Splicing Hints into Reasoning Traces: Learning from Demonstrator Failures

arXiv:2610.13996 · cs.LG, cs.AI · Submitted 2026-09-26 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-09-26

Updated: 2026-09-26

Code: https://github.com/aw31/openaiimo-2025-proofs

Terminology

• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Constitutional AI: Harmlessness from AI Feedback
• Early science acceleration experiments with GPT-5
• Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks
• Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving
• Training Verifiers to Solve Math Word Problems
• Escaping the Cognitive Well: Efficient Competition Math with Off-the-Shelf Models
• DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• The Open Proof Corpus: A Large-Scale Study of LLM-Generated Mathematical Proofs
• RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment
• Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
• Reinforced Self-Training (ReST) for Language Modeling
• LatentRevise: Learning from Zero-Hit Reasoning
• SPIRAL: Learning to Search and Aggregate
• GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements
• Measuring Mathematical Problem Solving With the MATH Dataset
• Distilling the Knowledge in a Neural Network
• Large Language Models Cannot Self-Correct Reasoning Yet
• Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline
• OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks