Agentic Retrieval and Reinforcement Learned Equation Chains: A Controlled Generation Framework for Complex and Novel Physics Word Problems

• URL: http://arxiv.org/abs/2606.15591v1
• Date: Sun, 14 Jun 2026 04:22:36 GMT
• Title: Agentic Retrieval and Reinforcement Learned Equation Chains: A Controlled Generation Framework for Complex and Novel Physics Word Problems
• Abstract summary: ARVRE (Agentic Retrieval Value Reinforced Equation-chain) is a two-stage framework for generating diverse and mathematically valid PWPs.<n>In the first stage, a form of offline temporal-difference learning is used to construct valid chains of physics equations.<n>In the second stage, a Large Language Model (LLM) converts the equation chain and retrieved concepts into a natural-language physics question.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating high-quality Physics Word Problems (PWPs) that are novel, complex, and solvable remains a challenging and underexplored problem in educational content generation. Existing approaches, many adapted from Math Word Problem (MWP) generation, often produce ambiguous, unsolvable, or structurally simple questions with limited linguistic diversity. We introduce ARVRE (Agentic Retrieval Value Reinforced Equation-chain), a two-stage framework for generating diverse and mathematically valid PWPs. In the first stage, a form of offline temporal-difference learning is used to construct valid chains of physics equations, while an agentic retrieval-augmented generation (RAG) framework dynamically selects topic-specific concepts and vocabulary. This design enables explicit control over problem structure and difficulty. In the second stage, a Large Language Model (LLM) converts the equation chain and retrieved concepts into a natural-language physics question. By grounding generation in valid equation chains, our method preserves mathematical correctness while promoting linguistic diversity and contextual richness. Human and automated evaluations demonstrate that ARVRE generates PWPs that are more complex, novel, and solvable than those produced by existing approaches. These results highlight the potential of combining reinforcement learning, retrieval, and LLMs for reliable generation of educational physics content.

Related papers

• Data-driven discovery of governing differential equations across physical systems [61.522420798136984]
  We propose a problem-oriented perspective on data-driven differential equation discovery.<n>We first introduce a two-dimensional phase diagram of equation discoverability.<n>We then present the representation-evaluation-optimization (REO) framework as a fundamental abstraction of the discovery process.
  arXiv  Detail & Related papers  (2026-06-08T15:35:06Z)
• Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery [3.9943798586374784]
  This survey provides a unified account of the field's evolution.<n>We organize the landscape along four axes: (i) informal reasoning over text and diagrams, spanning MWP solving, multimodal geometry, and RLMs; (ii) formal reasoning in proof assistants, including autoformalization, tactic prediction, compiler-guided repair, and proof search; (iii) mathematical discovery, where systems propose constructions, improve bounds, or assist attacks on open problems; and (iv) the inference and training-time techniques, including CoT prompting, tool use, process reward models, and VLVR, that increasingly connect generation with
  arXiv  Detail & Related papers  (2026-06-07T16:50:07Z)
• Top 10 Open Challenges Steering the Future of Diffusion Language Model and Its Variants [85.33837131101342]
  We propose a strategic roadmap organized into four pillars: foundational infrastructure, algorithmic optimization, cognitive reasoning, and unified multimodal intelligence.<n>We argue that this transition is essential for developing next-generation AI capable of complex structural reasoning, dynamic self-correction, and seamless multimodal integration.
  arXiv  Detail & Related papers  (2026-01-20T14:58:23Z)
• Multi-Agent Collaborative Framework For Math Problem Generation [0.0]
  We introduce a collaborative multi-agent framework as a novel method of incorporating inference-time into automatic question generation.<n>Preliminary evaluations show that this collaborative multi-agent framework elevates the quality of generated educational content.
  arXiv  Detail & Related papers  (2025-11-06T01:24:07Z)
• From Logic to Language: A Trust Index for Problem Solving with LLMs [0.0]
  This paper introduces a unified framework to understand and contrast Large Language Models (LLMs)<n>We define and delineate the problem spaces addressable by formal languages versus natural language.<n>We therefore introduce a vector-valued trust index Q, which reflects solution quality and distinguishes the binary correctness of formal solutions from the continuous adequacy spectrum characteristic of natural language solutions.
  arXiv  Detail & Related papers  (2025-07-21T19:50:45Z)
• OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization [88.76091817642963]
  Recent large-scale language models (LLMs) with long Chain-of-such reasoning as DeepSeek-R1-have achieved impressive results on Olympiad-level mathematics.<n>We introduce OMEGA-Out-of-distribution Math Problems Evaluation with 3 Generalization Axes-a benchmark designed to evaluate three axes of out-of-distribution generalization.
  arXiv  Detail & Related papers  (2025-06-23T17:51:40Z)
• Can Theoretical Physics Research Benefit from Language Agents? [50.57057488167844]
  Large Language Models (LLMs) are rapidly advancing across diverse domains, yet their application in theoretical physics research is not yet mature.<n>This position paper argues that LLM agents can potentially help accelerate theoretical, computational, and applied physics when properly integrated with domain knowledge and toolbox.<n>We envision future physics-specialized LLMs that could handle multimodal data, propose testable hypotheses, and design experiments.
  arXiv  Detail & Related papers  (2025-06-06T16:20:06Z)
• ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent [50.508669199496474]
  We develop a ReAct-style LLM agent with the ability to reason and act upon external knowledge. We refine the agent through a ReST-like method that iteratively trains on previous trajectories. Starting from a prompted large model and after just two iterations of the algorithm, we can produce a fine-tuned small model.
  arXiv  Detail & Related papers  (2023-12-15T18:20:15Z)
• MacGyver: Are Large Language Models Creative Problem Solvers? [87.70522322728581]
  We explore the creative problem-solving capabilities of modern LLMs in a novel constrained setting.<n>We create MACGYVER, an automatically generated dataset consisting of over 1,600 real-world problems.<n>We present our collection to both LLMs and humans to compare and contrast their problem-solving abilities.
  arXiv  Detail & Related papers  (2023-11-16T08:52:27Z)
• MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledge [0.6708125191843434]
  A set of AI agents can solve mechanics tasks, here demonstrated for elasticity problems, via autonomous collaborations. A two-agent team can effectively write, execute and self-correct code, in order to apply finite element methods to solve classical elasticity problems. For more complex tasks, we construct a larger group of agents with enhanced division of labor among planning, formulating, coding, executing and criticizing the process and results.
  arXiv  Detail & Related papers  (2023-11-14T13:49:03Z)
• Automatic Generation of Word Problems for Academic Education via Natural Language Processing (NLP) [0.0]
  This thesis proposes an approach to generate diverse, context rich word problems. The proposed approach is proven to be effective in generating valid word problems for mathematical statistics.
  arXiv  Detail & Related papers  (2021-09-27T15:36:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.