SCALAR accepted at ICML 2026 AI4Physics

Sat, 11 Jul 2026 00:00:00 +0000

The paper, When Does Critique Improve AI-Assisted Theoretical Physics? SCALAR: Structured Critic-Actor Loop for Agentic Reasoning, was accepted to the AI4Physics Workshop at ICML 2026. It presents SCALAR (Structured Critic-Actor Loop for Agentic Reasoning), a controlled study of how critique affects agentic reasoning on theoretical-physics problems.

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 Agentic 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, 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, 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.

More information about the AI4Physics Workshop is available online.

AI for Physics | Sokratis Trifinopoulos

SCALAR accepted at ICML 2026 AI4Physics