CoEvo: Oracle-Grounded Self-Evolution of a Single Model for Multi-Step Causal Reasoning
cs.LG
Submitted: 2026-08-18
Updated: 2026-08-18
Comments: 9 pages, 2 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Training Language Models to Win Debates with Self-Play Improves Judge Accuracy
- Self-Evolving Curriculum for LLM Reasoning
- Multi-Agent Evolve: LLM Self-Improve through Co-evolution
- Distilling the Knowledge in a Neural Network
- R-Zero: Self-Evolving Reasoning LLM from Zero Data
- AI safety via debate
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Solving math word problems with process- and outcome-based feedback
- Benchmarking Multi-Step Legal Reasoning and Analyzing Chain-of-Thought Effects in 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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks