Hierarchical Experimentalist Agents

arXiv:2606.29315 · cs.AI, cs.LG · Submitted 2026-06-28 · Read on arXiv

cs.AI, cs.LG

Submitted: 2026-06-28

Updated: 2026-10-09

Terminology

• Benchmark — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes

Sources

• CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
• Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning
• EvoSkill: Automated Skill Discovery for Multi-Agent Systems
• PHYRE: A New Benchmark for Physical Reasoning
• CoPhy: Counterfactual Learning of Physical Dynamics
• Thought Anchors: Which LLM Reasoning Steps Matter?
• PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priors
• CL-bench: A Benchmark for Context Learning
• ToyBox: Better Atari Environments for Testing Reinforcement Learning Agents
• Retrieval-Augmented Generation for Large Language Models: A Survey
• Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
• Open-Endedness is Essential for Artificial Superhuman Intelligence
• VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
• Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models
• In-context Reinforcement Learning with Algorithm Distillation
• Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale
• Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
• SkillNet: Create, Evaluate, and Connect AI Skills
• SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

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