arXiv:2604. 12198v2 Announce Type: replace-cross Abstract: Autonomous LLM agents now produce complete research artifacts in machine-learning sandboxes, but real computational physics is harder: experiments are first-principles calculations against re-runnable physical ground truth, and meaningful new work almost always builds on a key existing paper.
arXiv:2607. 02329v1 Announce Type: new Abstract: Autonomous-research agents have demonstrated end-to-end LLM automation in machine-learning sandboxes where execution provides calibration.
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...
arXiv:2603. 13191v2 Announce Type: replace-cross Abstract: While large language models (LLMs) have transformed AI agents into proficient executors of computational materials science, performing a hundred simulations does not make a researcher.
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.
Deep equilibrium models promise input-adaptive implicit computation: harder problems should demand more solver iterations, and the solved equilibrium should encode the result of genuine iterative inference. We report a cautionary study of a port-Hamiltonian DEQ with a learned initialization on two reasoning tasks -- ProofWriter entailment over frozen DeBERTa embeddings and a BFS-verified graph-reachability benchmark -- in which the implicit computation is a silent no-op.
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:2607. 11116v1 Announce Type: cross Abstract: Deep equilibrium models promise input-adaptive implicit computation: harder problems should demand more solver iterations, and the solved equilibrium should encode the result of genuine iterative inference.
arXiv:2604. 17406v3 Announce Type: replace Abstract: The convergence of large language models and agents is catalyzing a new era of scientific discovery: Agentic Science.
AxQM is a new benchmark for formal proof synthesis in physics, comprising 1,019 Lean‑kernel‑checkable tasks drawn from the textbook *Quantum Computation and Quantum Information* by Nielsen and Chuang. The tasks are defined in a custom Lean library for finite‑dimensional quantum mechanics and are guaranteed solvable because they stem from a near‑complete formalization of the textbook’s formal content. Grading is deterministic, requiring proofs to compile, contain no sorrys, and introduce no new axioms.
The paper introduces AutoMat, a benchmark designed to test large language model (LLM) coding agents on their ability to reproduce claims from computational materials science. AutoMat presents three challenges: reconstructing underspecified procedures, navigating specialized toolchains, and assessing whether the evidence supports a claim. Experiments show that current LLM agents achieve low success rates, with the best setting reaching only 53%, and failures stem mainly from incomplete procedures, methodological deviations, and execution fragility.
arXiv:2602. 02905v2 Announce Type: replace Abstract: Autonomous agents powered by large language models (LLMs) promise to accelerate scientific discovery end-to-end, but rigorously evaluating their capacity for verifiable discovery remains a central challenge.
VeriHarness is a method that enhances verification for large language model agents tackling long‑horizon tasks without needing reference answers at test time. It transforms the base LLM into an agentic verifier by providing a workspace, evidence tools, and reusable verification skills, using disagreement resolution and consensus challenge to evaluate competing claims. Across five benchmarks and two frontier models, VeriHarness outperforms baselines, achieving significant performance gains and demonstrating self‑improvement of verification skills from failure feedback.