proomt

Search

Search posts, papers, and topics

All posts

Hugging Face Daily PapersJieyuan Liu, Mengzhou Hu, Jefferson Chen1 min readpaperadvanced

HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses

Read on arxiv.org

Summary

The paper presents HypoEvolve, a generational genetic algorithm that coordinates specialized LLM agents to iteratively propose, critique, and refine scientific hypotheses. On a drug‑repurposing benchmark across 34 cancer types, it outperforms six baselines, achieving a DepMap selectivity of 0.171 versus 0.115.

  • HypoEvolve treats hypotheses as a population evolved by GA operators (selection, crossover, mutation) driven by LLM agents' scientific judgments.
  • Three specialized agents handle mechanistic argument generation, assumption reconsideration, and evidence/testability assessment each generation.
  • Evaluation uses DepMap and Open Targets to score hypothesis relevance and selectivity; HypoEvolve reaches 0.171 selectivity, beating the best baseline (0.115).
  • Performance gains hold on held‑out cancer types, indicating the approach generalizes beyond training data.

AI researchers and drug‑discovery teams should care because it shows how evolutionary coordination of LLM agents can materially improve hypothesis quality and accelerate autonomous scientific insight.

8/10
llmmulti agent systemsgenetic algorithmsdrug repurposingcancer

Related reading

  2. ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

    ScienceIDE is a framework that turns existing scientific software repositories into programmable environments that agents can use for task generation, execution, and verification. Training on these environments yields LLMs (PhAI‑IDE series) that outperform baselines on scientific code repair and several general code‑reasoning benchmarks.

    Hugging Face Daily Papersarxiv.org2 minpaper

  3. Advancing AI for biology: Teaching models to design and characterize antibodies

    Amazon Bio Discovery developed three AI models: MochiBind for fast, sequence-based antibody binding ranking, CA-MAP for context-aware developability prediction robust to batch effects, and an agent-guided system for de novo antibody design. These advancements aim to accelerate and improve the accuracy of antibody drug discovery, with experimental validation for a novel cancer target.

    Amazon Scienceamazon.science10 min

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

    ScienceBuddy is an interactive workspace that converts researcher prompts, feedback, and execution traces into continual‑learning tasks for AI agents. It introduces a "recursive‑in‑recursive" self‑improvement loop that alternates harness refinement and model training, and showcases case studies across four scientific task families.

    Hugging Face Daily Papersarxiv.org1 minpaperHN2

  6. COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization

    COBRA‑Skills uses a contextual‑bandit loop to selectively evaluate and evolve LLM agent skills, achieving better performance with roughly half the evaluation cost of prior methods. The framework works with limited examples and remains robust across different agent setups and even when the target model creates its own skills.

    Hugging Face Daily Papersarxiv.org1 minpaper