AI/ reasoning-models · chain-of-thought · llm-training · math-ai

New Training Method Teaches AI Models to Reason Backward

A new method trains reasoning models to think backward as well as forward, aiming to fix five recurring math-reasoning failure modes.

A new paper argues today's top reasoning models struggle because they only know how to think in one direction.

Researchers studied why models like GPT-o1, GPT-o3, and DeepSeek-R1 still botch math problems despite generating long chains of thought. Analyzing accuracy across multiple problem sets, they identified five recurring failure patterns: models don't cover enough of the solution space, they make computational mistakes, they run with unverified assumptions, they ignore stated constraints, and they simply hit the response-length limit before finishing. Their proposed fix is a backward reasoning pattern, trained using a two-stage easy-to-hard math dataset that pairs each problem with both a forward and a backward solution path. A fine-grained reward system with smoothed signals is meant to stop the model from gaming the reward, while a gradually shifting sampling schedule keeps forward and backward training examples balanced.

Chain-of-thought models have mostly been improved by making them think longer, not differently - more tokens, more steps, same direction every time. This work treats reasoning direction as a choice the model should make for itself, which is a cheaper lever to pull than just throwing more test-time compute at a problem.

The paper reports improved accuracy and efficiency on math proofs, but it doesn't publish head-to-head numbers against the models it critiques, so the real test is whether this holds up outside the benchmark built to showcase it.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →