Inverse Reasoning Models for Efficient Post-Training and Verification from Answer-Only Data

arXiv:2610.18878 · cs.LG, cs.AI, stat.ML · Submitted 2026-10-01 · Read on arXiv

cs.LG, cs.AI, stat.ML

Submitted: 2026-10-01

Updated: 2026-10-01

Comments: Published at the COLM 2026 Workshop on Efficient Reasoning

Code: https://github.com/ekorman/dialectic

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Verification — 1× in this paper · explained in 2 episodes

Sources

• Training Verifiers to Solve Math Word Problems
• Stream of Search (SoS): Learning to Search in Language
• Tulu 3: Pushing Frontiers in Open Language Model Post-Training
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Self-Consistency Improves Chain of Thought Reasoning in Language Models
• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• Coupled Variational Reinforcement Learning for Language Model General Reasoning
• Qwen3 Technical Report
• Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

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