Component-Aware Feedback for Self-Evolving Programs
cs.AI, cs.IR
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/codelion/openevolve
Sources
- TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy
- DeltaEvolve: Accelerating Scientific Discovery through Momentum-Driven Evolution
- LLMs Get Lost In Multi-Turn Conversation
- ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
- EvoX: Meta-Evolution for Automated Discovery
- JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!
- Rank1: Test-Time Compute for Reranking in Information Retrieval
- A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems