MIT CSAIL paper: LM harnesses act as compositional generalizers during RL training
lateinteraction · x · 2026-11-21
A new MIT CSAIL paper by Alex Zhang, Souradip Chakraborty and Omar Khattab, "LM Harnesses are Compositional Generalizers," pushes back on the assumption that RL naturally generalizes — generalization depends on learned representations that may not transfer. By programmatically managing context so every individual LM call stays locally in-distribution (LID), harnesses let RL learn reusable decomposition strategies that compose existing capabilities to solve unseen tasks, generalizing over task length, strategy, and recursive depth while making long-task training more data-efficient. The takeaway: harnesses are not inference-time scaffolding but deeply intertwined with model learning, and agent training should be designed accordingly.
Related event: MIT Paper: LM Harnesses Are Compositional Generalizers, Not Crutches(10 posts)→
More from coding & agent
- Grok Bot Gets Its Own Email Addresses to Sign Up and Handle Promos for You — elonmusk · 2026-11-21
- CapCut × ChatGPT plugin turns chat into a video generator and editor — SimplyAnnisa · 2026-11-21
- Dev builds daily X-digest Grok bot that auto-blocked 19 reply bots, heading to marketplace — petergyang · 2026-11-21
- DeepMind's Antigravity Robotics Plugin: 2 Prompts, ~20 Minutes to Command a Real FR3 Duo Arm — jackyliang42 · 2026-11-21
- Asking Astra 6.2 to Review Code Written by Opus 5.5 Yields Almost Nothing — rickasaurus · 2026-11-21
- Security & Web3 Firewall MCP Server Hits Official Registry: Detects Tool-Poisoning and Rug-Pull Drift — ezelech · 2026-11-21