Skip to main content
Search

Zixu Wang

1 related articles

Subscribe to updates
  1. arXiv

    Multi-agent chat no longer collapses to one score: OPSD4MAS turns future replies into token-level credit, lifting math pass@4 by up to 20 points

    Multi-agent reinforcement learning has compressed inter-agent dialogue into scalar rewards, which say whether to reinforce a response but not which tokens to revise. OPSD4MAS extracts facts from later communication, ranks them by association and screens them with leave-one-out testing to form privileged context, then compares token probabilities for the same policy with and without those facts to obtain token-level credit, trained jointly with GRPO under linear annealing. Across six math benchmarks, the variant using a four-response future window raises mean pass@1 and pass@4 over GRPO by 8.87 and 9.54 percentage points, with single-point pass@4 gains up to 20.00 points.

You’re all caught up