Correct, Concise and Complete: Multi-stage Training For Adaptive Reasoning

• URL: http://arxiv.org/abs/2601.02972v1
• Date: Tue, 06 Jan 2026 12:31:51 GMT
• Title: Correct, Concise and Complete: Multi-stage Training For Adaptive Reasoning
• Authors: Nathanaël Carraz Rakotonirina, Ren Pang, Neha Anna John, Michael Bohlke-Schneider, Momchil Hardalov,
• Abstract summary: We propose a multi-stage efficient reasoning method that combines supervised fine-tuning and reinforcement learning.<n>Our approach reduces response length by an average of 28% for 8B models and 40% for 32B models.<n>It achieves a superior trade-off compared to more complex state-of-the-art efficient reasoning methods.
• Score: 11.179446105672461
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The reasoning capabilities of large language models (LLMs) have improved substantially through increased test-time computation, typically in the form of intermediate tokens known as chain-of-thought (CoT). However, CoT often becomes unnecessarily long, increasing computation cost without actual accuracy gains or sometimes even degrading performance, a phenomenon known as ``overthinking''. We propose a multi-stage efficient reasoning method that combines supervised fine-tuning -- via rejection sampling or reasoning trace reformatting -- with reinforcement learning using an adaptive length penalty. We introduce a lightweight reward function that penalizes tokens generated after the first correct answer but encouraging self-verification only when beneficial. We conduct a holistic evaluation across seven diverse reasoning tasks, analyzing the accuracy--response length trade-off. Our approach reduces response length by an average of 28\% for 8B models and 40\% for 32B models, while incurring only minor performance drops of 1.6 and 2.5 points, respectively. Despite its conceptual simplicity, it achieves a superior trade-off compared to more complex state-of-the-art efficient reasoning methods, scoring 76.6, in terms of the area under the Overthinking-Adjusted Accuracy curve ($\text{AUC}_{\text{OAA}}$) -- 5 points above the base model and 2.5 points above the second-best approach.

Related papers

• Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning [66.22060690012512]
  Large reasoning models improve with more test-time computation, but often overthink, producing unnecessarily long chains-of-thought that raise cost without improving accuracy.<n>We propose Step-wise Adaptive Penalization (SWAP), a fine-grained framework that allocates length reduction across steps based on intrinsic contribution.
  arXiv  Detail & Related papers  (2026-02-27T20:23:59Z)
• On-Policy Supervised Fine-Tuning for Efficient Reasoning [27.67711115864118]
  Large reasoning models (LRMs) are commonly trained with reinforcement learning (RL) to explore long chain-of-thought reasoning.<n>Recent methods add multi-reward objectives to jointly optimize correctness and brevity, but these complex extensions often destabilize training and yield suboptimal trade-offs.<n>We propose a simplified training strategy on-policy SFT, which reduces CoT length by up to 80 while maintaining original accuracy.
  arXiv  Detail & Related papers  (2026-02-13T19:16:39Z)
• Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty [42.57318973226598]
  ARLCP is a reinforcement learning framework designed to balance reasoning efficiency and solution accuracy.<n>We evaluate our method on five mathematical reasoning benchmarks using DeepSeek-R1-Distill-Qwen-1.5B and DeepSeek-R1-Distill-Qwen-7B models.
  arXiv  Detail & Related papers  (2026-02-12T16:04:00Z)
• ENTRA: Entropy-Based Redundancy Avoidance in Large Language Model Reasoning [30.786062954495403]
  Large Reasoning Models (LRMs) often suffer from overthinking, generating unnecessarily long reasoning chains even for simple tasks.<n>We propose ENTRA, an entropy-based training framework that suppresses redundant reasoning while preserving performance.
  arXiv  Detail & Related papers  (2026-01-12T01:26:30Z)
• Efficient Reasoning via Reward Model [24.105621725286497]
  Reinforcement learning with verifiable rewards (RLVR) has been shown to enhance the reasoning capabilities of large language models (LLMs)<n>LRMs such as DeepSeek-R1 and OpenAI o1 often generate verbose responses containing redundant or irrelevant reasoning step-a phenomenon known as overthinking.<n>We introduce a novel reward formulation named Conciseness Reward Function (CRF) with explicit dependency between the outcome reward and conciseness score.
  arXiv  Detail & Related papers  (2025-11-12T09:51:07Z)
• DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching [54.98126916293868]
  Large Reasoning Models (LRMs) produce excessively long chain-of-thought traces that degrade accuracy.<n>We propose a model-agnostic decoding framework that sketches the reasoning space by branching at high-entropy tokens and applies early stopping to select the shortest completed reasoning path.<n>This approach approximates the optimal solution that enhances both efficiency and accuracy, without requiring additional training or supervision.
  arXiv  Detail & Related papers  (2025-11-01T17:41:28Z)
• Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression [68.69801176669843]
  We propose an online post-training RL method that prunes redundant steps and estimates difficulty.<n> TRAAC (Think Right with Adaptive, Attentive Compression) achieves an average absolute accuracy gain of 8.4%.<n>Although our models are trained on math datasets, they show accuracy and efficiency gains on out-of-distribution non-math datasets.
  arXiv  Detail & Related papers  (2025-10-02T02:00:20Z)
• Inducing Faithfulness in Structured Reasoning via Counterfactual Sensitivity [6.908972852063454]
  Large language models often generate a correct answer while relying on a flawed or irrelevant reasoning trace.<n>This paper introduces textbfCounterfactual Sensitivity Regularization (CSR), a novel training objective.<n>CSR improves faithfulness over standard fine-tuning and process supervision by up to 70 percentage points.
  arXiv  Detail & Related papers  (2025-09-01T15:18:46Z)
• Stable Reinforcement Learning for Efficient Reasoning [2.838966689544288]
  GRPO-$lambda$ is an efficient and stabilized variant of GRPO.<n>It dynamically adjusts the reward strategy by monitoring the correctness ratio.<n>It improves average accuracy by 1.48% while reducing CoT sequence length by 47.3%.
  arXiv  Detail & Related papers  (2025-05-23T16:43:03Z)
• Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens [51.90059610606049]
  This paper revisits the efficiency of such reasoning processes through an information-theoretic lens.<n>We propose two metrics, InfoBias and InfoGain, to quantify divergence from ideal reasoning paths and stepwise information contribution.<n>Motivated by these findings, we introduce an entropy-based Adaptive Think strategy that dynamically halts reasoning once confidence is sufficiently high.
  arXiv  Detail & Related papers  (2025-05-23T13:38:56Z)
• Fractured Chain-of-Thought Reasoning [61.647243580650446]
  We introduce Fractured Sampling, a unified inference-time strategy that interpolates between full CoT and solution-only sampling.<n>We show that Fractured Sampling consistently achieves superior accuracy-cost trade-offs, yielding steep log-linear scaling gains in Pass@k versus token budget.
  arXiv  Detail & Related papers  (2025-05-19T11:30:41Z)
• ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning [1.0416697066889342]
  We propose a simple yet effective reinforcement learning method that enables reasoning models to learn their own optimal CoT lengths without manual supervision.<n>ShorterBetter achieves 50%-80% reduction in output lengths in both in-domain and out-of-domain reasoning tasks.<n>Our reasoning trace analysis shows that ShorterBetter refines the structure of the reasoning traces by reducing unnecessary repetition, excessive self-verification, and over-exploration of alternatives.
  arXiv  Detail & Related papers  (2025-04-30T07:04:19Z)
• Learning Adaptive Parallel Reasoning with Language Models [70.1745752819628]
  We propose Adaptive Parallel Reasoning (APR), a novel reasoning framework that enables language models to orchestrate both serialized and parallel computations end-to-end.<n> APR generalizes existing reasoning methods by enabling adaptive multi-threaded inference using spawn() and join() operations.<n>A key innovation is our end-to-end reinforcement learning strategy, optimizing both parent and child inference threads to enhance task success rate without requiring predefined reasoning structures.
  arXiv  Detail & Related papers  (2025-04-21T22:29:02Z)

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.