The paper presents an explore‑then‑commit protocol that uses a large language model to generate hypotheses, a programmatic planner to collect measurements, and a fresh prompt to synthesize a scientific law from fixed observations. In 576 NewtonBench trials across 12 physics modules, the protocol—especially when interpreter‑enabled planners are used—reduces the number of measurements needed and improves root‑mean‑squared logarithmic error for both GPT‑4.1‑mini and GPT‑4.1. The study demonstrates measurement savings in every module, though it notes that the causal components and generalization beyond noiseless direct‑equation tasks remain unresolved.
arXiv:2607. 00436v1 Announce Type: new Abstract: Large language model agents are increasingly connected to scientific software, yet it remains unclear when tool access makes scientific computation more reliable rather than merely more complex.
The paper introduces an experimental model‑class revision framework that jointly proposes structural edits to a hypothesis space and diagnostic experiments to test those edits. By coupling a class‑level distinguishability objective with anytime‑valid sequential evidence, the method only revises the model class after the current one is rejected. On 400 controlled dynamical environments, the approach achieves 89.5% exact recovery with 32 experiments, outperforming baselines and transferring well to unseen mechanisms, library insufficiency detection, and other benchmark tasks.
ToolGate is an executable acceptance pipeline designed to streamline the creation of scientific benchmarks that rely on specialist software. It evaluates each model-generated item through three gates: (1) an executable solution script must reproduce the proposed answer, (2) a randomized no‑tool screen rejects items solvable without the software, and (3) a tool‑using agent must solve the item within a time limit. In a FEniCSx instantiation, 500 generation attempts produced 128 unique, verified benchmark items after successive filtering.
arXiv:2606. 27383v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as research assistants, yet it remains unclear whether they can calibrate research takeaways to the strength and scope of the supporting evidence.
arXiv:2607. 05682v1 Announce Type: new Abstract: LLM systems for scientific discovery increasingly assist with ideation, literature synthesis, experiment planning, and report generation, but the first research question they propose can remain difficult to audit: it may sound plausible without exposing the mechanism, falsifier, or assumption that a scientist should inspect.
arXiv:2606. 13535v1 Announce Type: cross Abstract: Particle physics collider experiments provide Rivet routines as part of the analysis preservation strategy for model-independent measurements.
La Agente ’Optima is an agentic framework that builds and manages Bayesian optimization campaigns for self‑driving laboratories, separating large language model reasoning from campaign execution. It maintains a persistent optimization state, allowing consistent repetitive loops and auditable decisions, and only returns control to the agent when interpretation or revision is needed. In tests on digital discovery tasks and physical platforms, it corrected measurement failures, improved yields, and recommended formulation changes, outperforming human‑directed campaigns in cost and material usage.
arXiv:2607. 07379v1 Announce Type: new Abstract: In agentic scientific machine learning (SciML), large language model (LLM) agents can discover surrogate models and select one by an automated score, typically an error metric.
The paper "Beyond Execution: Auditing Experimental Fidelity in LLM-Driven Scientific Research" argues that large language model agents must faithfully implement reference methods, design experiments that truly test claims, and provide supporting evidence. It reports that agents often hallucinate methodology—reducing datasets, substituting components, or drawing conclusions from limited resources—leading to false claims. To counter this, the authors introduce ABE‑Ralph, a reference‑anchored auditing framework that structures experimental constraints, guides implementation, and verifies results, achieving a 93% robust execution rate across 30 reproduction runs and matching or exceeding state‑of‑the‑art performance on 5 NatureBench tasks. "whyItMatters":"The study demonstrates that evaluating AI scientists requires more than code execution; it must ensure experimental design and evidence truly support the claimed scientific outcomes."
arXiv:2605.26087v2 Announce Type: replace-cross Abstract: Frontier LLMs now perform strongly across a wide range of physics evaluations, but it is hard to disentangle genuine reasoning from recall of...
SCICONVBENCH is a benchmark designed to evaluate large language models (LLMs) on multi‑turn clarification tasks in computational science. It focuses on two key abilities: eliciting missing information (disambiguation) and resolving contradictory requests (inconsistency resolution) across four domains—fluid mechanics, solid mechanics, materials science, and partial differential equations. The benchmark pairs a structured task ontology with a rubric‑based evaluation framework, measuring LLM performance in clarification behavior, conversational grounding, and final‑specification fidelity, and reveals that even top models only resolve about 52.7% of disambiguation cases in fluid mechanics while often making ungrounded assumptions.
arXiv:2606. 20512v1 Announce Type: cross Abstract: LLM-based coding agents need higher-level operational knowledge about a repository (which files house which subsystems, how to run the test suite, which workflows have historically led to wrong fixes) that does not exist in the code itself.