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

Published
Source
arXiv
Paper number
1463
Field
Agents
arXiv ID
2611.17041

Key points

  • The authors target the problem that training only the main agent or broadcasting the same team advantage to all agents can reward misleading subagent reports and penalize useful ones.
  • LEAD-RL uses a training-time rubric to evaluate the research utility of each subagent report and gates its inherited team advantage.
  • Helpful reports retain only positive team advantages, and harmful reports retain only negative ones.
  • Final-answer correctness remains the only team reward, with no token, step, or speedup reward used.
  • On BrowseComp, LEAD-RL improves accuracy by 2.49 percentage points and reduces critical-path cost by 24.5% over joint training with shared team credit.
  • It reaches 73.5% accuracy on BrowseComp with a 124B-A5.1B model, outperforming the more than twice larger DeepSeek V4 Flash.

Paper links

External research summaries. These are not HDATF publications or measured product results.

Read original (opens in a new tab)