GraphReAct enables step-by-step graph inference by combining topological and semantic retrieval actions with context refinement in an LLM reasoning-acting loop, outperforming prior methods on six benchmarks.
Automatic chain of thought prompting in large language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
MANGO optimizes multi-agent LLM workflows via flow networks, RL, and textual gradients, delivering up to 12.8% higher performance and 47.4% better efficiency while generalizing to new domains.
citing papers explorer
-
GraphReAct: Reasoning and Acting for Multi-step Graph Inference
GraphReAct enables step-by-step graph inference by combining topological and semantic retrieval actions with context refinement in an LLM reasoning-acting loop, outperforming prior methods on six benchmarks.
-
Reinforced Collaboration in Multi-Agent Flow Networks
MANGO optimizes multi-agent LLM workflows via flow networks, RL, and textual gradients, delivering up to 12.8% higher performance and 47.4% better efficiency while generalizing to new domains.