Agentic GraphRAG constructs a Neo4j graph via deterministic structured ingestion plus LLM extraction from notices, then deploys modular agents with tool access and reflection to outperform vector-RAG baselines on Swiss commercial gazette data across entity resolution, answer quality, and multi-turn
React: Synergizing reasoning and acting in language models
3 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
MolReAct uses an LLM agent to dynamically constrain RL action spaces to validated reaction templates, achieving the highest average Top-10 score of 0.571 across 14 drug optimization tasks while providing explicit synthetic pathways.
RelAgent uses an LLM agent to autonomously generate SQL feature programs paired with classical models for interpretable relational learning predictions that execute efficiently on standard databases.
citing papers explorer
-
Agentic GraphRAG: Navigating Unstructured Financial Data with Collaborative AI
Agentic GraphRAG constructs a Neo4j graph via deterministic structured ingestion plus LLM extraction from notices, then deploys modular agents with tool access and reflection to outperform vector-RAG baselines on Swiss commercial gazette data across entity resolution, answer quality, and multi-turn
-
Reinforcement Learning with LLM-Guided Action Spaces for Synthesizable Lead Optimization
MolReAct uses an LLM agent to dynamically constrain RL action spaces to validated reaction templates, achieving the highest average Top-10 score of 0.571 across 14 drug optimization tasks while providing explicit synthetic pathways.
-
RelAgent: LLM Agents as Data Scientists for Relational Learning
RelAgent uses an LLM agent to autonomously generate SQL feature programs paired with classical models for interpretable relational learning predictions that execute efficiently on standard databases.