OraclePhys: A Systematic Framework for LLM Fine-Tuning on Structural Mechanics
cs.LG
Submitted: 2026-08-17
Updated: 2026-11-08
Terminology
Sources
- Physics of Language Models: Part 3.1, Knowledge Storage and Extraction
- NFT: Bridging Supervised Learning and Reinforcement Learning in Math Reasoning
- Reinforced Self-Training (ReST) for Language Modeling
- BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning
- Automating Structural Engineering Workflows with Large Language Model Agents
- ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
- Spurious Rewards: Rethinking Training Signals in RLVR
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- RL's Razor: Why Online Reinforcement Learning Forgets Less
- SPhyR: Spatial-Physical Reasoning Benchmark on Material Distribution
- Solving math word problems with process- and outcome-based feedback
- A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis