Exploring Structures in Physics Problems: Can AI Agents Discover Statistical Mechanical Mappings?

The promise of AI-driven scientific discovery hinges on whether AI agents can autonomously design and execute the computational workflows that underpin modern science. Molecular dynamics (MD) simulation presents a natural test bed to stress-test this claim; it requires translating physical intuition into syntactically and semantically correct input scripts, reasoning about initial and boundary conditions, diagnosing numerically unstable trajectories, and interpreting outputs against known physical behavior and laws. We introduce MDGYM, a benchmark of 169 expert-curated MD simulations spanning LAMMPS and GROMACS, two widely used MD packages, across three increasing difficulty levels. We evaluate three agentic frameworks -- Claude Code, Codex, and OpenHands -- with four LLMs, and find that all perform poorly: even the strongest agent solves only 21% of easy-level tasks, with less than 10% at higher difficulties. Trajectory analysis reveals a characteristic pattern of failure -- agents successfully invoke simulation machinery but produce physically unstable configurations, fabricate numerical outputs without executing the underlying computation, or abandon tasks prematurely rather than iterating through simulation-specific errors. These failure modes are qualitatively distinct from those observed in general software engineering benchmarks, indicating that fluent code generation does not transfer to grounded physical reasoning.

Frontier LLMs now perform strongly across a wide range of physics evaluations, but it is hard to disentangle genuine reasoning from recall of established science. We introduce DiscoverPhysics, an interactive benchmark that asks a LLM agent to discover the laws of motion of a simulated world whose physics deliberately deviates from our own. We construct 22 worlds governed by, among others, screened and fractional-power gravity, multi-species couplings, hidden dark-matter-like particles, non-coordinate-free physics, and time-varying interactions. Each world is generated on demand by an N-body simulator, for which the agent proposes several rounds of experiments, observes raw trajectory data, and ultimately submits both a natural-language explanation of the world's physics and a Python implementation of the inferred law. Because solving a world requires the agent to design informative experiments and revise its hypotheses, the benchmark probes long-horizon reasoning over an experimental history. We evaluate submissions along two complementary axes: trajectory MSE on held-out particles and an LLM-judged explanation score following an expert-written rubric assessing conceptual understanding of each world. Across eleven frontier models, we find that the strongest agents pass only half of the worlds and consistently fail on those where latent structure must be uncovered. Open-source models lag substantially behind commercial models, both in their ability to design informative experiments and in extracting conclusions from the data. We further find that good predictive accuracy does not guarantee high explanation quality and that conceptual understanding depends on hypothesis refinement through well-chosen experiments.

As large language models (LLMs) show increasing promise on research-level physics reasoning tasks and agentic AI becomes more common, a practical question emerges: How does the interaction between researchers and agents affect the results? We study this using SCALAR (Structured Critic--Actor Loop for AI Reasoning), an Actor--Critic--Judge pipeline applied to quantum field theory and string theory problems. The Actor proposes solutions, the Critic provides iterative feedback, and an independent Judge evaluates the transcript against reference solutions. We vary the Actor persona, the Critic feedback strategy, and the Actor model family and scale. Multi-turn dialogue improves over single-shot attempts throughout, but both the mechanism of improvement and the value of different prompting choices depend strongly on the Actor--Critic pairing. Increasing the scale within one model family (e.g. from the 8B-parameter DeepSeek-R1 variant to DeepSeek-R1 70B) improves some easier-problem behavior, but does not remove the hardest bottleneck we observe. Critic feedback strategy matters most clearly in the asymmetric Actor--Critic setting (e.g., a lightweight Haiku Actor guided by a stronger Sonnet Critic), where constructive feedback improves mean-score outcomes. In same-family Actor--Critic settings, strategy effects are weaker: lenient feedback is sometimes favored, while strict and adversarial feedback are not beneficial. Taken together, SCALAR provides a controlled testbed for evaluating which interaction structures help or hinder AI-driven scientific discovery.