# Collaborative Principle Evolution via Evidence Transfer for Scientific Discovery

arXiv: https://arxiv.org/abs/2609.35315 · HTML: https://mlsanity.com/paper/2609.35315/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 57 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 30 of 30)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning](https://mlsanity.com/paper/2409.05556/) (2024)
- [Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions](https://mlsanity.com/paper/2503.08979/) (2025)
- [Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System](https://mlsanity.com/paper/2410.09403/) (2024)
- [DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively](https://mlsanity.com/paper/2509.26603/) (2025)
- [Robin: A multi-agent system for automating scientific discovery](https://mlsanity.com/paper/2505.13400/) (2025)
- [EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery](https://mlsanity.com/paper/2603.08127/) (2026)
- [Evaluating Large Language Models in Scientific Discovery](https://mlsanity.com/paper/2512.15567/) (2025)
- [PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaboration](https://mlsanity.com/paper/2505.15047/) (2025)
- [InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery](https://mlsanity.com/paper/2602.08990/) (2026)
- [DeltaEvolve: Accelerating Scientific Discovery through Momentum-Driven Evolution](https://mlsanity.com/paper/2602.02919/) (2026)
- [Think like a Scientist: Physics-guided LLM Agent for Equation Discovery](https://mlsanity.com/paper/2602.12259/) (2026)
- [AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentation](https://mlsanity.com/paper/2509.25651/) (2025)
- [Debate-Driven Multi-Agent LLMs for Phishing Email Detection](https://mlsanity.com/paper/2503.22038/) (2025)
- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis](https://mlsanity.com/paper/2507.21035/) (2025)
- [How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks](https://mlsanity.com/paper/2608.14905/) (2026)
- [Principle-Evolvable Scientific Discovery via Uncertainty Minimization](https://mlsanity.com/paper/2602.06448/) (2026)
- [Bilevel Autoresearch: Meta-Autoresearching Itself](https://mlsanity.com/paper/2603.23420/) (2026)
- [On Negative Transfer and Structure of Latent Functions in Multi-output Gaussian Processes](https://mlsanity.com/paper/2004.02382/) (2020)
- [EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery](https://mlsanity.com/paper/2606.13662/) (2026)
- [TS-RSR: A provably efficient approach for batch Bayesian Optimization](https://mlsanity.com/paper/2403.04764/) (2024)
- [Safe Bayesian Optimization for the Control of High-Dimensional Embodied Systems](https://mlsanity.com/paper/2412.20350/) (2024)
- [EvoSci: A Bio-Inspired Multi-Agent Framework for the Evolution of Scientific Discovery](https://mlsanity.com/paper/2605.24018/) (2026)
- [Randomized Kriging Believer for Parallel Bayesian Optimization with Regret Bounds](https://mlsanity.com/paper/2603.01470/) (2026)
- [Cultivating Archipelago of Forests: Evolving Robust Decision Trees through Island Coevolution](https://mlsanity.com/paper/2412.13762/) (2024)
- [Bayesian Optimization of a Multi-Product Chemical Reactor Using Composite Models and Partial Physics Knowledge](https://mlsanity.com/paper/2606.08611/) (2026)

## Abstract (arXiv)

Large Language Model (LLM)-based agents promise to automate scientific discovery, yet exploring the vast hypothesis space remains costly. Existing principle-evolution methods accelerate this loop, but operate sequentially, which caps exploration breadth and wastes wall-clock time on challenging problems. To address this, we formulate collaborative scientific discovery as evidence transfer between parallel principle-evolution branches. We present COEVOLVE, which realizes this transfer through a coordination core over parallel branches. By integrating value-of-information-gated routing and context-discounted likelihood injection, COEVOLVE enables branches to collaborate through shared measurements while keeping their principle posteriors separate. Across six scientific-discovery tasks under a matched evaluation budget, COEVOLVE attains a mean solution quality of 66.5% versus 57.0% for single-branch principle evolution, with a 1.80x mean wall-clock speedup on the GPT-5.6-Terra backbone; on five auto-research tasks delegated to an autonomous research harness, it is the only arm whose mean stays above the published SOTA anchor on every task. These results establish when evidence sharing accelerates parallel discovery and when transfer safeguards are necessary to limit negative or inert transfers