Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning

• URL: http://arxiv.org/abs/2504.04383v2
• Date: Tue, 15 Apr 2025 14:07:31 GMT
• Title: Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning
• Authors: Ximing Lu, Seungju Han, David Acuna, Hyunwoo Kim, Jaehun Jung, Shrimai Prabhumoye, Niklas Muennighoff, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Yejin Choi,
• Abstract summary: We introduce Retro-Search, an MCTS-inspired search algorithm, for distilling higher quality reasoning paths from large models.<n>Retro-Search retrospectively revises reasoning paths to discover better, yet shorter traces, which can lead to student models with enhanced reasoning capabilities.<n>Our approach can enable two use cases: self-improvement, where models are fine-tuned on their own Retro-Search-ed traces, and weak-to-strong improvement.
• Score: 84.2749507577386
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large reasoning models exhibit remarkable reasoning capabilities via long, elaborate reasoning trajectories. Supervised fine-tuning on such reasoning traces, also known as distillation, can be a cost-effective way to boost reasoning capabilities of student models. However, empirical observations reveal that these reasoning trajectories are often suboptimal, switching excessively between different lines of thought, resulting in under-thinking, over-thinking, and even degenerate responses. We introduce Retro-Search, an MCTS-inspired search algorithm, for distilling higher quality reasoning paths from large reasoning models. Retro-Search retrospectively revises reasoning paths to discover better, yet shorter traces, which can then lead to student models with enhanced reasoning capabilities with shorter, thus faster inference. Our approach can enable two use cases: self-improvement, where models are fine-tuned on their own Retro-Search-ed thought traces, and weak-to-strong improvement, where a weaker model revises stronger model's thought traces via Retro-Search. For self-improving, R1-distill-7B, fine-tuned on its own Retro-Search-ed traces, reduces the average reasoning length by 31.2% while improving performance by 7.7% across seven math benchmarks. For weak-to-strong improvement, we retrospectively revise R1-671B's traces from the OpenThoughts dataset using R1-distill-32B as the Retro-Search-er, a model 20x smaller. Qwen2.5-32B, fine-tuned on this refined data, achieves performance comparable to R1-distill-32B, yielding an 11.3% reduction in reasoning length and a 2.4% performance improvement compared to fine-tuning on the original OpenThoughts data. Our work counters recently emergent viewpoints that question the relevance of search algorithms in the era of large reasoning models, by demonstrating that there are still opportunities for algorithmic advancements, even for frontier models.

Related papers

• Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models [49.598776427454176]
  Large Reasoning Models (LRMs) have gradually become a research hotspot due to their outstanding performance in handling complex tasks.<n>However, with the widespread application of these models, the problem of overthinking has gradually emerged.<n>Various efficient reasoning methods have been proposed, aiming to reduce the length of reasoning paths without compromising model performance and reasoning capability.
  arXiv  Detail & Related papers  (2025-08-04T06:54:31Z)
• ASTRO: Teaching Language Models to Reason by Reflecting and Backtracking In-Context [66.15505423059234]
  We introduce ASTRO, a framework for training language models to reason like search algorithms.<n>We apply ASTRO to the Llama 3 family of models and achieve absolute performance gains of 16.4% on MATH-500, 26.9% on AMC 2023, and 20.0% on AIME 2024.
  arXiv  Detail & Related papers  (2025-07-01T04:10:15Z)
• Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models [29.615519143908998]
  Self-affirmation reflections are redundant reflective steps that affirm prior content and often occur after the already correct reasoning steps.<n>We show that suppressing self-affirmation reflections reduces output length without degrading accuracy across multiple models.<n>We also improve current train-based method by explicitly suppressing such reflections.
  arXiv  Detail & Related papers  (2025-06-14T05:30:09Z)
• Does Thinking More always Help? Understanding Test-Time Scaling in Reasoning Models [103.03315678501546]
  Extending thinking traces using prompts like "Wait" or "Let me rethink" can improve performance.<n>This raises a natural question: Does thinking more at test-time truly lead to better reasoning?<n>We show a consistent pattern of initial performance improvements from additional thinking followed by a decline, due to "overthinking"
  arXiv  Detail & Related papers  (2025-06-04T17:55:09Z)
• Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models [68.96619605651155]
  Large reasoning models (LRMs) may drastically increase the output length due to overthinking.<n>We propose a dynamic optimization framework that segments model-generated reasoning paths into distinct thinking patterns.<n>Our method achieves up to a 12% accuracy improvement and reducing token usage from approximately 5,000 to 3,000 tokens.
  arXiv  Detail & Related papers  (2025-05-27T20:59:29Z)
• ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning [1.170732359523702]
  Reasoning models such as OpenAI o3 and DeepSeek-R1 have demonstrated strong performance on reasoning-intensive tasks. Long reasoning traces can facilitate a more thorough exploration of solution paths for complex problems. We introduce ShorterBetter, a simple yet effective reinforcement learning methed that enables reasoning language models to discover their own optimal CoT lengths.
  arXiv  Detail & Related papers  (2025-04-30T07:04:19Z)
• Think Deep, Think Fast: Investigating Efficiency of Verifier-free Inference-time-scaling Methods [39.89239733570008]
  This work conducts a comprehensive analysis of inference-time scaling methods for both reasoning and non-reasoning models. We find that non-reasoning models, even with an extremely high inference budget, still fall substantially behind reasoning models. For reasoning models, majority voting proves to be a robust inference strategy, generally competitive or outperforming other more sophisticated ITC methods.
  arXiv  Detail & Related papers  (2025-04-18T19:32:55Z)
• Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time [14.963731580129892]
  We introduce Speculative Thinking, a training-free framework that enables large reasoning models to guide smaller ones during inference at the reasoning level. By strategically delegating reflective steps to a more capable model, our method significantly boosts the reasoning accuracy of reasoning models while shortening their output.
  arXiv  Detail & Related papers  (2025-04-12T21:25:32Z)
• To Backtrack or Not to Backtrack: When Sequential Search Limits Model Reasoning [31.21491548356213]
  Backtracking naturally scales test-time compute by enabling sequential, linearized exploration via long chain-of-thought (CoT) generation. Despite the growing adoption of sequential search, its advantages over parallel sampling remain poorly understood. We show that models with backtracking capabilities benefit significantly from RL fine-tuning, while models without backtracking see limited, mixed gains.
  arXiv  Detail & Related papers  (2025-04-09T17:12:49Z)
• R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model [70.77691645678804]
  We present the first successful replication of emergent characteristics for multimodal reasoning on only a non-SFT 2B model.<n>Our model achieves 59.47% accuracy on CVBench, outperforming the base model by approximately 30% and exceeding both SFT setting by 2%.<n>In addition, we share our failed attempts and insights in attempting to achieve R1-like reasoning using RL with instruct models.
  arXiv  Detail & Related papers  (2025-03-07T04:21:47Z)
• Benchmarking Reasoning Robustness in Large Language Models [76.79744000300363]
  We find significant performance degradation on novel or incomplete data. These findings highlight the reliance on recall over rigorous logical inference. This paper introduces a novel benchmark, termed as Math-RoB, that exploits hallucinations triggered by missing information to expose reasoning gaps.
  arXiv  Detail & Related papers  (2025-03-06T15:36:06Z)
• Reverse Thinking Makes LLMs Stronger Reasoners [90.42357659849215]
  RevThink is a framework composed of data augmentation and learning objectives.<n> Experiments across 12 datasets show an average 13.53% improvement over the student model's zero-shot performance.<n>RevThink also exhibits strong generalization to out-of-distribution held-out datasets.
  arXiv  Detail & Related papers  (2024-11-29T17:27:05Z)
• Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding [74.31981011985681]
  Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. We introduce LaTent Reasoning Optimization (LaTRO), a principled framework that formulates reasoning as sampling from a latent distribution. We validate LaTRO through experiments on GSM8K and ARC-Challenge datasets using multiple model architectures.
  arXiv  Detail & Related papers  (2024-11-06T22:02:30Z)
• SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction [89.56181323849512]
  SuperCorrect is a novel two-stage framework that uses a large teacher model to supervise and correct both the reasoning and reflection processes of a smaller student model.<n>In the first stage, we extract hierarchical high-level and detailed thought templates from the teacher model to guide the student model in eliciting more fine-grained reasoning thoughts.<n>In the second stage, we introduce cross-model collaborative direct preference optimization (DPO) to enhance the self-correction abilities of the student model.
  arXiv  Detail & Related papers  (2024-10-11T17:25:52Z)

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.