Janus: An Algorithm-Evaluator Co-Evolution Framework for LLM-Driven Discovery under Expensive Evaluation Budgets
Ximeng Liu, Qianlong Wang, Yingming Mao, Annan Li, Yatao Li, Shizhen Zhao, Jianmin Wu, Dawei Yin, Dou Shen
cs.AI
Submitted: 2026-08-08
Updated: 2026-08-11
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Large Language Model-Driven Surrogate-Assisted Evolutionary Algorithm for Expensive Optimization
- Beyond Static Evaluation: Co-Evolutionary Mechanisms for LLM-Driven Strategy Evolution in Adversarial Games
- Game-Theoretic Co-Evolution for LLM-Based Heuristic Discovery
- Self-Evolving Deep Research via Joint Generation and Evaluation
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