# CoEvo: Oracle-Grounded Self-Evolution of a Single Model for Multi-Step Causal Reasoning

arXiv: https://arxiv.org/abs/2609.26094 · HTML: https://mlsanity.com/paper/2609.26094/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning.
- Builds on 9 of its 38 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Placed in

- LLM reasoning / [Causal reasoning in LLMs](https://mlsanity.com/lr/causal-reasoning-in-llms/)

## Builds on (most cited first, 9 of 9)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [R-Zero: Self-Evolving Reasoning LLM from Zero Data](https://mlsanity.com/paper/2508.05004/) (2025)
- [Self-Evolving Curriculum for LLM Reasoning](https://mlsanity.com/paper/2505.14970/) (2025)
- [Multi-Agent Evolve: LLM Self-Improve through Co-evolution](https://mlsanity.com/paper/2510.23595/) (2025)
- [Training Language Models to Win Debates with Self-Play Improves Judge Accuracy](https://mlsanity.com/paper/2409.16636/) (2024)
- [Benchmarking Multi-Step Legal Reasoning and Analyzing Chain-of-Thought Effects in Large Language Models](https://mlsanity.com/paper/2511.07979/) (2025)

## Abstract (arXiv)

Multi-step causal reasoning requires chaining inferences where each step constrains the next. An early error propagates silently, and a correct answer reached via flawed logic evades outcome-level detection. In specialized domains, teacher LLMs err on intermediate steps, safety constraints restrict cloud distillation, and shifting conditions demand adaptation, leaving self-evolution as the practical route. Naive self-evolution can collapse: outcome-only rewards let the model exploit distributional shortcuts, and weak self-evaluation reinforces spurious paths into stable failure patterns. We exploit a key asymmetry: generating a correct chain is hard, but verifying a single step is easy. Many high-stakes domains admit a deterministic, queryable oracle, a physics simulator or rule engine over codified constraints. It checks asserted steps without teacher-level ability and abstains beyond its rules; it can check what the model asserts, never replace it. This enables CoEvo, an oracle-grounded self-evolution framework where a single model alternates between Proposer and Solver. As Solver, the model generates competing chains; intra-group debate exposes disagreement steps, a proxy for the capability boundary, and the oracle adjudicates them into process-level supervision. As Proposer, the same model constructs progressively harder scenarios inside oracle constraints, steering the curriculum toward deep multi-hop chains. Both roles are updated jointly, so training pressure co-evolves with the model. On industrial, clinical, and legal multi-step causal reasoning benchmarks, CoEvo enables an 8B LLM to sustain self-evolution, surpassing distillation baselines and the strongest proprietary reference on path correctness (82.1% vs. 71.4%). The trained model generalizes to unseen categories and systems, preserving root-cause accuracy.