Thoughts-as-Planning: Latent World Models for Chain-of-Thoughts Optimization via Reinforcement Planning

• URL: http://arxiv.org/abs/2605.28842v1
• Date: Mon, 27 Apr 2026 08:18:12 GMT
• Title: Thoughts-as-Planning: Latent World Models for Chain-of-Thoughts Optimization via Reinforcement Planning
• Abstract summary: Thoughts-as-Planning is a novel framework that formalizes reasoning chain optimization as a sequential decision-making process.<n>Our method supports multi-scale abstraction, allowing reasoning chain edits at token, segment, and instruction levels to be integrated into a unified planner.
• Score: 40.65153547415224
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The success of large language models (LLMs) across diverse NLP tasks has elevated the importance of reasoning chain optimization as a critical step in aligning model behavior with task objectives. Existing reasoning chain tuning methods often rely on black-box heuristics or gradient-free search, which lack interpretability, generalization, and sample efficiency. In this work, we introduce \textbf{Thoughts-as-Planning}, a novel framework that formalizes reasoning chain optimization as a sequential decision-making process over a latent semantic space. We model the LLM as a partially observable environment and learn a latent world model that simulates the effect of reasoning chain edits on downstream outputs. A proximity-preserving embedding space is constructed to encode reasoning chain-response dynamics, enabling planning via gradient descent or reinforcement learning. Our method supports multi-scale abstraction, allowing reasoning chain edits at token, segment, and instruction levels to be integrated into a unified planner. Through extensive experiments on language understanding and generation tasks, we demonstrate that Thoughts-as-Planning outperforms state-of-the-art reasoning chain tuning baselines in efficiency, robustness, and generalization, while offering interpretability through its structured planning trajectory. Our code is available at https://github.com/FastLM/Thoughts-as-Planning.

Related papers

• Segment-Aligned Policy Optimization for Multi-Modal Reasoning [55.29606572822562]
  We propose a novel reinforcement learning paradigm that treats coherent reasoning steps, rather than tokens or full sequences as fundamental units of policy update.<n>Experiments on representative reasoning benchmarks demonstrate that SAPO consistently outperforms token-level and sequence-level policy optimization methods.<n>Our work underscores the importance of aligning reinforcement learning updates with the structure of reasoning, paving the way for more efficient and semantically grounded policy optimization in complex reasoning tasks.
  arXiv  Detail & Related papers  (2026-05-02T08:47:45Z)
• iCLP: Large Language Model Reasoning with Implicit Cognition Latent Planning [28.763018368302117]
  Large language models (LLMs) can perform reliable step-by-step reasoning during problem-solving.<n> generating accurate and effective textual plans remains challenging due to hallucinations.<n>We propose iCLP, a novel framework that enables LLMs to adaptively generate latent plans.
  arXiv  Detail & Related papers  (2025-12-30T06:19:04Z)
• Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planning [23.185497225384207]
  Large language models (LLMs) have demonstrated impressive capabilities across diverse tasks, yet their ability to perform structured symbolic planning remains limited.<n>We present a novel instruction tuning framework, PDDL-Instruct, designed to enhance LLMs' symbolic planning capabilities through logical chain-of-thought reasoning.
  arXiv  Detail & Related papers  (2025-09-14T02:42:34Z)
• Implicit Reasoning in Large Language Models: A Comprehensive Survey [67.53966514728383]
  Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks.<n>Recent studies have shifted attention from explicit chain-of-thought prompting toward implicit reasoning.<n>This survey introduces a taxonomy centered on execution paradigms, shifting the focus from representational forms to computational strategies.
  arXiv  Detail & Related papers  (2025-09-02T14:16:02Z)
• CRISP: Complex Reasoning with Interpretable Step-based Plans [15.656686375199921]
  We introduce CRISP (Complex Reasoning with Interpretable Step-based Plans), a dataset of high-level plans for mathematical reasoning and code generation.<n>We demonstrate that fine-tuning a small model on CRISP enables it to generate higher-quality plans than much larger models using few-shot prompting.
  arXiv  Detail & Related papers  (2025-07-09T11:40:24Z)
• Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning [94.76546523689113]
  We introduce CodePlan, a framework that generates and follows textcode-form plans -- pseudocode that outlines high-level, structured reasoning processes. CodePlan effectively captures the rich semantics and control flows inherent to sophisticated reasoning tasks. It achieves a 25.1% relative improvement compared with directly generating responses.
  arXiv  Detail & Related papers  (2024-09-19T04:13:58Z)
• Exploring and Benchmarking the Planning Capabilities of Large Language Models [57.23454975238014]
  This work lays the foundations for improving planning capabilities of large language models (LLMs) We construct a comprehensive benchmark suite encompassing both classical planning benchmarks and natural language scenarios. We investigate the use of many-shot in-context learning to enhance LLM planning, exploring the relationship between increased context length and improved planning performance.
  arXiv  Detail & Related papers  (2024-06-18T22:57:06Z)
• Guiding Language Model Reasoning with Planning Tokens [122.43639723387516]
  Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks. We propose a hierarchical generation scheme to encourage a more structural generation of chain-of-thought steps. Our approach requires a negligible increase in trainable parameters (0.001%) and can be applied through either full fine-tuning or a more parameter-efficient scheme.
  arXiv  Detail & Related papers  (2023-10-09T13:29:37Z)

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.