A neuro-symbolic system using LLM-guided best-first search and Isabelle tools proves up to 77.6% of theorems on the seL4 benchmark, outperforming prior LLM methods and Sledgehammer.
Solving olympiad geometry without human demonstrations.Nature, 625(7995):476–482
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Reinforcement learning with three causal constraints enables multimodal models to internalize diagram-reasoning links in geometry, unlike SFT which only mimics surface format and harms performance.
Agent Cybernetics reframes foundation agent design by adapting classical cybernetics laws into three engineering desiderata for reliable, long-running, self-improving agents.
citing papers explorer
-
Neuro-Symbolic Proof Generation for Scaling Systems Software Verification
A neuro-symbolic system using LLM-guided best-first search and Isabelle tools proves up to 77.6% of theorems on the seL4 benchmark, outperforming prior LLM methods and Sledgehammer.
-
How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning
Reinforcement learning with three causal constraints enables multimodal models to internalize diagram-reasoning links in geometry, unlike SFT which only mimics surface format and harms performance.
-
The Agent Use of Agent Beings: Agent Cybernetics Is the Missing Science of Foundation Agents
Agent Cybernetics reframes foundation agent design by adapting classical cybernetics laws into three engineering desiderata for reliable, long-running, self-improving agents.
- Superposition Yields Robust Neural Scaling