ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling

• URL: http://arxiv.org/abs/2608.10928v1
• Date: Tue, 11 Aug 2026 13:58:07 GMT
• Title: ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling
• Abstract summary: ThinkRetrieve is a test-time scaling framework for large reasoning models.<n>It retrieves relevant exemplars at each intermediate step and injects them directly into the thinking trace.<n>It consistently improves accuracy over standard test-time scaling.
• Score: 60.48279351544583
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Reasoning Models (LRMs) improve performance by allocating additional inference-time compute to generate extended chain-of-thought reasoning. However, recent studies reveal that sequential test-time scaling often yields diminishing or even negative returns, as longer traces exhibit increased uncertainty, error compounding, and drift from the original problem. We propose ThinkRetrieve, a test-time scaling framework that augments the reasoning traces of LRMs with dynamically retrieved solved examples at each reasoning step. Given an external corpus of problems paired with step-by-step solutions, ThinkRetrieve retrieves relevant exemplars at each intermediate step and injects them directly into the thinking trace, providing the model with guidance on how to reason rather than merely what facts are relevant. Experiments across five reasoning models (1.5B--8B parameters) on GSM-8K, MATH-500, AIME 2025, and SciQ demonstrate that ThinkRetrieve consistently improves accuracy over standard test-time scaling, with relative gains of up to $60\%$ on AIME 2025.

Related papers

• Efficient Test-Time Scaling via Temporal Reasoning Aggregation [5.87118425760756]
  We propose TRACE, a training-free framework for efficient test-time scaling.<n>TRACE determines when to terminate reasoning based on temporal aggregation of multi-step evidence.<n>We show that TRACE reduces reasoning token usage by 25-30% on average while maintaining accuracy within 1-2% of full-length reasoning.
  arXiv  Detail & Related papers  (2026-04-19T07:39:40Z)
• Precedent-Informed Reasoning: Mitigating Overthinking in Large Reasoning Models via Test-Time Precedent Learning [37.40951956513094]
  Reasoning in Large Language Models (LLMs) often suffers from inefficient long chain-of-thought traces with redundant self-exploration and validation.<n>Inspired by human reasoning patterns where people solve new problems by leveraging past related cases to constrain search spaces and reduce trial-and-error, we propose Precedent Informed Reasoning (PIR)<n>PIR transforms LRMs'reasoning paradigm from exhaustive self-exploration to guided learning from precedents.
  arXiv  Detail & Related papers  (2026-02-16T04:17:46Z)
• NEAT: Neuron-Based Early Exit for Large Reasoning Models [37.88270573682948]
  Large Reasoning Models (LRMs) often suffer from emphoverthinking, a phenomenon in which redundant reasoning steps are generated after a correct solution has been reached.<n>Existing early reasoning exit methods rely on output-levels or trained probing models to skip redundant reasoning steps.<n>We propose textbfNEAT, a framework that monitors neuron-level activation dynamics to enable training-free early exits.
  arXiv  Detail & Related papers  (2026-02-02T12:09:59Z)
• APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards [61.52322047892064]
  Test-Time Scaling (TTS) has significantly enhanced the capabilities of Large Reasoning Models (LRMs)<n>We observe that LRMs frequently conduct repetitive self-verification without revision even after obtaining the final answer during the reasoning process.<n>We propose Anchor-based Process Reward (APR), a structure-aware reward shaping method that localizes the reasoning anchor and penalizes exclusively the post-anchor AST.
  arXiv  Detail & Related papers  (2026-01-31T14:53:20Z)
• Inverse Scaling in Test-Time Compute [51.16323216811257]
  Extending the reasoning length of Large Reasoning Models (LRMs) deteriorates performance.<n>We identify five distinct failure modes when models reason for longer.<n>These findings suggest that while test-time compute scaling remains promising for improving model capabilities, it may inadvertently reinforce problematic reasoning patterns.
  arXiv  Detail & Related papers  (2025-07-19T00:06:13Z)
• What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding [84.42056293290015]
  We analyze the token-level misalignment between reasoning and non-reasoning models.<n>Motivated by the Local Misalignment Diminish, we propose FoReaL-Decoding.<n>On four popular math-reasoning benchmarks, FoReaL-Decoding reduces theoretical FLOPs by 30 to 50% and trims CoT length by up to 40%.
  arXiv  Detail & Related papers  (2025-06-08T05:08:32Z)
• Let LRMs Break Free from Overthinking via Self-Braking Tuning [68.93713497579853]
  Large reasoning models (LRMs) have significantly enhanced their reasoning capabilities by generating longer chains of thought.<n>This performance gain comes at the cost of a substantial increase in redundant reasoning during the generation process.<n>We propose a novel framework, Self-Braking Tuning (SBT), which tackles overthinking from the perspective of allowing the model to regulate its own reasoning process.
  arXiv  Detail & Related papers  (2025-05-20T16:53:40Z)
• Dynamic Early Exit in Reasoning Models [21.30793518631921]
  Overthinking in long chain-of-thought (CoT) generation slows down the efficiency of problem solving, but also risks accuracy loss.<n>We propose a simple yet effective method that allows LLMs to self-truncate CoT sequences by early exit during generation.<n>Our method requires no additional training and can be seamlessly integrated into existing o1-like reasoning LLMs.
  arXiv  Detail & Related papers  (2025-04-22T13:36:53Z)
• Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning [108.07030347318624]
  We show that scaling with longer Chain of Thoughts (CoTs) can indeed impair the reasoning performance of Large Language Models (LLMs) in certain domains.<n>We propose a Thinking- Optimal Scaling strategy to teach models to adopt different reasoning efforts for deep thinking.<n>Our self-improvement models built upon Qwen2.5-32B-Instruct outperform other distillation-based 32B o1-like models across various math benchmarks.
  arXiv  Detail & Related papers  (2025-02-25T10:48:05Z)

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.