Precedent-Informed Reasoning: Mitigating Overthinking in Large Reasoning Models via Test-Time Precedent Learning
- URL: http://arxiv.org/abs/2602.14451v1
- Date: Mon, 16 Feb 2026 04:17:46 GMT
- Title: Precedent-Informed Reasoning: Mitigating Overthinking in Large Reasoning Models via Test-Time Precedent Learning
- Authors: Qianyue Wang, Jinwu Hu, Huanxiang Lin, Bolin Chen, Zhiquan Wen, Yaofo Chen, Yu Rong, Mingkui Tan,
- Abstract summary: 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.
- Score: 37.40951956513094
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Reasoning in Large Language Models (LLMs) often suffers from inefficient long chain-of-thought traces with redundant self-exploration and validation, which inflate computational costs and even degrade performance. 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) transforming LRMs'reasoning paradigm from exhaustive self-exploration to guided learning from precedents. PIR addresses two key challenges: what precedents to adopt and how to utilize them. First, Adaptive Precedent Selection (APS) constructs, for each question and LRM, a compact set of precedents that are both semantically related and informative for the model. It ranks examples by a joint score with semantic similarity and model perplexity, then adapts the amount of precedents to maximize perplexity reduction. Second, Test-time Experience Internalization (TEI) is treated as the test-time learning on precedent-informed instruction, updating lightweight adapters to internalize solution patterns and use them as a prior during subsequent reasoning. Experiments across mathematical reasoning, scientific QA, and code generation demonstrate that PIR consistently shortens reasoning traces while maintaining or improving final accuracy across LLMs, yielding outstanding accuracy-efficiency trade-offs.
Related papers
- Beyond What Seems Necessary: Hidden Gains from Scaling Training-Time Reasoning Length under Outcome Supervision [30.75583081407994]
Training LLMs to think and reason for longer has become a key ingredient in building state-of-the-art models.<n>Recent efforts pursue this in different ways, such as RL fine-tuning to elicit long CoT or scaling latent reasoning through architectural recurrence.<n>Under outcome-only supervision, out-of-distribution (OOD) performance can continue improving as training-time reasoning length increases.
arXiv Detail & Related papers (2026-01-31T22:54:45Z) - 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) - Structured Reasoning for Large Language Models [59.215789462977206]
We propose Structured Reasoning (SCR), a framework that decouples reasoning trajectories into explicit, evaluable, and trainable components.<n>SCR substantially improves reasoning efficiency and self-verification.<n>Compared with existing reasoning paradigms, it reduces output token length by up to 50%.
arXiv Detail & Related papers (2026-01-12T04:04:01Z) - Reasoning Pattern Alignment Merging for Adaptive Reasoning [48.347817456299104]
Reasoning Pattern Alignment Merging (RPAM)<n>RPAM is a layer-wise model merging framework based on feature alignment to facilitate query-adaptive reasoning.<n> Experiments on seven widely used reasoning benchmarks show that RPAM substantially reduces inference cost while maintaining strong performance.
arXiv Detail & Related papers (2026-01-07T01:36:39Z) - Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search [62.1546099504045]
We propose a dual-phase test-time scaling framework that separates reasoning into planning and execution.<n>Specifically, we decompose reasoning trajectories and develop reward models for each phase, enabling the search to explore and prune plans and executions separately.<n> Experiments on both mathematical reasoning and code generation benchmarks demonstrate that our approach consistently improves accuracy while reducing computation redundant.
arXiv Detail & Related papers (2025-09-29T19:27:23Z) - Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors [45.578570554635775]
Large language models (LLMs) now solve multi-step problems by emitting extended chains of thought.<n>We study a simple mechanism that converts recurring reasoning fragments into concise, reusable "behaviors"<n>These behaviors are stored in a "behavior handbook" which supplies them to the model in-context at inference or distills them into parameters via supervised fine-tuning.
arXiv Detail & Related papers (2025-09-16T16:44:26Z) - Accelerating LLM Reasoning via Early Rejection with Partial Reward Modeling [12.835376812101323]
We introduce the hypothesis that PRMs are also Partial Reward Models.<n>This allows for principled early rejection based on intermediate token-level signals.<n>On math reasoning benchmarks, our method achieves up to 1.4$times$-9$times$ reduction in inference FLOPs without degrading final performance.
arXiv Detail & Related papers (2025-08-04T00:58:56Z) - Consistency-based Abductive Reasoning over Perceptual Errors of Multiple Pre-trained Models in Novel Environments [5.5855749614100825]
This paper addresses the hypothesis that leveraging multiple pre-trained models can mitigate this recall reduction.<n>We formulate the challenge of identifying and managing conflicting predictions from various models as a consistency-based abduction problem.<n>Our results validate the use of consistency-based abduction as an effective mechanism to robustly integrate knowledge from multiple imperfect models in challenging, novel scenarios.
arXiv Detail & Related papers (2025-05-25T23:17:47Z) - The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models [69.798277882245]
We introduce Unsupervised Prefix Fine-Tuning (UPFT) to enhance large language models' reasoning efficiency.<n>UPFT removes the need for labeled data or exhaustive sampling.<n> Experiments show that UPFT matches the performance of supervised methods.
arXiv Detail & Related papers (2025-03-04T18:56:03Z)
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.