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.
Graph attention networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
baseline 1polarities
baseline 1representative citing papers
HeterSEED decouples semantics from structure in heterogeneous graphs under heterophily using separate channels and adaptive fusion, proving higher expressiveness and lower bias than standard HGNNs while outperforming baselines on large graphs.
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.
-
HeterSEED: Semantics-Structure Decoupling for Heterogeneous Graph Learning under Heterophily
HeterSEED decouples semantics from structure in heterogeneous graphs under heterophily using separate channels and adaptive fusion, proving higher expressiveness and lower bias than standard HGNNs while outperforming baselines on large graphs.