Axiomatic World Modeling for Physics Reasoning
Summary
提出 RLAWM，通过分层建模与求解奖励惩罚模型内部世界模型与真实物理公理之间的偏差，显著提升 LLM 在物理推理基准上的表现。
View Cached Full Text
Cached at: 10/21/26, 06:23 PM
Paper page - Axiomatic World Modeling for Physics Reasoning
Source: https://huggingface.co/papers/2610.24519
Abstract
RLAWM improves physics reasoning by penalizing divergence between a model’s internal world model and true physical axioms through hierarchical modeling and solving rewards.
Recent research-level physics-reasoning benchmarks for LLMs reveal a failure mode that lies not in knowledge or execution, but in modeling the world being reasoned about. Models often silently alter given quantities, fabricate laws, or inject unstated assumptions to force a problem into familiar patterns, and then reason inside this corrupted world. We define this premise-level divergence asmodeling drift: the gap between a model’s internalaxiomatic world model(AWM) and the true physical world specified in the problem. AlthoughRLVRandPRMhave yielded substantial gains in mathematics and code, their reward shapes do not directly supervise world modeling in axiomatic domains such as physics. We proposeReinforcement Learning with Axiomatic World Modeling(RLAWM), which optimizes the policy by penalizing divergence between its inferredaxiomatic world modeland the true physics world.RLAWMprobes physics reasoning at two hierarchical levels (modeling and solving), each scored by a physically grounded reward. Themodeling rewardtargets abstract knowledge formulation, evaluating whether the model captures the true axiomatic world before attempting calculation. Thesolving rewardtargets instantiated knowledge reasoning, checking whether the model’s concrete derivation remains consistent with the axiomatic world. This two-level structure separates what world the model believes it is reasoning in from how it reasons within that world. The framework operates exclusively during training, with no extra cost during inference.RLAWMimproves performance by up to +12.2 points on PhysReason and +5.2 on PHYSICS over the baseline. It also generalizes zero-shot across difficulty, source, and domain, with a 2.45x gain and +10 points over the strongest baseline on olympiad-level physics and math.
View arXiv pageView PDFProject pageAdd to collection
Get this paper in your agent:
hf papers read 2610\.24519
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2610.24519 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2610.24519 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2610.24519 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Words to World: Benchmarking LLMs in Interactive Physical Environments
该论文提出了一个用于评估大语言模型在闭环物理交互中表现的基准，模型需通过连接机械臂、摄像头和传感器的系统在真实环境中执行任务并根据物理反馈调整行动。实验揭示了LLM在物理行动中的常见失败模式，如幻觉状态变化、糟糕的异常恢复和不稳定的长程规划。
Scientific Logicality Enriched Methodology for LLM Reasoning: A Practice in Physics
This paper introduces a methodology to enrich scientific logicality in LLM reasoning, including assessment criteria and data sampling methods, and demonstrates its effectiveness on physics problems using multiple backbone LLMs.
PhysMent: An Interactive Approach For LLM Reasoning In Physics Problems
PhysMent introduces an interactive benchmark that evaluates LLM physical reasoning via iterative tool-mediated experimentation with a MuJoCo physics simulator, revealing model weaknesses in multi-step procedural tasks.
Testing Frontier Large Language Models' Physics Literacy in Parallel Physical Worlds
This paper introduces a four-stage diagnostic to test whether LLMs can reason in unfamiliar physics frameworks, finding that frontier models achieve low pass rates and exhibit a qualitative-versus-quantitative asymmetry.
Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
This paper introduces ScaleLogic, a framework demonstrating that RL training compute scales as a power law with reasoning depth in LLMs. It highlights that logical expressiveness is key to improving downstream transfer and training efficiency.