Kamal, Tim OatesAI Agent Reliability LLM Self-Refinement
Department of Computer Science, University of Maryland Baltimore County, Baltimore, MD, USA.
BenchTrace: A Benchmark for Testing Reflection Ability and Controlled Evolution in LLM Agents
May 28, 2026Jiahao Huang, Fei Cheng, Junfeng Jiang +2LLM Agent Evaluation Self-Reflection in Language Model Agents
University of Tokyo · Kyoto University · National Institute of Informatics
Training Language Agents to Learn from Experience
May 19, 2026Yuval Shalev, Zifeng Ding, Mateja JamnikContinual Learning for LLM Agents Self-Improving Agents
University of Cambridge
OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences
May 18, 2026Kaixiang Wang, Jiong Lou, Zhaojiacheng Zhou +1Self-Reflection in Language Model Agents LLM Agent Security
Shanghai Jiao Tong University Shanghai, China
ReFlect: An Effective Harness System for Complex Long-Horizon LLM Reasoning
May 7, 2026Fan HuangLLM Self-Correction Long-Horizon LLM Reasoning
Indiana University Bloomington
Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents
Apr 29, 2026Benjamin Probst, Andreas Happe, Jürgen CitoSelf-Reflection in Language Model Agents Open-Weight Language Models
TU Wien, Vienna, Austria

Oct 19, 2026J/K move · Enter open · S save

AllPath: Layered Verification for a Deployed, Self-Revising LLM Trading Agent under Human-Gated and Autonomous Regimes

Tian Zhang, Meng Li

Independent Researcher USA

LLM Agent Verification LLM Agents LLM Agent Reliability AI Agent Monitoring Runtime Enforcement for AI Agents Self-Reflection in Language Model Agents

Open paper AskPDF arXiv

LLM trading agents are evaluated almost exclusively in backtests and autonomous benchmark harnesses. Deployment, where actions are irreversible, raises a different question: who verifies the agent's actions, and which failures can each verifier structurally catch? We report on AllPath, a personal LLM trading agent deployed against a live paper-brokerage account. The system watches positions through a deterministic rules engine, and each night it reviews its own day and proposes revisions to its own trading strategies. Verification is split across three layers. Code verifies what must not depend on judgment: deterministic gates enforce risk limits and block any strategy revision that fails an integrity check. The agent verifies itself within fixed bounds: its nightly review has an iteration cap and no tools that can act. A human verifies judgment, through approval screens that show the current state of each proposal. We also compared two verification policies for the agent's self-revisions on the live system: two and a half weeks with every self-revision human-gated, then five weeks with reflection revisions auto-applied behind the same code gates, while the operator's chat channel stayed human-gated throughout. Each layer caught a different kind of failure. The code gates rejected no proposal; their role was keeping revisions consistent. The human rejected two proposals that passed every code check, both over a disagreement about the market, and later removed 11 of the 19 rules the agent had added on its own, at a median lag of eight days. The most instructive production incidents, such as strategies silently left unmonitored, passed every gate; the operator found them by hand, and the fix each time was an interface change that makes the condition visible. We contribute the layered architecture, the two-regime account, and a production incident taxonomy, none observable in a backtest.