Meta-reasoning harness hits 71.5% on ProgramBench, beating Codex by 13.5 points

anirudhg9119 · x · 2026-10-01

A new arXiv paper, Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning, from Paras Dahal, Anirudh Goyal and colleagues (including Taco Cohen, Rob Fergus, Jason Weston, Ruslan Salakhutdinov) proposes agentic meta-reasoning — an inference-time harness that makes execution control an explicit reasoning process.

Related event: Meta Proposes Agentic Meta-Reasoning for Self-Organized Inference Graphs(3 posts)→

Original post →

More from coding & agent

coding & agent channel →