StarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling

• URL: http://arxiv.org/abs/2606.15197v2
• Date: Thu, 18 Jun 2026 04:46:26 GMT
• Title: StarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling
• Abstract summary: We propose StarOR, a search-and-adaptation framework that couples MCTS with Test-Time Reinforcement Learning for optimization modeling.<n>StarOR decomposes the modeling process into four stages and updates a transient LoRA adapter via GRPO at each non-terminal node.<n> Experiments across five optimization benchmarks show that StarOR achieves state-of-the-art performance even with a 4B backbone.
• Score: 13.71352763893512
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Optimization modeling is inherently hierarchical, requiring a precise sequence of symbolic commitments. Traditional learning-based automated optimization modeling methods improve modeling policies through large-scale annotated or curated training data, but are costly to adapt to new problem distributions. Meanwhile, one-shot generation remains brittle in hierarchical modeling, where early symbolic errors can propagate into invalid formulations. Test-time scaling offers a promising alternative by enabling structural exploration with additional instance-level computation; however, existing search-based methods typically rely on a fixed policy, causing repeated rollouts to inherit similar modeling biases and providing limited credit assignment for intermediate decisions. To address these limitations, we propose StarOR, a synergistic search-and-adaptation framework that couples MCTS with Test-Time Reinforcement Learning for optimization modeling. StarOR decomposes the modeling process into four stages and updates a transient LoRA adapter via GRPO at each non-terminal node. By using MCTS-generated siblings as local comparison sets, StarOR transforms search-time exploration into instance-specific policy refinement. Moreover, an unsupervised multi-faceted reward system provides fine-grained feedback for intermediate formulation decisions without ground-truth labels. Experiments across five optimization benchmarks show that StarOR achieves state-of-the-art performance even with a 4B backbone, outperforming existing methods and the frontier LLMs.

Related papers

• Efficient Test-time Inference for Generative Planning Models [2.993222488868623]
  We show that a modified version of a classical Open-Closed List (OCL) search provides just such an efficient inference procedure.<n>Our algorithm synergizes two learned components: a generative model that performs fast rollouts from intermediate states and a model that prioritizes among candidate reasoning paths.
  arXiv  Detail & Related papers  (2026-05-30T08:46:44Z)
• Dual-Phase LLM Reasoning: Self-Evolved Mathematical Frameworks [48.105258051884384]
  This paper proposes a new two-stage training framework that enhances models' self-correction capabilities.<n>During the first stage, a multi-turn dialogue strategy guides the model to generate long chain-of-thought (CoT) data.<n>The second stage employs a difficulty-aware rejection sampling mechanism to dynamically optimize data distribution.
  arXiv  Detail & Related papers  (2026-01-09T08:19:11Z)
• PROMISE: Process Reward Models Unlock Test-Time Scaling Laws in Generative Recommendations [52.67948063133533]
  Generative Recommendation has emerged as a promising paradigm, reformulating recommendation as a sequence-to-sequence generation task over hierarchical Semantic IDs.<n>Existing methods suffer from a critical issue we term Semantic Drift, where errors in early, high-level tokens irreversibly divert the generation trajectory into irrelevant semantic subspaces.<n>We propose Promise, a novel framework that integrates dense, step-by-step verification into generative models.
  arXiv  Detail & Related papers  (2026-01-08T07:38:46Z)
• 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)
• Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models [99.85131798240808]
  We introduce a novel generative framework called textitGuided Topology Diffusion (GTD)<n>Inspired by conditional discrete graph diffusion models, GTD formulates topology synthesis as an iterative construction process.<n>At each step, the generation is steered by a lightweight proxy model that predicts multi-objective rewards.<n>Experiments show that GTD can generate highly task-adaptive, sparse, and efficient communication topologies.
  arXiv  Detail & Related papers  (2025-10-09T05:28:28Z)
• Matching Markets Meet LLMs: Algorithmic Reasoning with Ranked Preferences [12.277072346419748]
  We study matching markets, a core framework behind applications like resource allocation and ride-sharing.<n>We evaluate several state-of-the-art models on a hierarchy of preference-based reasoning tasks.<n>Surprisingly, even top-performing models with advanced reasoning struggle to resolve instability in large markets.
  arXiv  Detail & Related papers  (2025-06-04T21:51:15Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning [56.273799410256075]
  The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to optimize the reasoning path. The framework has been tested on general and advanced benchmarks, showing superior performance in terms of search efficiency and problem-solving capability.
  arXiv  Detail & Related papers  (2024-10-03T18:12:29Z)
• When to Update Your Model: Constrained Model-based Reinforcement Learning [50.74369835934703]
  We propose a novel and general theoretical scheme for a non-decreasing performance guarantee of model-based RL (MBRL) Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns.
  arXiv  Detail & Related papers  (2022-10-15T17:57:43Z)

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.