MASPO jointly optimizes prompts in multi-agent LLM systems via downstream-success evaluation and evolutionary beam search, delivering 2.9 average accuracy gains over prior methods across six tasks.
This validates our hypothesis that in multi-step reasoning chains, the final outcome provides a supervision signal that is too sparse and noisy for intermediate agents
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems
MASPO jointly optimizes prompts in multi-agent LLM systems via downstream-success evaluation and evolutionary beam search, delivering 2.9 average accuracy gains over prior methods across six tasks.