Back to AI News
arxiv

From Delegation to Coordination: Learning Efficient Multi-Agent Deep Research

The paper introduces LEAD-RL, a joint main-agent/subagent training framework for multi-agent deep-research systems that uses contribution-aware credit assignment. A training-time rubric scores the research utility of each subagent report and gates its inherited team advantage, while final-answer correctness remains the only team reward. Across five benchmarks and two model families, LEAD-RL improves answer quality; on BrowseComp it raises accuracy by 2.49 percentage points and cuts critical-path cost by 24.5% versus joint training with shared team credit. Validation showed a 6.78-point accuracy gain at roughly constant critical-path cost.

AI Brief

It offers a concrete training method for making multi-agent deep-research systems both more accurate and cheaper, with measured gains reported across multiple benchmarks.

arXiv:2611.17041v1 Announce Type: cross Abstract: Multi-agent deep-research systems use delegation to parallelize search and keep long tool traces out of the main agent's context. Yet delegation helps only when task allocation and subtask execution are coordinated: the main agent must issue useful subtasks, while subagents must return reliable evidence. Existing training either optimizes only the main agent or broadcasts the same team advantage to all agents, which can reward misleading subagent reports and penalize useful ones. We introduce LEAD-RL (Learning Effective Agent Delegation with Reinforcement Learning), a joint main-agent-subagent training framework with contribution-aware credit assignment. A training-time rubric evaluates the research utility of each subagent report and gates its inherited team advantage, while final-answer correctness remains the only team reward; no token, step, or speedup reward is used. Across five benchmarks and two model families, LEAD-RL improves answer quality. On BrowseComp, it improves accuracy by 2.49 percentage points and reduces critical-path cost by 24.5% over joint training with shared team credit. During validation, accuracy increases by 6.78 points at approximately constant critical-path cost. These results show that contribution-aware credit assignment improves the quality-efficiency trade-off of multi-agent deep research.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!