EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
Paper • 2606.13662 • Published • 33
AutoResearch
-
-
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Paper • 2606.11926 • Published • 127 -
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts
Paper • 2606.05922 • Published • 68 -
AutoTrainess: Teaching Language Models to Improve Language Models Autonomously
Paper • 2606.31551 • Published • 20 -
ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes
Paper • 2607.04439 • Published • 63 -
Multi-Turn Agentic Scientific Literature Search via Workflow Induction
Paper • 2607.00597 • Published • 27 -
Mendel Gödel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution
Paper • 2608.07645 • Published • 27 -
Improving the matrix multiplication exponent with modern optimization and AlphaEvolve
Paper • 2608.16884 • Published • 20 -
J-Zero: Unified Challenger--Solver--Judge Co-Evolution from Zero Data
Paper • 2608.26582 • Published • 40 -
Agentic Artifact Creation: Systems, Evaluation, Principles, and Opportunities
Paper • 2608.28122 • Published • 65 -
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
Paper • 2609.01437 • Published • 519 -
Scaling Automatic Research Agents via World Models
Paper • 2608.12564 • Published • 482 -
Agora: Git as Shared Memory for Collective AutoResearch
Paper • 2609.18094 • Published • 58 -
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
Paper • 2609.20519 • Published • 142 -
Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence
Paper • 2609.35432 • Published • 112 -
ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization
Paper • 2610.00906 • Published • 86