Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning

• URL: http://arxiv.org/abs/2606.24064v1
• Date: Tue, 23 Jun 2026 02:14:12 GMT
• Title: Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning
• Abstract summary: Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories.<n>This trajectory-level imitation encourages memorization of instance-specific steps rather than acquisition of transferable problem-solving skills.<n>We propose Strategy-Guided Policy Optimization, which replaces instance-level trajectory imitation with reusable strategy distillation.
• Score: 76.93011742289768
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferring what to answer rather than how to reason. This trajectory-level imitation encourages memorization of instance-specific steps rather than acquisition of transferable problem-solving skills, limiting generalization to novel problems. We propose Strategy-Guided Policy Optimization (SGPO), which replaces instance-level trajectory imitation with reusable strategy distillation. SGPO extracts structured strategy descriptions from strong-model responses and, for each problem, constructs both autonomous and strategy-guided trajectories to enable direct comparison of the model's behavior with and without strategic guidance. The framework then addresses two key questions. For how to distill, a token-level forward-KL objective selectively transfers the distributional shift induced by strategy conditioning into the unguided policy, with proximal constraints ensuring stability. For when to distill, adaptive instance-level weighting strengthens guidance when autonomous exploration falls short and reduces it as the model's own competence grows. Experiments on four mathematical benchmarks across two model families show that SGPO consistently outperforms SFT, on-policy RL, and hybrid-policy baselines, improving the average score by 2.2 points over the strongest baseline on Qwen2.5-7B-Instruct. Analysis reveals that the forward-KL objective provides an inherently selective distillation signal that outperforms direct trajectory imitation, and that strategy distillation exhibits complementary scaling with base model capability.

Related papers

• Harnessing the Wisdom of LLM Crowds through Complementarity-Driven Iterative Collaboration [7.252833168419753]
  Large language models (LLMs) are increasingly deployed in enterprise settings, yet individual models remain bounded by model-specific capability limitations.<n>We propose WILC (Wisdom Integration of LLM Crowds), a framework grounded in two design principles.<n>WilC matches the average benchmark performance of GPT-5.2 at roughly 7 times lower estimated per-Query cost.
  arXiv  Detail & Related papers  (2026-07-31T07:13:59Z)
• S-GRPO: Unified Post-Training for Large Vision-Language Models [11.901218794806796]
  We propose Supervised Group Relative Policy Optimization (S-GRPO) for adapting Large Vision-Language Models (LVLMs)<n>S-GRPO integrates the guidance of imitation learning into the multi-trajectory exploration of preference optimization.<n>It gracefully bridges the gap between Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL)
  arXiv  Detail & Related papers  (2026-04-17T08:39:07Z)
• TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training [53.93696896939915]
  Training tool-use agents typically rely on Supervised Fine-Tuning (SFT) on successful trajectories and Reinforcement Learning (RL) on pass-rate-selected tasks.<n>We propose TopoCurate, an interaction-aware framework that projects multi-trial rollouts from the same task into a unified semantic quotient topology.<n>TopoCurate achieves consistent gains of 4.2% (SFT) and 6.9% (RL) over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-02T10:38:54Z)
• Strategy Executability in Mathematical Reasoning: Leveraging Human-Model Differences for Effective Guidance [86.46794021499511]
  We show a previously underexplored gap between strategy usage and strategy executability.<n>We propose Selective Strategy Retrieval (SSR), a test-time framework that explicitly models executability.<n> SSR yields reliable and consistent improvements over direct solving, in-context learning, and single-source guidance.
  arXiv  Detail & Related papers  (2026-02-26T03:34:23Z)
• Continuous-Utility Direct Preference Optimization [14.867957084669497]
  We introduce Continuous Utility Direct Preference Optimization (CU-DPO), a framework that aligns models to a portfolio of prompt-based cognitive strategies.<n>We prove that learning with K strategies yields a Theta(K log K) improvement in sample complexity over binary preferences.<n>We show that CU-DPO improves strategy selection accuracy from 35-46 percent to 68-78 percent across seven base models.
  arXiv  Detail & Related papers  (2026-01-31T23:15:32Z)
• MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization [56.074760766965085]
  Group-Relative Policy Optimization has emerged as an efficient paradigm for aligning Large Language Models (LLMs)<n>We propose MAESTRO, which treats reward scalarization as a dynamic latent policy, leveraging the model's terminal hidden states as a semantic bottleneck.<n>We formulate this as a contextual bandit problem within a bi-level optimization framework, where a lightweight Conductor network co-evolves with the policy by utilizing group-relative advantages as a meta-reward signal.
  arXiv  Detail & Related papers  (2026-01-12T05:02:48Z)
• Generative Actor Critic [74.04971271003869]
  Generative Actor Critic (GAC) is a novel framework that decouples sequential decision-making by reframing textitpolicy evaluation as learning a generative model of the joint distribution over trajectories and returns.<n>Experiments on Gym-MuJoCo and Maze2D benchmarks demonstrate GAC's strong offline performance and significantly enhanced offline-to-online improvement compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-25T06:31:11Z)
• Plan before Solving: Problem-Aware Strategy Routing for Mathematical Reasoning with LLMs [49.995906301946]
  Existing methods usually leverage a fixed strategy to guide Large Language Models (LLMs) to perform mathematical reasoning.<n>Our analysis reveals that the single strategy cannot adapt to problem-specific requirements and thus overlooks the trade-off between effectiveness and efficiency.<n>We propose Planning and Routing through Instance-Specific Modeling (PRISM), a novel framework that decouples mathematical reasoning into two stages: strategy planning and targeted execution.
  arXiv  Detail & Related papers  (2025-09-29T07:22:41Z)
• EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning [69.55982246413046]
  We propose explicit policy optimization (EPO) for strategic reasoning.<n>We train the strategic reasoning model via multi-turn reinforcement learning (RL),utilizing process rewards and iterative self-play.<n>Our findings reveal various collaborative reasoning mechanisms emergent in EPO and its effectiveness in generating novel strategies.
  arXiv  Detail & Related papers  (2025-02-18T03:15:55Z)

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.