DisCo distills GitHub repos into agent skills, doubling MLE-bench to 72.89%
rohanpaul_ai · x · 2026-09-06
The DisCo paper argues agents waste effort rediscovering operational know-how — which tool to use, how to set it up, how to recover from failures.
- Approach: distill GitHub repos and papers into compact, verified reusable skills, both task-agnostic (a general library) and task-oriented.
- Scale: the AREX-Skill Library holds 5,353 skills from 1,000 widely used ML repos, organized into 20 areas and 178 capability families.
- Results: with the GPT-5.5 backbone, harness, and execution budget fixed, MLE-bench jumps from 31.11% to 72.89% (+134.3%), PaperBench +34.4%, with FrontierCS and PassNet improving too.
Takeaway: better agents may come from teaching proven workflows, not just scaling the underlying model.
More from coding & agent
- SurfSense: an open-source local NotebookLM with MCP agents and a prompt-caching lesson — FurtiveMirth · 2026-10-23
- procedural-memory: let agents replay saved tool-call sequences instead of re-solving tasks — Sad-Response1560 · 2026-10-23
- Med student seeking whole-library book search: Cognee's graph memory beats plain RAG so far — shrike293103 · 2026-10-23
- Dev demos AI models handling 3D objects and animations surprisingly well — chongdashu · 2026-10-23
- Jason Kneen burns 104.56B tokens and $24.7K in 304 days of AI coding on Codex and Claude Code — jasonkneen · 2026-10-23
- Typosquatted Blender MCP Repo Hit 958 Stars in Days and Silently Ran Malware — Promptmethus · 2026-10-23