Market-based Post-Training: decentralized agent swarms learn self-orchestration via bidding, no central coordinator
shangbinfeng · x · 2026-10-21
An arXiv paper (2610.22322) by Guowei Xu, Zhenting Qi, Yilun Du et al. introduces Market-based Post-Training (MPT): agents bid for opportunities to act, and those bids determine who acts and how collective outcomes become individual learning credit. Action policies and self-orchestration are learned jointly without a central coordinator, letting individual capability and cooperation patterns evolve together — a step toward Society-of-Mind-style decentralized agent societies.
More from coding & agent
- How a solo founder hit £100K/month in 95 days with a Claude Code system and zero hires — aakashgupta · 2026-10-21
- Dev hasn't touched his MacBook screen in weeks: agents do everything, iPad is the interface — MarcJSchmidt · 2026-10-21
- Reason Network OSS lets Claude Code, Codex and hosted agents like Grok Bot talk peer-to-peer — AIFlow_ML · 2026-10-21
- Omnigent v0.19 adds MCP gateway, keyless sandbox Git access and SDK reasoning controls — matei_zaharia · 2026-10-21
- Sentry Android SDK is 20-30% faster, saving 6,250 CPU-hours per day — zeeg · 2026-10-21
- mcporter bridges MCP into non-MCP agent harnesses, dev shows on-the-go workflow — steipete · 2026-10-21