Cogentic: Multi-Agent Orchestration for Automated Proof Discovery

Paper number
1157
Field
Research

Key points

  • Solved open problems that single-shot generation cannot handle via an iterative prove-verify loop.
  • Accumulated confirmed intermediate results in a permanent ledger so long-horizon work keeps its progress.
  • Produced new results on five open problems in online learning, auction theory, and mechanism design, all independently verified by domain experts.
  • Used adversarial verifiers that start by assuming the proof is wrong, catching flaws in drafts.
  • Runs on a relatively low inference budget of roughly O(100) to O(1000) model calls per problem.

Paper links

External research summaries. These are not HDATF publications or measured product results.

Read original (opens in a new tab)