Theme · 86 episode(s)

Training Methods

← all concepts

Definition

Training methods is the broad category covering how models actually learn: pretraining objectives, fine-tuning recipes, RL setups, curricula, data mixes. Most capability differences between frontier models come from training methods, not architecture.

Episodes covering this

  1. 206
    How Four-Second Clips Become Hours of Playable AI Soccer
    Multiplayer Interactive World Models with Representation Autoencoders
    · ·15 min·Jul 07, 2026
  2. 200
    The One Mechanism That Turns Twenty AI Clones Into an Actual Team
    EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales
    Zhang, Xu, Dai et al. · Oregon State University; AG2AI·19 min·Jul 04, 2026
  3. 198
    The Model That Knows the Answer and Can't Say It
    Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale
    Gollapudi, Gupta, Singhal et al. · UC Berkeley·17 min·Jul 03, 2026
  4. 197
    Twin Problems Suggest AI Reasoning Gains Are Mostly Better Fact Recall
    IsoSci: A Benchmark of Isomorphic Cross-Domain Science Problems for Evaluating Reasoning versus Knowledge Retrieval in LLMs
    Abdaljalil, Serpedin, Kurban · Texas A&M University·17 min·Jul 03, 2026
  5. 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
  6. 193
    Freeze Most of the Network: Where RL Improvement Actually Lives in a Transformer
    Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training
    Zhang, Hu, Glentis et al. · University of Minnesota·22 min·Jul 02, 2026
  7. 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
  8. 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
  9. 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
  10. 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
  11. 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
  12. 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
  13. 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
  14. 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
  15. 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
  16. 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
  17. 167
    How Teaching an AI to Predict, Not Act, Made It a Better Actor
    Qwen-AgentWorld: Language World Models for General Agents
    Team, Zuo, Xiao et al. · ·27 min·Jun 24, 2026
  18. 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
  19. 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
  20. 163
    Why Training Only on Perfect Solutions Cripples a Model's Reasoning
    Provable Benefits of RLVR over SFT for Reasoning Models: Learning to Backtrack Efficiently
    Wei, Kim · Princeton University·22 min·Jun 23, 2026
  21. 161
    A Robot That Plays Before You Give It a Job, And Why That Beats Retrying
    Playful Agentic Robot Learning
    Zhang, Ge, Yoo et al. · University of California·19 min·Jun 19, 2026
  22. 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
  23. 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
  24. 156
    Why More Human Demonstrations Made a Computer-Use Agent Worse
    ProCUA-SFT Technical Report
    Jung, Lu, Cui et al. · NVIDIA / University of Washington·20 min·Jun 18, 2026
  25. 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
  26. 154
    How a 7B Model Out-Investigates a 72B One by Choosing What to Look At
    Native Active Perception as Reasoning for Omni-Modal Understanding
    Xing, Xu, Wang et al. · The Chinese University of Hong Kong·21 min·Jun 18, 2026
  27. 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
  28. 148
    Why Letting an AI Watch Its Own Scoreboard Can Quietly Overwrite Its Safety
    Greed Is Learned: Visible Incentives as Reward-Hacking Triggers
    Che, Wu · NVIDIA Research·26 min·Jun 16, 2026
  29. 145
    Building Forgetting Into a Language Model With One Extra Line of Code
    Natively Unlearnable Large Language Models
    Ghosal, Maini, Raghunathan · Carnegie Mellon University·22 min·Jun 15, 2026
  30. 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
  31. 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
  32. 128
    How a Model Can Earn Full Reward and Still Resist Training
    Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization
    Xiao, Phuong · California Institute of Technology·29 min·Jun 11, 2026
  33. 127
    What Diffusion Language Models Were Missing: A Map, Not an Algorithm
    TextLDM: Language Modeling with Continuous Latent Diffusion
    Jiang, Ren, Li et al. · JoyFuture Academy / HIT·30 min·Jun 11, 2026
  34. 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
  35. 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
  36. 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
  37. 116
    Why Streaming Half a Reasoning Chain Beats Sending the Whole Thing
    Streaming Communication in Multi-Agent Reasoning
    Yang, Xu, Wang et al. · HKUST (GZ)·26 min·Jun 04, 2026
  38. 115
    Teaching a Phone Agent to Reason Silently, And Keeping It Honest
    MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models
    Yang, Hu, Hao et al. · Beihang University·24 min·Jun 04, 2026
  39. 114
    Agents That Rewrite Their Own Weights Instead of Just Taking Notes
    Scaling Self-Evolving Agents via Parametric Memory
    Ren, Luo, Yang et al. · Peking University / Alibaba Group·26 min·Jun 04, 2026
  40. 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
  41. 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
  42. 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
  43. 108
    The Reasoning Cliff: Why Thinking Longer Makes Models Worse at Exact Step-by-Step Tasks
    The Deterministic Horizon: When Extended Reasoning Fails and Tool Delegation Becomes Necessary
    Guo, Wu, Yiu · The University of Hong Kong·32 min·Jun 03, 2026
  44. 107
    How a Market of Crippled AI Agents Outscored One Unrestricted Model
    Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions
    Qi, Su, Qu et al. · Harvard·26 min·Jun 03, 2026
  45. 106
    Giving Agents a Notebook Instead of New Weights: How ExpGraph Lets Frozen Models Learn
    ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents
    Feng, Ye, Luo et al. · University of Illinois Urbana-Champaign·26 min·Jun 02, 2026
  46. 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
  47. 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
  48. 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
  49. 085
    Why Long-Context Models Might Need Compute, Not Capacity, Before Eviction
    Language Models Need Sleep
    Lee, McLeish, Goldstein et al. · Carnegie Mellon University·24 min·May 26, 2026
  50. 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
  51. 083
    Training the Translator: How a Small Communication Model Lets Agent Teams Outperform Themselves
    AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning
    Hu, Qian, Wang et al. · GSAI·24 min·May 26, 2026
  52. 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
  53. 081
    When Reasoning Models Decide Before They Think: Detecting and Fixing Premature Confidence
    Understanding and Mitigating Premature Confidence for Better LLM Reasoning
    Gai, Zeng, Baek et al. · Carnegie Mellon University·25 min·May 26, 2026
  54. 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
  55. 079
    An Old Idea From Cognitive Psychology Reshapes How We Reward Reasoning Models
    Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
    Chen, Xu, Zhao et al. · Tongji University / Shanghai AI Laboratory / Nanyang Technological University·29 min·May 25, 2026
  56. 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
  57. 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
  58. 074
    How a Fifteen-Hundred-Dollar Training Run Matched Llama and Gemma on Reasoning
    HRM-Text: Efficient Pretraining Beyond Scaling
    Wang, Liu, Wang et al. · Sapient Intelligence·21 min·May 24, 2026
  59. 066
    Why Giving an AI Agent More Tools Can Make It Worse at Using a Computer
    ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
    Hu, Zhang, Xu et al. · Tongyi Lab·26 min·May 22, 2026
  60. 065
    One Loop to Optimize Them All: A Universal API for LLM-Driven Discovery
    optimize_anything: A Universal API for Optimizing any Text Parameter
    Agrawal, Lee, Tan et al. · UC Berkeley·27 min·May 22, 2026
  61. 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
  62. 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
  63. 059
    Firefly's Inversion: Building Verified Tool-Call Training Data by Working Backward
    Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs
    Lu, Wang, Lu et al. · Northeastern University·22 min·May 20, 2026
  64. 053
    An AI Agent Swapped In Focal Loss And Beat A Human-Tuned Training Script
    Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design
    Pepe, Lin, Magka et al. · FAIR at Meta·32 min·May 18, 2026
  65. 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
  66. 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
  67. 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
  68. 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
  69. 043
    When 'This Is False' Doesn't Stick: Why Models Learn the Lie Anyway
    Negation Neglect: When models fail to learn negations in training
    Mayne, McKinney, Dubiński et al. · University of Oxford·18 min·May 14, 2026
  70. 042
    An Agentic Scientific Computing System That Actually Remembers What It Learns
    GRAFT-ATHENA: Self-Improving Agentic Teams for Autonomous Discovery and Evolutionary Numerical Algorithms
    Toscano, Chai, Karniadakis · Division of Applied Mathematics·30 min·May 13, 2026
  71. 041
    When the Iteration Teaches the Model to Skip the Iteration
    Solve the Loop: Attractor Models for Language and Reasoning
    Fein-Ashley, Rashidinejad · University of Southern California·30 min·May 13, 2026
  72. 040
    Two Frozen Models Learn to Whisper: Coupling Through Hidden States
    The Bicameral Model: Bidirectional Hidden-State Coupling Between Parallel Language Models
    Flamant, Ghai, Shimizu · AWS Agentic AI·29 min·May 13, 2026
  73. 036
    Sparse Attention Was the Wrong Frame. Treat It as Geometry Instead.
    Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache
    Dehghankar, Asudeh · University of Illinois Chicago·24 min·May 11, 2026
  74. 033
    Echo: The Paper Arguing You Never Needed a KV Cache for Retrieval
    Echo: KV-Cache-Free Associative Recall with Spectral Koopman Operators
    Sridhar, Johansen · California·24 min·May 11, 2026
  75. 032
    A Sticky-Note for Every Layer: Letting Transformers Remember What They Were Just Thinking
    State Stream Transformer (SST) V2: Parallel Training of Nonlinear Recurrence for Latent Space Reasoning
    Aviss · Fifth Dimension·23 min·May 09, 2026
  76. 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
  77. 026
    What RL Actually Does to Language Models, at the Token Level
    Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning
    Akgül, Kannan, Neiswanger et al. · University of Southern California·24 min·May 08, 2026
  78. 025
    The Missing Gradient Term That Predicts Sycophancy in RLHF
    Explaining and Preventing Alignment Collapse in Iterative RLHF
    Gauthier, Bach, Jordan · Inria·22 min·May 07, 2026
  79. 022
    Training the Model Spec Directly: An Alignment Lever Aimed at the Say-Do Gap
    Model Spec Midtraining: Improving How Alignment Training Generalizes
    Li, Price, Marks et al. · Anthropic Fellows Program·32 min·May 06, 2026
  80. 021
    Ten Thousand Examples Beat the Full Industrial Pipeline for Search Agents
    OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories
    Du, Ye, Tang et al. · Shanghai Jiao Tong University·14 min·May 06, 2026
  81. 019
    When the Best Reward Model Trains the Worst Policy: Inside EvoLM
    EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics
    Li, Xin, Xiao et al. · University of Washington·26 min·May 06, 2026
  82. 013
    Why Search Keeps Rediscovering the Same Workflow, and What That Means
    Why Search When You Can Transfer? Amortized Agentic Workflow Design from Structural Priors
    Du, Liu, Du et al. · Carnegie Mellon University·22 min·May 03, 2026
  83. 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
  84. 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
  85. 009
    How Two Silent Library Bugs Quietly Invalidated a Wave of Reasoning Papers
    SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
    Limozin, Durech, Hoefler et al. · ETH AI Center·23 min·May 02, 2026
  86. 003
    How to Pick the Best of Sixteen Coding Agent Rollouts
    Scaling Test-Time Compute for Agentic Coding
    Kim, Yang, Niu et al. · Meta Superintelligence Labs / University of Washington·17 min·May 01, 2026

Worth reading next

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