Tag
The paper introduces DiscoveryRSI, a framework that applies recursive self-improvement to scientific hypothesis generation via multi-agent evolutionary search, harness replay and credit assignment, boosting hypothesis quality from 4.86 to 5.39 and reaching 6.3% correspondence with post-cutoff research across four life-science domains.
Gen-Verse 发布了 DiscoveryRSI-27B，一个 27B 指令微调语言模型，用于递归式科学假设开发、评估、修订与归因，配套 DiscoveryRSI 研究智能体框架支持生命科学研究工作流。
DiscoveryRSI introduces a multi-agent evolutionary search framework with recursive learning to generate and refine valuable scientific hypotheses, achieving self-improvement gains and outperforming baseline research agents like GPT-6 and Claude Opus on life-science benchmarks, alongside a new DFM-Bench evaluation suite.
本文提出使用可能性理论将开放式科学发现形式化为自主科学发现（AASD）问题，引入abductive utility作为发现进展的可计算度量，并提出possibility frontier search算法，在保持anytime有效性的同时渐近达到ε-最优abductive utility。
Researchers at Chalmers University of Technology developed a closed-loop AI scientist that generates biological hypotheses, designs and runs experiments via lab robots, and learns from the results, testing it on yeast by producing 1,933 candidate hypotheses.
This paper proposes a new unified pre-training framework for medical code sequences that captures hierarchical structures and complex interactions, demonstrating superior performance in clinical event prediction and drug repositioning case studies for Alzheimer's disease.
This podcast episode explores the concept of AI scientists, which combine large language models with automated laboratories to design and conduct experiments. Ant Rowstron from ARIA discusses the emerging architecture and ongoing research in the field.
The paper introduces MDA, a framework that uses LLMs for hypothesis generation and Bayesian inference for mechanism scoring, significantly reducing experiment needs while improving accuracy on scientific benchmarks like FORCEBENCH.
This paper presents a graph-to-answer mechanism-tracing case study for Graph-PRefLexOR-8B, a materials-science hypothesis generation model, using visualization and activation-based diagnostics to localize where mechanism support is lost or recovered during generation.
FirstResearch introduces a structured framework for LLM scientific discovery agents that generates a Research Question Certificate containing primitive definitions, assumptions, mechanism, falsifiable hypothesis, and failure update rules, making the proposed research question inspectable before execution. Preliminary evaluations using LLM judges show that the certificate-centered approach outperforms baseline systems in audibility and score.
EO-Agents presents a three-agent LLM pipeline for generating Earth observation hypotheses, leveraging a NASA knowledge graph and graph neural network to rank candidate dataset pairings, with LLM agents filtering, generating, and evaluating structured research hypotheses.
DiscoPER is an autonomous framework leveraging large language models and dynamic code generation for open-ended scientific research, using second-order meta-reflection to synthesize discoveries and statistical testing for rigor. Evaluated on a multimodal ecological benchmark, it outperforms baselines in recovering known patterns.
This paper proposes an evolutionary framework inspired by parallel tempering that uses multi-temperature sampling and information exchange to improve the diversity and quality of scientific hypotheses generated by large language models, demonstrated across molecular, equation, and algorithm discovery.
This paper introduces conditional hypothesis generation, a framework that incorporates researcher-specified covariates to steer LLM-based text analysis toward discovering meaningful subgroup differences while addressing confounds like stratum imbalance and sign reversal.
HypoAgent is an agentic framework for interactive abductive hypothesis generation over knowledge graphs, integrating three agents to handle evolving user intents and fine-grained diagnosis, achieving state-of-the-art performance.
LLM-AutoSciLab is a closed-loop framework that uses LLMs to iteratively generate hypotheses, select informative experiments, and refine mechanisms, achieving superior accuracy and sample efficiency on physics and biology benchmarks over prior static methods.
The paper introduces the Multi-Persona Debate System (MPDS), a literature-grounded framework that uses LLMs, persona induction, and structured multi-agent debate to automate the generation of scientific hypotheses, with evaluations in battery materials research showing improved hypothesis quality and cross-perspective integration.
Two AI-powered science assistants, Google's Co-Scientist and FutureHouse's Robin, can generate hypotheses and analyze biological data for drug retargeting, helping researchers find non-obvious connections across scientific fields.
Google DeepMind introduces Co-Scientist, a system that uses a multi-agent 'idea tournament' to generate, debate, and evaluate research hypotheses for open challenges.
This paper proposes a scalable supervised fine-tuning method for training language models to propose research hypotheses across disciplines. It has been accepted by ICML 2026 and the code is open source.