TheoremGraph builds a unified statement-level dependency graph across informal arXiv math and formal Lean code via parsing, embeddings, and LLM validation, releasing the data and APIs for search and retrieval.
G1: Teaching llms to reason on graphs with reinforcement learning
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
GraphScout trains LLMs to autonomously synthesize structured training data from knowledge graphs via flexible exploration tools, enabling a 4B model to outperform larger LLMs by 16.7% on average with fewer inference tokens and strong cross-domain transfer.
RL training compute for logical reasoning follows a power law with horizon depth whose exponent rises with logical expressiveness, yielding better downstream transfer when models train on richer logics.
A survey of LLMs for graph computation introduces a role-based taxonomy of executors versus planners and concludes that current models suit simple small-scale tasks but remain unreliable for large-scale exact computation.
Graphs can help LLMs reduce hallucinations, boost reasoning via prompting techniques, and better process structured data.
citing papers explorer
-
TheoremGraph: Bridging Formal and Informal Mathematics
TheoremGraph builds a unified statement-level dependency graph across informal arXiv math and formal Lean code via parsing, embeddings, and LLM validation, releasing the data and APIs for search and retrieval.
-
GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning
GraphScout trains LLMs to autonomously synthesize structured training data from knowledge graphs via flexible exploration tools, enabling a 4B model to outperform larger LLMs by 16.7% on average with fewer inference tokens and strong cross-domain transfer.
-
Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
RL training compute for logical reasoning follows a power law with horizon depth whose exponent rises with logical expressiveness, yielding better downstream transfer when models train on richer logics.
-
Are Large Language Models Suitable for Graph Computation? Progress and Prospects
A survey of LLMs for graph computation introduces a role-based taxonomy of executors versus planners and concludes that current models suit simple small-scale tasks but remain unreliable for large-scale exact computation.
-
Position: How can Graphs Help Large Language Models?
Graphs can help LLMs reduce hallucinations, boost reasoning via prompting techniques, and better process structured data.