Research
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.
multi-agent systemsreinforcement learningLLM agents