ProofGrid is a new benchmark for LLM reasoning that uses machine-checkable proofs in minimal formal notation, revealing progress on basic tasks but major gaps in complex combinatorial and synthesis reasoning.
Advances in Neural Information Processing Systems , year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LPSR raises 8B-model accuracy on MATH-500 from 28.8% to 44.0% by detecting error-indicating phase shifts in the residual stream and correcting via KV-cache rollback plus steering vectors, outperforming prompted self-correction and even a 70B model.
citing papers explorer
-
Stress-Testing the Reasoning Competence of LLMs With Proofs Under Minimal Formalism
ProofGrid is a new benchmark for LLM reasoning that uses machine-checkable proofs in minimal formal notation, revealing progress on basic tasks but major gaps in complex combinatorial and synthesis reasoning.
-
Latent Phase-Shift Rollback: Inference-Time Error Correction via Residual Stream Monitoring and KV-Cache Steering
LPSR raises 8B-model accuracy on MATH-500 from 28.8% to 44.0% by detecting error-indicating phase shifts in the residual stream and correcting via KV-cache rollback plus steering vectors, outperforming prompted self-correction and even a 70B model.