EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation

• URL: http://arxiv.org/abs/2609.01526v1
• Date: Tue, 01 Sep 2026 16:55:56 GMT
• Title: EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation
• Abstract summary: EvoSCM aims to equip scientific agents with explicit structural causal models that evolve as new evidence is collected.<n>We evaluate EvoSCM onPhysics, a benchmark requiring agents to uncover the hidden dynamics of noncanonical physical worlds through experimentation.
• Score: 68.80901568810616
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scientific agents must learn not only how to reason, but also what to believe. However, existing LLM agents typically express scientific hypotheses in free-form text, leaving their beliefs implicit and difficult to test or revise. We introduce EvoSCM, which equips scientific agents with explicit structural causal models that evolve as new experimental evidence is collected. EvoSCM maintains a population of competing SCM hypotheses, each encoding a candidate causal explanation of the environment, and evolves them through a closed discovery loop. In each round, the agent abduces latent mechanisms from accumulated evidence, designs discriminative interventions, and commits to falsifiable predictions that it tests through experimentation. Discrepancies between prediction and observation are inductively distilled into correction rules that revise the causal structures and mechanisms of each hypothesis, and the agent then deductively validates the revised population against accumulated evidence and structural consistency to guide the next round. We evaluate EvoSCM on DiscoverPhysics, a benchmark requiring agents to uncover the hidden dynamics of noncanonical physical worlds through experimentation. EvoSCM consistently improves scientific discovery over baselines, yielding more accurate explanations and predictions while making more effective use of experimental interactions.

Related papers

• HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses [35.57672494910454]
  How different forms of agent collaboration affect hypothesis quality remains an open question.<n>We introduce HypoEvolve, which makes collaboration explicit through successive updates to a hypothesis population.<n>Each generation specifies how scientific judgments and new proposals reshape the population, making collaboration effects on hypothesis quality directly testable.
  arXiv  Detail & Related papers  (2026-09-14T17:44:49Z)
• CausalArena: Benchmarking Causal Discovery in the Foundation Model Era [47.81267771630766]
  CausalArena is a unified benchmark for causal discovery under a common protocol.<n>We show that strong performance in one benchmark regime does not reliably transfer to others.
  arXiv  Detail & Related papers  (2026-09-10T17:53:15Z)
• Science sandboxes measure the scientific capability of AI agents [1.1846810006828092]
  We introduce science sandboxes, a framework for studying this capability in AI agents.<n>We instantiate this framework in two biological settings, models of regulatory genomics and protein fitness prediction.<n>In particular, their scientific reasoning deteriorated when they encountered systems whose rules fell outside familiar biological priors.
  arXiv  Detail & Related papers  (2026-08-31T02:33:38Z)
• Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM Agents [0.42970700836450476]
  Large language model (LLM) agents are increasingly expected to play a central role in AI-driven scientific discovery.<n>Here we propose the Hypothesis Evolution Protocol (HEP), an agent harness that provides hypothesis generation, evaluation, and evolution as explicit, auditable operations.<n>On materials-science research tasks, a HEP-equipped agent operates the hypothesis--test--evidence--belief cycle that planning-style agents lack, generalizes across research questions, and exploits the protocol more fully as the base LLM becomes more capable.
  arXiv  Detail & Related papers  (2026-07-10T08:39:30Z)
• Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning [103.788281428856]
  We introduce SciReasoner, a scientific foundation model for native structural reasoning across proteins, small molecules and inorganic crystals.<n>SciReasoner discretizes coordinates, topologies and periodic connectivities into a unified structure-aware vocabulary.<n>Across 86 benchmarks, SciReasoner achieves state-of-the-art performance on 67 tasks.
  arXiv  Detail & Related papers  (2026-07-08T17:59:59Z)
• Embodied Science: Closing the Discovery Loop with Agentic Embodied AI [73.54118756665221]
  We argue for embodied science, a paradigm that reframes scientific discovery as a closed loop tightly coupling agentic reasoning with physical execution.<n>We propose a unified Perception-Language-Action-Discovery (PLAD) framework, wherein embodied agents perceive experimental environments, reason over scientific knowledge, execute physical interventions, and internalize outcomes to drive subsequent exploration.
  arXiv  Detail & Related papers  (2026-03-20T09:20:12Z)
• Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics [82.55776608452017]
  Large language models (LLMs) provide a flexible and versatile framework that orchestrates interactions with human scientists, natural language, computer language and code, and physics.<n>This paper presents our view and vision of LLM-based scientific agents and their growing role in transforming the scientific discovery lifecycle.<n>We identify open research challenges and outline promising directions for building more robust, generalizable, and adaptive scientific agents.
  arXiv  Detail & Related papers  (2025-10-10T22:26:26Z)
• Towards an AI co-scientist [48.11351101913404]
  We introduce an AI co-scientist, a multi-agent system built on Gemini 2.0.<n>The AI co-scientist is intended to help uncover new, original knowledge and to formulate demonstrably novel research hypotheses.<n>The system's design incorporates a generate, debate, and evolve approach to hypothesis generation, inspired by the scientific method.
  arXiv  Detail & Related papers  (2025-02-26T06:17:13Z)
• BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery [32.395366135636046]
  We introduce BoxingGym, a benchmark with 10 environments for evaluating experimental design and model discovery.<n>We compute the expected information gain (EIG), an information-theoretic quantity which measures how much an experiment reduces uncertainty about the parameters of a generative model.<n>We find that current LLMs, such as GPT-4o, struggle with both experimental design and model discovery.
  arXiv  Detail & Related papers  (2025-01-02T21:15:57Z)
• LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery [141.39722070734737]
  We propose to enhance the knowledge-driven, abstract reasoning abilities of Large Language Models with the computational strength of simulations. We introduce Scientific Generative Agent (SGA), a bilevel optimization framework. We conduct experiments to demonstrate our framework's efficacy in law discovery and molecular design.
  arXiv  Detail & Related papers  (2024-05-16T03:04:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.