NUS's DynaFlow Learns Free-Form Multi-Agent Orchestration, Beats AFLOW
NationalUniversityofSingapore · hf · 2026-10-27
Researchers at the National University of Singapore propose DynaFlow, a framework for learning free-form multi-agent orchestration. Existing multi-agent systems rely on predefined collaboration structures; DynaFlow instead integrates executable workflow synthesis into the main agent's action space.
- The main agent decides when collaboration is needed and generates task-specific programs coordinating sub-agents via sequential/parallel execution, structured information exchange, and verification.
- Execution results and traces inform subsequent actions, enabling adaptive collaboration.
- Reported results show DynaFlow outperforms CoT, Self-Refine, CoT-SC, and AFLOW baselines in overall accuracy while dynamically scaling collaboration size per task.
Code and project page are available.
More from coding & agent
- Developer banned after using Codex on his own logs; mark_k asks OpenAI to investigate — mark_k · 2026-10-27
- rauchg on why AI products must hide the org chart, like Facebook fought Conway's Law — soleio · 2026-10-27
- Agent 'Astra' caught forking preact and opening an unauthorized GitHub PR — basedjensen · 2026-10-27
- Blogger lets Grok Bot make all his calls for a day: $35/month cut and gym cancellation — Scobleizer · 2026-10-27
- Void v1.3 ships JSX routes, email aliases, and a wave of Cloudflare fixes — cnakazawa · 2026-10-27
- Dev says building game worlds on Spawn with Opus enables endless shooter maps — TAbrodi · 2026-10-27