SCI-PRM: A Tool Aware Process Reward Model for Scientific Reasoning Verification
Quick Answer
The Sci-PRM model enhances scientific reasoning in complex domains by utilizing a new dataset, SCIPRM70K, which integrates tool usage with reasoning.
Quick Take
It improves foundation models through effective and provides dense reward signals in Reinforcement Learning, addressing hallucination issues and performance limitations.
Key Points
- Introduces SCIPRM70K, a dataset with Chain-of-Tool trajectories for scientific reasoning.
- Sci-PRM model improves tool selection and execution accuracy during inference.
- Enables Best-of-N selection for effective test-time scaling in foundation models.
- Provides dense reward signals in Reinforcement Learning to mitigate advantage disappearance.
- Significantly enhances performance ceilings in scientific reasoning tasks.
Paper Resources
Source Excerpt
From the original publisher, up to about 700 charactersarXiv:2606. 04579v1 Announce Type: new Abstract: While Process Reward Models (PRMs) have achieved remarkable success in mathematical reasoning, their application in complex scientific domains-such as biology, chemistry, and physics remains largely unexplored. Scientific problems demand not only logical rigor but also factual consistency and the precise usage of domain-specific tools, areas where current models often suffer from hallucinations and lack of verification.
In this paper, we first construct SCIPRM70K, a large-scale dataset featuring Chain-of-Tool trajectories that explicitly interleave reasoning with the execution of scientific tools. …
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Automatic Ordinary Differential Equations Discovery For Biological Systems Using Powered Agentic System
The MEDA system utilizes large language models and symbolic regression to autonomously discover ordinary differential equations for biological systems, achieving strong structural recovery and biologically plausible models. It outperforms existing methods by integrating domain knowledge and mechanistic constraints, demonstrating effective retrieval and extrapolation capabilities.