ConflictGuide: AutoResearch Improves When Competing Behaviors Are Made Visible
cs.AI, cs.LG
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/karpathy/autoresearch
Sources
- Physics-Audited Agentic Discovery in Scientific Machine Learning
- AIDE: AI-Driven Exploration in the Space of Code
- Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback
- AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery
- AgentFold: Closed-Loop Agentic Search for Protein Folding Model Design
- NOVA: A Verification-Aware Agent Harness for Architecture Evolution in Industrial Recommender Systems
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Toward a Better Understanding of Fourier Neural Operators from a Spectral Perspective
- Factorized Fourier Neural Operators
- LLaMEA-SAGE: Guiding Automated Algorithm Design with Structural Feedback from Explainable AI
- Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
- ASI-Evolve: AI Accelerates AI
- EvoPINN: Agentic Discovery of Executable Algorithms for Physics-Informed Neural Networks
- Automated Researchers Can Mitigate Well-characterized Alignment Failures
- Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents
- AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents
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