Direct Self-Evolving Optimization: Evolving LLMs without Challenger Training
cs.LG, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- Training Verifiers to Solve Math Word Problems
- Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
- OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
- Measuring Mathematical Problem Solving With the MATH Dataset
- R-Zero: Self-Evolving Reasoning LLM from Zero Data
- BIG-Bench Extra Hard
- Evolving Deeper LLM Thinking
- Solving Quantitative Reasoning Problems with Language Models
- Let's Verify Step by Step
- Large Language Models as Agents in Two-Player Games
- SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines
- Self-Refine: Iterative Refinement with Self-Feedback
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Reflexion: Language Agents with Verbal Reinforcement Learning
- Self-Instruct: Aligning Language Models with Self-Generated Instructions
- MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
- Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning
- WizardLM: Empowering large pre-trained language models to follow complex instructions
- Tree of Thoughts: Deliberate Problem Solving 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