# HypoForge: A Self-Improving Multi-Agent Framework for Automated Hypothesis Generation and Testing via Scientific Skill Learning

arXiv: https://arxiv.org/abs/2608.25770 · HTML: https://mlsanity.com/paper/2608.25770/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 9 of 9)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification](https://mlsanity.com/paper/2604.01687/) (2026)
- [DiscoveryBench: Towards Data-Driven Discovery with Large Language Models](https://mlsanity.com/paper/2407.01725/) (2024)
- [Reinforcement Learning for Self-Improving Agent with Skill Library](https://mlsanity.com/paper/2512.17102/) (2025)
- [Automated Hypothesis Validation with Agentic Sequential Falsifications](https://mlsanity.com/paper/2502.09858/) (2025)
- [HypoBench: Towards Systematic and Principled Benchmarking for Hypothesis Generation](https://mlsanity.com/paper/2504.11524/) (2025)
- [Towards Autonomous Hypothesis Verification via Language Models with Minimal Guidance](https://mlsanity.com/paper/2311.09706/) (2023)

## Built on by (most cited first, 2 of 2)

- [The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement](https://mlsanity.com/paper/2609.11873/) (2026)
- [ShadowMiner v1 - An Experience Report on Implementing and Measuring a Problem-and-Hypothesis Discovery Engine](https://mlsanity.com/paper/2610.04339/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have enabled AI scientist systems to automate scientific discovery, yet existing approaches most rely on static prompting or fixed workflows and fail to accumulate experience for continual improvement. We propose HypoForge, an experience-guided multi-agent framework that learns reusable scientific skills for automated hypothesis generation and hypothesis testing. HypoForge is built on the observation that these two stages involve different supervision signals. For hypothesis generation, where explicit feedback is unavailable, HypoForge adopts an adversarial generator--discriminator mechanism to improve reasoning through comparative critique. For hypothesis testing, where empirical feedback is available, HypoForge learns testing skills from execution outcomes and ground-truth results. By matching skill learning strategies with stage-specific supervision, HypoForge enables continual improvement without fine-tuning foundation models. Experiments on hypothesis generation and testing benchmarks show that HypoForge consistently outperforms existing AI scientist frameworks and skill-level variants. Further analysis demonstrates the effectiveness of the proposed stage-specific skill learning paradigms.