Concept · 39 episode(s)

Self-Correction

← all concepts

Definition

Self-correction has a model critique and revise its own output, ideally fixing errors without external feedback. The empirical story is mixed: models are decent at spotting their own mistakes when prompted, less reliable at correcting them, and prone to second-guessing correct answers.

Episodes covering this

  1. 204
    The Length Estimate Hiding Inside a Word-by-Word Model
    How Much is Left? LLMs Linearly Encode Their Remaining Output Length
    · ·14 min·Jul 07, 2026
  2. 194
    How a Robot Builds a Debugging Notebook It Can Read, Edit, and Hand to Another Robot
    ASPIRE: Agentic /Skills Discovery for Robotics
    Lu, Wu, Kou et al. · NVIDIA·24 min·Jul 02, 2026
  3. 189
    Why Phone Agents Ace the Test and Crash on Your Actual Phone
    Xiaomi-GUI-0 Technical Report
    Team, Qu, Luan · Xiaomi·24 min·Jul 02, 2026
  4. 188
    A Coding Agent Found a Hole in a Peer-Reviewed STOC Proof for Five Dollars
    Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics
    Moakhar, Gholami, Springer et al. · University of Maryland·20 min·Jul 02, 2026
  5. 185
    Aligned to Refuse, Built to Tap: When Phone Agents Know the Task Is a Crime and Do It Anyway
    It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents
    Sun, Chen, Zhou et al. · Fudan University·27 min·Jun 30, 2026
  6. 182
    How a Tiny Model Too Weak to Plan Cuts a Bigger Agent's Hallucinations by 80%
    Grounded Iterative Language Planning: How Parameterized World Models Reduce Hallucination Propagation in LLM Agents
    Song, Cai · Emory University·17 min·Jun 29, 2026
  7. 180
    The Bug Where Smart Assistants Read a Fact and Still Forget It
    Supersede: Diagnosing and Training the Memory-Update Gap in LLM Agents
    Patel · Vrin·24 min·Jun 29, 2026
  8. 172
    One Bad Token Can Sink a Model's Math, And You Can Delete It
    Cliff Tokens: Identifying Single-Token Failure Triggers in LLM Mathematical Reasoning
    Ko, Kang, Lee · Seoul National University·22 min·Jun 25, 2026
  9. 168
    When Turning Experience Into Code Makes Your AI Agent Dumber
    Metis: Bridging Text and Code Memory for Self-Evolving Agents
    Dai, He, Li et al. · The Chinese University of Hong Kong·27 min·Jun 24, 2026
  10. 155
    Why a Flawless Demo Makes a Worse Computer-Using Agent, And the Fix
    Skill-Guided Continuation Distillation for GUI Agents
    Fan, Yu, Shen et al. · StepFun·22 min·Jun 18, 2026
  11. 152
    Training a Model to Mean What It Says, And Why That Isn't the Same as Being Good
    Self-CTRL: Self-Consistency Training with Reinforcement Learning
    Pres, Ruis, Ghebreselassie et al. · MIT CSAIL·26 min·Jun 18, 2026
  12. 151
    Why More Experience Made This AI Agent Worse, And How to Fix It
    Not All Skills Help: Measuring and Repairing Agent Knowledge
    Wang, Zhou, Liang et al. · UNC Chapel Hill·28 min·Jun 16, 2026
  13. 150
    Don't Kill the Loser: A Different Way to Handle Two AI Agents Colliding
    CoAgent: Concurrency Control for Multi-Agent Systems
    Lyu, Zhang, Wu et al. · Shanghai Jiao Tong University·32 min·Jun 16, 2026
  14. 142
    Training a Tiny Model to Run the Plumbing Between an Agent and the World
    HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness
    Wang, Wang, Taylor et al. · University of California·24 min·Jun 12, 2026
  15. 140
    When a Reasoning Model Says "Let Me Double-Check" After It's Already Decided
    Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models
    Scalena, Candussio, Bortolussi et al. · University of Groningen / University of Milano-Bicocca·27 min·Jun 12, 2026
  16. 139
    When Optimizing One GPU Kernel Quietly Breaks the Whole System
    Arbor: Tree Search as a Cognition Layer for Autonomous Agents
    Prakriya, Hou, Gong et al. · AMD·30 min·Jun 12, 2026
  17. 133
    How MiniMax Turned a Reward-Hacking Disaster Into Olympiad Gold
    MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling
    Chen, Zhang, Zhang et al. · MiniMax / The Chinese University of Hong Kong·34 min·Jun 12, 2026
  18. 132
    The Agent Failed — But Did the Instructions Deserve to Be Followed?
    SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinement
    Gautam, Radhakrishna, Gulwani · Microsoft·30 min·Jun 11, 2026
  19. 131
    Why Autonomous Research Agents Forget Their Own Lessons, and Arbor's Fix
    Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
    Jin, Hu, Qiu et al. · Renmin University of China·33 min·Jun 11, 2026
  20. 125
    AI Coding Agents Run a Marathon, and Fewer Than One in Three Finish
    SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?
    Desai, Hu, Cabezas et al. · Abundant·27 min·Jun 09, 2026
  21. 121
    When the Agent Says It's Done But Nothing Happened: Debugging the Harness, Not the Model
    From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws
    Chen, Wang, Liu et al. · Institute of Software·27 min·Jun 05, 2026
  22. 120
    How an AI Agent Rewrites Its Own Tools, Without an Answer Key
    Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts
    Pan, Liu, Lin et al. · City University of Hong Kong·30 min·Jun 05, 2026
  23. 117
    How an Open AI System Verified 672 Hard Math Proofs for Under $300
    Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement
    Chung, Cai, Li et al. · Princeton University·26 min·Jun 05, 2026
  24. 110
    How an Agent Got 44 Points Better by Mining Its Own Scratch Paper
    Inducing Reasoning Primitives from Agent Traces
    Lei, Yan, Momo et al. · Carnegie Mellon University·27 min·Jun 03, 2026
  25. 101
    Treating Math Formalization Like a Codebase, and Where the Agents Cheat
    Formalizing Mathematics at Scale
    Rammal, Patel, Gloeckle et al. · FAIR at Meta / CERMICS·27 min·May 29, 2026
  26. 099
    How an Open-Book Trick Teaches a Model to Catch Its Own Mistakes
    Self-Trained Verification for Training- and Test-Time Self-Improvement
    Wu, Raghunathan · Carnegie Mellon University·21 min·May 29, 2026
  27. 096
    How Treating an AI Agent's Execution Like Git Recovers a Coordination Penalty
    Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace
    Yu, Chong, Nandi et al. · Northeastern University·22 min·May 28, 2026
  28. 088
    Two Levers for Self-Improving AI: When Rewriting Code Isn't Enough
    SIA: Self Improving AI with Harness & Weight Updates
    Hebbar, Manawat, Verboomen et al. · Hexo Labs·25 min·May 27, 2026
  29. 077
    Reading a Model's Confidence Curve to Decide When Chain-of-Thought Is Worth It
    When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions
    Xia, Wang, Tang et al. · State Key Laboratory of General Artificial Intelligence·22 min·May 25, 2026
  30. 075
    Growing Code and Proof Together: Verified Systems in Ten Hours Instead of a Year
    Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems
    Agarwal, Krentsel, Liu et al. · UC Berkeley·28 min·May 25, 2026
  31. 072
    A Robot Made Graphene Without Help, And Caught Itself Hallucinating
    Qumus: Realization of An Embodied AI Quantum Material Experimentalist
    Shi, Zheng, Juan et al. · Princeton University·29 min·May 23, 2026
  32. 071
    When the Model Is Fine and the Plumbing Is Broken: Fixing Agents at the Interface
    Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents
    Xu, Wen, Li · Peking University·23 min·May 22, 2026
  33. 067
    An AI Just Solved a 1996 Erdős Problem—and the Simplest Agent Won
    Advancing Mathematics Research with AI-Driven Formal Proof Search
    Tsoukalas, Kovsharov, Shirobokov et al. · Google DeepMind·31 min·May 22, 2026
  34. 052
    An Old Reinforcement Learning Tradeoff Sneaks Back Into LLM Agents
    Look Before You Leap: Autonomous Exploration for LLM Agents
    Ye, Shi, Liu et al. · University of Science and Technology of China / Meituan·23 min·May 18, 2026
  35. 048
    How a 30B Open Model Reached Olympiad Gold With the Right Recipe
    Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling
    Li, Zhan, Zhang et al. · Shanghai AI Laboratory / The Chinese University of Hong Kong·31 min·May 16, 2026
  36. 046
    When the AI Optimizer Edits the Grade Book: Why Harnessing Evolution Needs a Wall
    Harnessing Agentic Evolution
    Zhang, Gu, Ruan et al. · The Hong Kong University of Science and Technology (Guangzhou) / DeepWisdom·24 min·May 15, 2026
  37. 045
    When a Frontier Model Talks Its Own Twin Into Climate Denial
    LLM-Based Persuasion Enables Guardrail Override in Frontier LLMs
    Nogueira, Almeida, Bonás et al. · Maritaca AI·31 min·May 15, 2026
  38. 029
    Why Forty-Eight Percent on FrontierMath Isn't the Real Story in DeepMind's New Math Paper
    AI Co-Mathematician: Accelerating Mathematicians with Agentic AI
    Zheng, Glehn, Zwols et al. · Google DeepMind·20 min·May 08, 2026
  39. 002
    An AI Ran a Real Optics Lab for 21 Hours and Found a Transformer-Shaped Pattern in Light
    End-to-end autonomous scientific discovery on a real optical platform
    Yang, Chen, Zhao et al. · Zhejiang University·29 min·May 01, 2026

Worth reading next

Papers we haven't done a deep dive on yet, but would recommend on this topic.