HERA evolves query-specific agent topologies via reward-guided sampling and refines role-specific prompts via credit assignment, yielding 38.69% average gains on six knowledge-intensive benchmarks.
Hanlin Zhou and Huah Yong Chan
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2roles
baseline 1polarities
baseline 1representative citing papers
A critic-guided heterogeneous multi-agent LLM framework improves GSM8K math reasoning accuracy by up to 13% and enables smaller models to match larger ones via feedback loops.
citing papers explorer
-
Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts
HERA evolves query-specific agent topologies via reward-guided sampling and refines role-specific prompts via credit assignment, yielding 38.69% average gains on six knowledge-intensive benchmarks.
-
Critic-Guided Heterogeneous Multi-Agent Reasoning for Reliable Mathematical Problem Solving
A critic-guided heterogeneous multi-agent LLM framework improves GSM8K math reasoning accuracy by up to 13% and enables smaller models to match larger ones via feedback loops.