CollabFlow：智能体协作的递归自我改进系统

View PDF HTML (experimental)

Abstract:Recursive self-improvement (RSI) lets a system improve from its own outcomes; in LLM-based multi-agent systems, Agents refine one another within a task, and outcomes improve how they collaborate across tasks. However, existing multi-agent collaboration leaves this loop open: collaboration is pre-defined at the operator level, topology-only learning keeps verbatim exchange that propagates errors, and reward maximization on a system's own outcomes concentrates on a few teams. To address these challenges, we propose CollabFlow, an RSI system of Learned Agent Collaboration: a trainable Collab-Director constructs teams of complete Agents, a frozen executor runs them, and each round's outcomes retrain the director. Within each round, the edges of a collaboration graph carry protocols of Evidence-Conditioned Communication: a receiver adopts a differing answer only when the sender's evidence is stronger by a margin, so the director learns who communicates and how. Across rounds, we further propose Collaborative Trajectory Balance (CTB), a flow-based objective that credits each team once across its construction orders and targets a reward-proportional distribution over teams, so several good teams stay in play. We also bound how far this self-generated target moves between rounds, which shrinks as records accumulate. On twelve datasets, CollabFlow outperforms all baselines and keeps improving across rounds. Code is available at this https URL.

Subjects:	Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2609.38662 [cs.MA]
	(or arXiv:2609.38662v2 [cs.MA] for this version)
	https://doi.org/10.48550/arXiv.2609.38662 arXiv-issued DOI via DataCite

Submission history

From: Mingda Zhang [view email]
[v1] Tue, 29 Sep 2026 23:39:03 UTC (776 KB)
[v2] Fri, 16 Oct 2026 05:03:03 UTC (777 KB)