ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents

arXiv:2609.17523 · cs.AI, cs.CL · Submitted 2026-09-15 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-09-15

Updated: 2026-09-15

Comments: Website: http://science-buddy.io, Code: https://github.com/Gen-Verse/ScienceBuddy-RSI

Code: https://github.com/Gen-Verse/ScienceBuddy-RSI

Project page: http://science-buddy.io

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adaptation — 40× in this paper · explained in 1 episode
• Accuracy — 23× in this paper · explained in 1 episode
• Reinforcement Learning — 14× in this paper · explained in 4 episodes
• GRPO — 8× in this paper · explained in 6 episodes
• Trace — 5× in this paper · explained in 2 episodes
• Agent Harness — 4× in this paper · explained in 2 episodes
• Agentic Reasoning — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Verifier — 3× in this paper · explained in 2 episodes
• Continual Learning — 2× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Agent Skills — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
• AgentRx: Diagnosing AI Agent Failures from Execution Trajectories
• AdaRubric: Task-Adaptive Rubrics for Reliable LLM Agent Evaluation and Reward Learning
• Environment Evolution for Terminal Agents
• Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
• SIA: Self Improving AI with Harness & Weight Updates
• LAB-Bench: Measuring Capabilities of Language Models for Biology Research
• Meta-Harness: End-to-End Optimization of Model Harnesses
• Adaptive Prompt Structure Factorization: A Framework for Self-Discovering and Optimizing Compositional Prompt Programs
• SkillGen: Verified Inference-Time Agent Skill Synthesis
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Fantastic Scientific Agents and How to Build Them: AgentBuild for Rietveld Refinement
• Reflexion: Language Agents with Verbal Reinforcement Learning
• Executable Code Actions Elicit Better LLM Agents
• OpenClaw-RL: Train Any Agent Simply by Talking
• RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System
• PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents
• SkillOpt: Executive Strategy for Self-Evolving Agent Skills
• ReAct: Synergizing Reasoning and Acting in 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
• 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
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection