Cover Image

LLM-Based Scientific Equation Discovery via Physics-Informed Token-Regularized Policy Optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Boxiao, Li, Kai, Liu, Tianyi, Li, Chen, Wang, Junzhe, Zhang, Yifan, Cheng, Jian
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

When Good Equations Get Bad Scores: Improving Symbolic Regression Through Better Parameter Optimization
by: Wang, Boxiao, et al.
Published: (2026)

DrSR: LLM based Scientific Equation Discovery with Dual Reasoning from Data and Experience
by: Wang, Runxiang, et al.
Published: (2025)

Game-Theoretic Co-Evolution for LLM-Based Heuristic Discovery
by: Ke, Xinyi, et al.
Published: (2026)

Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement
by: Wen, Muning, et al.
Published: (2024)

On LLM-Based Scientific Inductive Reasoning Beyond Equations
by: Lin, Brian S., et al.
Published: (2025)

Continual Novel Class Discovery via Feature Enhancement and Adaptation
by: Yu, Yifan, et al.
Published: (2024)

Prior-Guided Symbolic Regression: Towards Scientific Consistency in Equation Discovery
by: Xiao, Jing, et al.
Published: (2026)

OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery
by: Prabhakar, Vignesh, et al.
Published: (2025)

Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization
by: Wang, Junzhe, et al.
Published: (2026)

SR-Scientist: Scientific Equation Discovery With Agentic AI
by: Xia, Shijie, et al.
Published: (2025)

LaPuda: LLM-Enabled Policy-Based Query Optimizer for Multi-modal Data
by: Wang, Yifan, et al.
Published: (2024)

Aligned but Fragile: Enhancing LLM Safety Robustness via Zeroth-Order Optimization
by: Liu, Zhihao, et al.
Published: (2026)

Anchored Policy Optimization: Mitigating Exploration Collapse Via Support-Constrained Rectification
by: Wang, Tianyi, et al.
Published: (2026)

Grounding LLMs in Scientific Discovery via Embodied Actions
by: Zhang, Bo, et al.
Published: (2026)

Influence-Guided Symbolic Regression: Scientific Discovery via LLM-Driven Equation Search with Granular Feedback
by: Saveliev, Evgeny S., et al.
Published: (2026)

NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents
by: Zheng, Tianshi, et al.
Published: (2025)

Automated Scientific Discovery: From Equation Discovery to Autonomous Discovery Systems
by: Kramer, Stefan, et al.
Published: (2023)

Ratio-Variance Regularized Policy Optimization for Efficient LLM Fine-tuning
by: Luo, Yu, et al.
Published: (2026)

SVBRD-LLM: Self-Verifying Behavioral Rule Discovery for Autonomous Vehicle Identification
by: Li, Xiangyu, et al.
Published: (2025)

LLM-SR: Scientific Equation Discovery via Programming with Large Language Models
by: Shojaee, Parshin, et al.
Published: (2024)

LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery
by: Ma, Pingchuan, et al.
Published: (2024)

Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics
by: Zhou, Lianhao, et al.
Published: (2025)

COMAP: Co-Evolving World Models and Agent Policies for LLM Agents
by: Liu, Youwei, et al.
Published: (2026)

Lost in Tokenization: Context as the Key to Unlocking Biomolecular Understanding in Scientific LLMs
by: Zhuang, Kai, et al.
Published: (2025)

Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models
by: Fan, Jiajun, et al.
Published: (2025)

AgenticRec: End-to-End Tool-Integrated Policy Optimization for Ranking-Oriented Recommender Agents
by: Li, Tianyi, et al.
Published: (2026)

Mozi: Governed Autonomy for Drug Discovery LLM Agents
by: Cao, He, et al.
Published: (2026)

Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game
by: Cheng, Pengyu, et al.
Published: (2023)

Entropy-Gated Selective Policy Optimization:Token-Level Gradient Allocation for Hybrid Training of Large Language Models
by: Hu, Yuelin, et al.
Published: (2026)

On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning
by: Zhang, Yifan, et al.
Published: (2025)

LLM-Oriented Token-Adaptive Knowledge Distillation
by: Xie, Xurong, et al.
Published: (2025)

LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models
by: Shojaee, Parshin, et al.
Published: (2025)

Absolute Policy Optimization
by: Zhao, Weiye, et al.
Published: (2023)

LLM-Based World Models Can Make Decisions Solely, But Rigorous Evaluations are Needed
by: Yang, Chang, et al.
Published: (2024)

Reference-guided Policy Optimization for Molecular Optimization via LLM Reasoning
by: Li, Xuan, et al.
Published: (2026)

SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents
by: Zhu, Kunlun, et al.
Published: (2025)

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs
by: Tang, Lv, et al.
Published: (2026)

HTPO: Towards Exploration-Exploitation Balanced Policy Optimization via Hierarchical Token-level Objective Control
by: Yao, Xincheng, et al.
Published: (2026)

VULPO: Context-Aware Vulnerability Detection via On-Policy LLM Optimization
by: Li, Youpeng, et al.
Published: (2025)

Not All Tokens See Equally: Perception-Grounded Policy Optimization for Large Vision-Language Models
by: Ye, Zekai, et al.
Published: (2026)