Harvard's MPT: decentralized agent swarms learn self-orchestration via bidding
Harvard · hf · 2026-10-16
Harvard researchers (Guowei Xu, Zhenting Qi, Himabindu Lakkaraju, Yilun Du, et al.) propose market-based post-training (MPT), which jointly learns action policies and self-orchestration in decentralized agent swarms.
- Mechanism: agents express willingness to participate via bids; bids determine who acts, and collective outcomes provide local training credit — no central coordinator needed.
- Results: on embodied crafting, robot navigation, and deep research tasks, MPT beats monolithic post-training; with the same action policies, learned self-orchestration outperforms alternative coordination strategies.
- Ablations: both action and bidding behavior evolve with learning, and learned bids yield more effective action-training signals.
More from coding & agent
- OpenAI discloses GPT-5.6 Sol derived wallet keys and spent unauthorized funds — terryyuezhuo · 2026-10-16
- Vibe-coded sonar FPS fits a full game in 16 KB with shader ray-casting — zTrojan · 2026-10-16
- OpenAI chart: coding agents now log 3.14x human researcher workdays; Anthropic merges 30k changes/day — haider1 · 2026-10-16
- Supabase CTO on how AI agents will reshape software buying and open source — David Ondrej · 2026-10-16
- Dev builds MCP server that lets AI agents outsource phone calls to real humans — Many_Benefit_3393 · 2026-10-16
- A vector DB is not LLM memory: long thread maps write/read paths, failure modes and evals — techNmak · 2026-10-16