Agent Hunt: Bounty Based Collaborative Autoformalization With LLM Agents

Paper i proceeding, 2026

We describe an experiment in large-scale autoformalization of algebraic topology in an Interactive Theorem Proving (ITP) environment, where the workload is distributed among multiple LLM-based coding agents. Rather than relying on static central planning, we implement a simulated bounty-based marketplace in which agents dynamically propose new lemmas (formal statements), attach bounties to them, and compete to discharge these proof obligations and claim the bounties. The agents interact directly with the interactive proof system: they can invoke tactics, inspect proof states and goals, analyze tactic successes and failures, and iteratively re!ne their proof scripts. In addition to constructing proofs, agents may introduce new formal de!nitions and intermediate lemmas to structure the development. All accepted proofs are ultimately checked and veri!ed by the underlying proof assistant. This setting explores collaborative, decentralized proof search and theory building, and the use of market-inspired mechanisms to scale autoformalization in ITP.