Concept · 33 episode(s)

Supervised Fine-Tuning

← all concepts

Definition

SFT (Supervised Fine-Tuning) trains a pretrained model on (input, target output) pairs to teach a specific behavior or format. It’s the simplest post-training method and the first step in most modern alignment pipelines before any RL.

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. 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
  5. 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
  6. 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
  7. 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
  8. 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
  9. 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
  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. 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
  12. 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
  13. 141
    How Two Tokens Reopened a Reasoning Method the Field Had Given Up On
    Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning
    Yang, Chen, Wu et al. · HKUST(GZ)·29 min·Jun 12, 2026
  14. 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
  15. 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
  16. 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
  17. 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
  18. 091
    When Better Fine-Tuning Can't Help: A Geometric Impossibility in LLM Causal Reasoning
    Why LLMs Fail at Causal Discovery and How Interventional Agents Escape
    Roy, Parbhoo · SIRE·24 min·May 28, 2026
  19. 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
  20. 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
  21. 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
  22. 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
  23. 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
  24. 070
    When Models Know the Answer But Say the Wrong Thing Anyway
    Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer
    Yeom, Sok, Kim et al. · Graduate School of Data Science·22 min·May 22, 2026
  25. 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
  26. 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
  27. 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
  28. 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
  29. 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
  30. 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
  31. 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
  32. 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
  33. 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

Worth reading next

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