Theme · 35 episode(s)

Agentic RL

← all concepts

Definition

Agentic RL applies reinforcement learning directly to multi-step, tool-using agent trajectories, training the model to take sequences of actions that lead to rewarded outcomes. It generalizes RLHF beyond single-turn responses, and brings classic RL headaches — credit assignment, exploration, reward hacking — into the LLM era.

Episodes covering this

  1. 192
    A 32B Open Model Matched Frontier Systems By Learning to Take Notes
    AutoMem: Automated Learning of Memory as a Cognitive Skill
    Wu, Zhu, Zhang et al. · Stanford University·22 min·Jul 02, 2026
  2. 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
  3. 187
    An 8-Billion Agent That Beats Models 80 Times Its Size By Looking Things Up
    An AI agent for treatment reasoning over a biomedical tool universe
    Gao, Noori, Zhu et al. · Department of Biomedical Informatics·19 min·Jun 30, 2026
  4. 186
    How a Frozen Model Went From 2% to 77% on Physics Puzzles — Without Retraining
    Hierarchical Experimentalist Agents
    Chandra, Vaidyanathan, Dhanuka et al. · University of Massachusetts Amherst·22 min·Jun 30, 2026
  5. 183
    Why You Can't Fine-Tune Foresight Into an AI Agent
    Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning
    Zhang, Zhou, Qiao et al. · Fudan University / Shanghai Innovation Institute / Tencent Youtu Lab·23 min·Jun 29, 2026
  6. 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
  7. 178
    How an AI Reviewer Learned to Stop Going Easy on AI Writing
    The Red Queen Gödel Machine: Co-Evolving Agents and Their Evaluators
    Iacob, Jovanović, Shen et al. · University of Cambridge·23 min·Jun 26, 2026
  8. 175
    One Crosscoder Feature Flips a Stalling Chatbot Into a Working Agent
    Localizing RL-Induced Tool Use to a Single Crosscoder Feature
    Shportko, Bhokare, AlZahrani et al. · Northwestern University·26 min·Jun 26, 2026
  9. 173
    The Free Step-Level Grader Hiding in Every RL Training Run
    Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
    Oh, Li, Park et al. · University of Wisconsin–Madison·22 min·Jun 25, 2026
  10. 166
    A Router That Beats the Frontier Models It Calls
    Sakana Fugu Technical Report
    Tang, Cetin, Xu et al. · Sakana AI·26 min·Jun 23, 2026
  11. 165
    A Free-Lunch Tweak That Lets a Tiny Agent Beat Frontier Giants
    Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning
    Wang, Song, Zhang et al. · Peking University·22 min·Jun 23, 2026
  12. 160
    Training an AI to Take Its Own Notes, So Its Future Self Works Better
    Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning
    Chen, Shi, Xie et al. · Alibaba Group·23 min·Jun 19, 2026
  13. 159
    Can a Coding Agent Run Its Own Robot Experiments Overnight, With No Human Resetting the Scene?
    ENPIRE: Agentic Robot Policy Self-Improvement in the Real World
    Xiao, Xie, Zhang et al. · NVIDIA·23 min·Jun 19, 2026
  14. 147
    Agents Fail at the Body, Not the Brain: A Self-Rewriting Scaffold That Lifts a 9B Model 44 Points
    HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
    Chen, Lu, Zhao et al. · ·30 min·Jun 15, 2026
  15. 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
  16. 126
    How Coding Agents Can Mine Their Own Failures Into a Self-Targeting Curriculum
    Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills
    Xiao, Jiao, Wang et al. · Shanghai Jiao Tong University·21 min·Jun 09, 2026
  17. 119
    Beating Reinforcement Learning Without Ever Touching the Model's Weights
    Agentic Monte Carlo: Simulating Reinforcement Learning for Black-Box Agents
    Hwang, Suri, Villecroze et al. · Layer6 AI·22 min·Jun 05, 2026
  18. 111
    How a 4B Web Agent Beat Models 60x Its Size on 500 Demonstrations
    OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
    Yang, Wu, Chen et al. · UIUC·24 min·Jun 03, 2026
  19. 109
    An AI Got Caught Reading the Answer Key, And Why That Catch Matters
    EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
    Chen, Shi, Li et al. · Shenzhen Institutes of Advanced Technology·28 min·Jun 03, 2026
  20. 090
    How MiniMax-M2 Bets That Sparsity Plus Verifiable Rewards Can Match Frontier Agents
    The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
    MiniMax · MiniMax·28 min·May 27, 2026
  21. 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
  22. 084
    Terminal Agents Get Free Supervision From The Tokens We've Been Throwing Away
    ECHO: Terminal Agents Learn World Models for Free
    Shrivastava, Kauffmann, Awadallah et al. · Microsoft Research·26 min·May 26, 2026
  23. 082
    Training a Deep Research Agent on 8,000 Synthetic Tasks: The Rubric Tree Trick
    QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks
    Xie, Lin, Wang et al. · The Ohio State University·31 min·May 26, 2026
  24. 080
    How a Two-Agent Trick Unlocked Large-Scale Training for Computer-Use Agents
    CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents
    Wang, Lu, Wang et al. · The University of Hong Kong·32 min·May 26, 2026
  25. 078
    Training a Markdown File: When LLM Self-Improvement Borrows the Discipline of Neural Net Training
    SkillOpt: Executive Strategy for Self-Evolving Agent Skills
    Yang, Gong, Huang et al. · Microsoft·28 min·May 25, 2026
  26. 068
    The OS Trick That Makes Tree Search Practical for Coding Agents
    DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback
    Dong, He, Hou et al. · Institute of Parallel and Distributed Systems·27 min·May 22, 2026
  27. 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
  28. 064
    When Agent Memory Stops Being a Database and Starts Being a Skill
    Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents
    Ye, Liu, Wang et al. · University of Illinois Urbana-Champaign·30 min·May 22, 2026
  29. 060
    When Splitting One Model Across Three Agents Doubles Its Accuracy
    NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning
    Lu, Fang, Zhong et al. · University of Georgia·26 min·May 20, 2026
  30. 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
  31. 047
    When Agent Benchmarks Lie: The Harness Problem in Open-Source AI
    Orchard: An Open-Source Agentic Modeling Framework
    Peng, Yao, Wu et al. · Microsoft Research·28 min·May 15, 2026
  32. 028
    Teaching a Model to Hire Copies of Itself: Recursive Agent Optimization
    Recursive Agent Optimization
    Gandhi, Chakraborty, Wang et al. · Carnegie Mellon University·23 min·May 08, 2026
  33. 011
    When RL Actually Teaches Agents Something New, And When It Doesn't
    Does RL Expand the Capability Boundary of LLM Agents? A PASS@(k,T) Analysis
    Zhai, Yan, Shao et al. · Fudan University·23 min·May 02, 2026
  34. 010
    When Reward Climbs But Reasoning Goes Generic: Diagnosing Template Collapse in Agentic RL
    RAGEN-2: Reasoning Collapse in Agentic RL
    Wang, Gui, Jin et al. · Northwestern University·22 min·May 02, 2026
  35. 008
    Why Long-Horizon AI Agents Get Stuck, and a Milestone-Based Fix That Helps
    A Subgoal-driven Framework for Improving Long-Horizon LLM Agents
    Wang, Gooding, Hartmann et al. · Google DeepMind·24 min·May 02, 2026

Worth reading next

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