Papers
arxiv:2507.15550

PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priors

Published on Jul 21
· Submitted by YimengChen on Jul 22
Authors:
,
,
,

Abstract

PhysGym, a new benchmark suite, evaluates large language model-based agents' scientific reasoning in interactive physics environments, focusing on their handling of complexity and prior knowledge.

AI-generated summary

Evaluating the scientific discovery capabilities of large language model based agents, particularly how they cope with varying environmental complexity and utilize prior knowledge, requires specialized benchmarks currently lacking in the landscape. To address this gap, we introduce PhysGym, a novel benchmark suite and simulation platform for rigorously assessing LLM-based scientific reasoning in interactive physics environments. PhysGym's primary contribution lies in its sophisticated control over the level of prior knowledge provided to the agent. This allows researchers to dissect agent performance along axes including the complexity of the problem and the prior knowledge levels. The benchmark comprises a suite of interactive simulations, where agents must actively probe environments, gather data sequentially under constraints and formulate hypotheses about underlying physical laws. PhysGym provides standardized evaluation protocols and metrics for assessing hypothesis accuracy and model fidelity. We demonstrate the benchmark's utility by presenting results from baseline LLMs, showcasing its ability to differentiate capabilities based on varying priors and task complexity.

Community

Paper author Paper submitter
This comment has been hidden (marked as Resolved)
Paper author Paper submitter
edited 1 day ago

Can LLM truly think like a Physicist?
We propose PhysGym, a new benchmark that tests if LLM can perform scientific discovery. PhysGym's interactive platform challenges LLM-based agents to discover physics laws by designing their own experiments, uniquely allowing researchers to control and even hide prior knowledge like variable descriptions and context.
success_rate_pro.png

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2507.15550 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2507.15550 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2507.15550 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.