Large Reasoning Models

Ask about this topic

Overview

Large reasoning models study how language models can solve difficult problems by allocating computation across intermediate steps, tools, and alternative solution paths. Common approaches include reinforcement learning with verifiable rewards, supervised reasoning-trace distillation, tool use, search over sequential or parallel paths, and latent recurrent computation. Evaluation spans mathematics, coding, science question answering, logic, and multimodal tasks, measuring not only accuracy but also compute use, robustness, and the quality of intermediate reasoning. A central tension is that extra thinking can help on hard problems but also produce loops, errors, and safety risks, so researchers are developing adaptive stopping and compression while testing whether reasoning traces reliably reflect how answers are formed.

Latest papers

CardsList

339 papers25 papers in the last four weeks, up 4% on the four weeks before. 0.1% of all new papers.

Apr 16, 2026

TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models

Large Reasoning Models (LRMs) achieve strong performance on complex tasks through extended chains of thought but suffer from high inference latency due to autoregressive reasoning. Recent work explores using Small Reasoning Models (SRMs) to accelerate LRM inference. In this paper, we systematically characterize the capability boundaries of SRMs and identify three common types of reasoning risks: (1) path divergence, where SRMs lack the strategic ability to construct an initial plan, causing reasoning to deviate from the most probable path; (2) cognitive overload, where SRMs fail to solve particularly difficult steps; and (3) recovery inability, where SRMs lack robust self-reflection and error correction mechanisms. To address these challenges, we propose TrigReason, a trigger-based collaborative reasoning framework that replaces continuous polling with selective intervention. TrigReason delegates most reasoning to the SRM and activates LRM intervention only when necessary-during initial strategic planning (strategic priming trigger), upon detecting extraordinary overconfidence (cognitive offload trigger), or when reasoning falls into unproductive loops (intervention request trigger). The evaluation results on AIME24, AIME25, and GPQA-D indicate that TrigReason matches the accuracy of full LRMs and SpecReason, while offloading 1.70x - 4.79x more reasoning steps to SRMs. Under edge-cloud conditions, TrigReason reduces latency by 43.9% and API cost by 73.3%. Our code is available at https://github.com/QQQ-yi/TrigReason

Yi Zhao, Yajuan Peng, Cam-Tu Nguyen +4

AGI Institute, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · Shanghai Key Laboratory for Intelligent Information Processing, Fudan University · State Key Laboratory for Novel Software Technology, Nanjing University +2

Efficient Language Model ReasoningLLM Inference AccelerationEfficient Language Model InferenceMulti-Agent ReasoningMulti-LLM CollaborationLarge Reasoning Models
AskPDF
Apr 15, 2026

Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models

Professional fact-checkers rely on domain knowledge and deep contextual understanding to verify claims. Large language models (LLMs) and large reasoning models (LRMs) lack such grounding and primarily reason from available evidence alone, creating a mismatch between expert-led and fully automated claim verification. To mitigate this gap, we posit human-AI collaboration as a more promising path forward, where expert feedback, grounded in real-world knowledge and domain expertise, guides the model's reasoning. However, existing LRMs are hard to calibrate to natural language feedback, particularly in a multi-turn interaction setup. We propose Co-FactChecker, a framework for human-AI collaborative claim verification. We introduce a new interaction paradigm that treats the model's thinking trace as a shared scratchpad. Co-FactChecker translates expert feedback into trace-edits that introduce targeted modifications to the trace, sidestepping the shortcomings of dialogue-based interaction. We provide theoretical results showing that trace-editing offers advantages over multi-turn dialogue, and our automatic evaluations demonstrate that Co-FactChecker outperforms existing autonomous and human-AI collaboration approaches. Human evaluations further show that Co-FactChecker is preferred over multi-turn dialogue, producing higher quality reasoning and verdicts along with relatively easier to interpret and more useful thinking traces.

Dhruv Sahnan, Subhabrata Dutta, Tanmoy Chakraborty +2

MBZUAI, UAE · TU Darmstadt, Germany · IIT Delhi, India

Automated Fact-CheckingHuman-AI CollaborationLarge Reasoning Models
AskPDF
Apr 15, 2026

Quantifying and Understanding Uncertainty in Large Reasoning Models

Large Reasoning Models (LRMs) have recently demonstrated significant improvements in complex reasoning. While quantifying generation uncertainty in LRMs is crucial, traditional methods are often insufficient because they do not provide finite-sample guarantees for reasoning-answer generation. Conformal prediction (CP) stands out as a distribution-free and model-agnostic methodology that constructs statistically rigorous uncertainty sets. However, existing CP methods ignore the logical connection between the reasoning trace and the final answer. Additionally, prior studies fail to interpret the origins of uncertainty coverage for LRMs as they typically overlook the specific training factors driving valid reasoning. Notably, it is challenging to disentangle reasoning quality from answer correctness when quantifying uncertainty, while simultaneously establishing theoretical guarantees for computationally efficient explanation methods. To address these challenges, we first propose a novel methodology that quantifies uncertainty in the reasoning-answer structure with statistical guarantees. Subsequently, we develop a unified example-to-step explanation framework using Shapley values that identifies a provably sufficient subset of training examples and their key reasoning steps to preserve the guarantees. We also provide theoretical analyses of our proposed methods. Extensive experiments on challenging reasoning datasets verify the effectiveness of the proposed methods.

Yangyi Li, Chenxu Zhao, Mengdi Huai

Department of Computer Science, Iowa State University

LLM Uncertainty EstimationLarge Reasoning ModelsConformal Prediction
AskPDF
Apr 15, 2026

Empirical Evidence of Complexity-Induced Limits in Large Language Models on Finite Discrete State-Space Problems with Explicit Validity Constraints

Large Language Models (LLMs) are increasingly described as possessing strong reasoning capabilities, supported by high performance on mathematical, logical, and planning benchmarks. However, most existing evaluations rely on aggregate accuracy over fixed datasets, obscuring how reasoning behavior evolves as task complexity increases. In this work, we introduce a controlled benchmarking framework to systematically evaluate the robustness of reasoning in Large Reasoning Models (LRMs) under progressively increasing problem complexity. We construct a suite of nine classical reasoning tasks: Boolean Satisfiability, Cryptarithmetic, Graph Coloring, River Crossing, Tower of Hanoi, Water Jug, Checker Jumping, Sudoku, and Rubik's Cube, each parameterized to precisely control complexity while preserving underlying semantics. Using deterministic validators, we evaluate multiple open and proprietary LRMs across low, intermediate, and high complexity regimes, ensuring that only fully valid solutions are accepted. Our results reveal a consistent phase transition like behavior: models achieve high accuracy at low complexity but degrade sharply beyond task specific complexity thresholds. We formalize this phenomenon as reasoning collapse. Across tasks, we observe substantial accuracy declines, often exceeding 50%, accompanied by inconsistent reasoning traces, constraint violations, loss of state tracking, and confidently incorrect outputs. Increased reasoning length does not reliably improve correctness, and gains in one problem family do not generalize to others. These findings highlight the need for evaluation methodologies that move beyond static benchmarks and explicitly measure reasoning robustness under controlled complexity.

Md. Fahad Ullah Utsho, Mohd. Ruhul Ameen, Akif Islam +2

Department of Information and Communication Engineering, University of Rajshahi, Bangladesh · College of Engineering and Computer Sciences, Marshall University, Huntington, WV, USA · Department of Computer Science and Engineering, University of Rajshahi, Bangladesh

LLM EvaluationLarge Reasoning ModelsReasoning Consistency in Language ModelsConstraint Satisfaction
AskPDF
Apr 14, 2026

Heuristic Classification of Thoughts Prompting (HCoT): Integrating Expert System Heuristics for Structured Reasoning into Large Language Models

This paper addresses two limitations of large language models (LLMs) in solving complex problems: (1) their reasoning processes exhibit Bayesian-like stochastic generation, where each token is sampled from a context-dependent probability distribution, leading to inherently random decision trajectories rather than deterministic planning; (2) the reasoning and decision-making mechanisms are statically decoupled, meaning dynamically retrieved domain knowledge fails to dynamically adjust the underlying reasoning strategy. These dual deficiencies result in initial decisions lacking strategic anchoring and reasoning chains often failing to converge on correct solutions, as stochastic generation lacks mechanisms for trajectory correction or knowledge-guided optimization during sequential reasoning. To resolve these issues, we propose a problem-solving method integrated into the LLM's generation process to guide reasoning. This method, compatible with numerous LLMs and featuring reusable solutions, is grounded in a novel Heuristic-Classification-of-Thoughts prompting schema (HCoT). HCoT synergizes the LLM's reasoning ability with a structured problem space via a heuristic classification model that controls the reasoning process and provides reusable abstract solutions. Evaluated on two complex inductive reasoning tasks with ill-defined search spaces, HCoT outperforms existing approaches (e.g., Tree-of-Thoughts and Chain-of-Thoughts prompting) in performance. On the well-structured 24 Game task, HCoT demonstrates significantly higher token efficiency compared to the state-of-the-art Tree-of-Thoughts-Breadth-First-Search. In terms of both accuracy and token usage, HCoT achieves a Pareto frontier balance, offering a strong trade-off between performance and computational cost.

Lei Lin, Jizhao Zhu, Yong Liu +3

Computer Network Information Center, Chinese Academy of Sciences, Beijing, China · Shenyang Aerospace University · ZGC LAB, Beijing,China +1

Structured Reasoning in Language ModelsConstraint-Guided Reasoning in Language ModelsInductive Reasoning in Language ModelsLLM PromptingEfficient Language Model ReasoningLarge Reasoning Models
AskPDF
Apr 10, 2026

Conflicts Make Large Reasoning Models Vulnerable to Attacks

Large Reasoning Models (LRMs) have achieved remarkable performance across diverse domains, yet their decision-making under conflicting objectives remains insufficiently understood. This work investigates how LRMs respond to harmful queries when confronted with two categories of conflicts: internal conflicts that pit alignment values against each other and dilemmas, which impose mutually contradictory choices, including sacrificial, duress, agent-centered, and social forms. Using over 1,300 prompts across five benchmarks, we evaluate three representative LRMs - Llama-3.1-Nemotron-8B, QwQ-32B, and DeepSeek R1 - and find that conflicts significantly increase attack success rates, even under single-round non-narrative queries without sophisticated auto-attack techniques. Our findings reveal through layerwise and neuron-level analyses that safety-related and functional representations shift and overlap under conflict, interfering with safety-aligned behavior. This study highlights the need for deeper alignment strategies to ensure the robustness and trustworthiness of next-generation reasoning models. Our code is available at https://github.com/DataArcTech/ConflictHarm. Warning: This paper contains inappropriate, offensive and harmful content.

Honghao Liu, Chengjin Xu, Xuhui Jiang +5

International Digital Economy Academy · The Hong Kong University of Science and Technology (Guangzhou) · DataArc Tech +1

LLM SafetyLarge Reasoning ModelsLLM Safety AlignmentAdversarial Robustness of Language ModelsAdversarial Attacks on LLMsLLM Safety Benchmarks
AskPDF
Apr 10, 2026

Think Less, Know More: State-Aware Reasoning Compression with Knowledge Guidance for Efficient Reasoning

Large Reasoning Models (LRMs) achieve strong performance on complex tasks by leveraging long Chain-of-Thought (CoT), but often suffer from overthinking, leading to excessive reasoning steps and high inference latency. Existing CoT compression methods struggle to balance accuracy and efficiency, and lack fine-grained, step-level adaptation to redundancy and reasoning bias. Therefore, we propose State-Aware Reasoning Compression with Knowledge Guidance (STACK), a framework that performs step-wise CoT compression by explicitly modeling stage-specific redundancy sources and integrating with a retrieval-augmented guidance. STACK constructs online long-short contrastive samples and dynamically switches between knowledge-guided compression for uncertain or biased reasoning state and self-prompted compression for overly long but confident state, complemented by an answer-convergence-based early stopping mechanism to suppress redundant verification. We further propose a reward-difference-driven training strategy by combining Proximal Policy Optimization (PPO) and Direct Preference Optimization (DPO), enabling models to learn state-conditioned compression strategies. Experiments on three mathematical reasoning benchmarks show that STACK achieves a superior accuracy-efficiency balance, reducing average response length by 59.9% while improving accuracy by 4.8 points over existing methods.

Yi Sui, Chaozhuo Li, Dawei Song

Beijing Institute of Technology, China · Beijing University of Posts and Telecommunications, China · The Open University, UK

CoT CompressionEfficient Language Model ReasoningLarge Reasoning Models
AskPDF
Apr 9, 2026

When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning

Large reasoning models (LRMs) have achieved strong performance enhancement through scaling test time computation, but due to the inherent limitations of the underlying language models, they still have shortcomings in tasks that require precise computation and extensive knowledge reserves. Tool-Integrated Reasoning (TIR) has emerged as a promising paradigm that incorporates tool call and execution within the reasoning trajectory. Although recent works have released some powerful open-source TIR models, our analysis reveals that these models still suffer from critical deficiencies. We find that when the reasoning of the model conflicts with the tool results, the model tends to believe in its own reasoning. And there are cases where the tool results are correct but are ignored by the model, resulting in incorrect answers, which we define as "Tool Ignored''. This indicates that the model does not know when to trust or ignore the tool. To overcome these limitations, We introduce Adaptive Tool Trust Calibration (ATTC), a novel framework that guides the model to adaptively choose to trust or ignore the tool results based on the confidence score of generated code blocks. The experimental results from various open-source TIR models of different sizes and across multiple datasets demonstrate that ATTC effectively reduces the "Tool Ignored" issue, resulting in a performance increase of 4.1% to 7.5%.

Ruotao Xu, Yixin Ji, Yu Luo +5

School of Computer Science and Technology, Soochow University · Department of Foundation Model, 2012 Labs, Huawei · Harbin Institute of Technology, Shenzhen (HITSZ)

Tool-Integrated ReasoningLLM ReasoningLarge Reasoning Models
AskPDF
Apr 9, 2026

SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking

Large Reasoning Models (LRMs) have revolutionized complex problem-solving, yet they exhibit a pervasive "overthinking", generating unnecessarily long reasoning chains. While current solutions improve token efficiency, they often sacrifice fine-grained control or risk disrupting the logical integrity of the reasoning process. To address this, we introduce Stepwise Adaptive Thinking (SAT), a framework that performs step-level, difficulty-aware pruning while preserving the core reasoning structure. SAT formulates reasoning as a Finite-State Machine (FSM) with distinct thinking modes (Slow, Normal, Fast, Skip). It navigates these states dynamically using a lightweight Process Reward Model (PRM), compressing easy steps while preserving depth for hard ones. Experiments across 9 LRMs and 7 benchmarks show that SAT achieves up to 40% reduction in reasoning tokens while generally maintaining or improving accuracy.

Weiyang Huang, Xuefeng Bai, Kehai Chen +4

Harbin Institute of Technology (Shenzhen), Shenzhen, China · Huawei Technologies

Efficient Language Model ReasoningOverthinking in Language ModelsLarge Reasoning Models
AskPDF
Apr 8, 2026

Unified Deployment-Aware Evaluation of Open Reasoning Language Models

Open reasoning language models are often compared under mixed sample sizes, partially standardized prompts, and accuracy-centered summaries, which makes practical model selection difficult to interpret. We present a unified evaluation of seven open reasoning language model configurations across four benchmarks: ARC-Challenge, GSM8K, MATH levels 1 to 3, and TruthfulQA MC1. We test zero-shot, chain-of-thought (CoT), and few-shot CoT prompting on the same 238-example subset for every model--dataset--strategy condition, yielding a complete 7 x 4 x 3 design with 84 conditions and 19,992 evaluated examples. Beyond accuracy, we report Wilson confidence intervals, latency, peak video random access memory (VRAM), weighted aggregate performance, Pareto-efficient operating points, prompt-sensitivity metrics, and compatibility diagnostics. Gemma-4-26B-A4B with zero-shot prompting achieves the highest weighted score at 0.794. Gemma-4-E4B remains close to the top across prompting settings while using substantially lower latency and memory, making it a strong practical operating point. Bootstrap and paired-permutation analyses show that the leading configurations are close enough that deployment tradeoffs remain important. We also find that prompting strategy changes model rankings rather than shifting all models uniformly. Benchmark-specific complementarity creates routing headroom, with an oracle task-aware selector reaching a weighted score of 0.825. Compatibility diagnostics show that some apparent failures, especially Phi-4-Reasoning on GSM8K, reflect robustness and interface-adherence problems under the shared evaluation pipeline. These results support a central claim: open-model evaluation should be framed as a deployment-aware, multi-objective operating-point problem rather than as a single-score leaderboard exercise.

Md Motaleb Hossen Manik, Ge Wang

Department of Computer Science, Rensselaer Polytechnic Institute · Department of Biomedical Engineering, Rensselaer Polytechnic Institute

LLM EvaluationLanguage Model Reasoning EvaluationLarge Reasoning Models
AskPDF
Apr 8, 2026

On the Step Length Confounding in LLM Reasoning Data Selection

Large reasoning models have recently demonstrated strong performance on complex tasks that require long chain-of-thought reasoning, through supervised fine-tuning on large-scale and high-quality datasets. To construct such datasets, existing pipelines generate long reasoning data from more capable Large Language Models (LLMs) and apply manually heuristic or naturalness-based selection methods to filter high-quality samples. Despite the proven effectiveness of naturalness-based data selection, which ranks data by the average log probability assigned by LLMs, our analysis shows that, when applied to LLM reasoning datasets, it systematically prefers samples with longer reasoning steps (i.e., more tokens per step) rather than higher-quality ones, a phenomenon we term step length confounding. Through quantitative analysis, we attribute this phenomenon to low-probability first tokens in reasoning steps; longer steps dilute their influence, thereby inflating the average log probabilities. To address this issue, we propose two variant methods: ASLEC-DROP, which drops first-token probabilities when computing average log probability, and ASLEC-CASL, which applies a causal debiasing regression to remove the first tokens' confounding effect. Experiments across four LLMs and five evaluation benchmarks demonstrate the effectiveness of our approach in mitigating the step length confounding problem.

Bing Wang, Rui Miao, Chen Shen +7

College of Computer Science and Technology, Jilin University · Key Laboratory of Symbolic Computation and Knowledge Engineering, MoE, Jilin University · Alibaba Cloud Computing +4

Large Reasoning Models
AskPDF
Apr 8, 2026

When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning

Large reasoning models (LRMs) have achieved remarkable performance in complex reasoning tasks, driven by their powerful inference-time scaling capability. However, LRMs often suffer from overthinking, which results in substantial computational redundancy and significantly reduces efficiency. Early-exit methods aim to mitigate this issue by terminating reasoning once sufficient evidence has been generated, yet existing approaches mostly rely on handcrafted or empirical indicators that are unreliable and impractical. In this work, we introduce Dynamic Thought Sufficiency in Reasoning (DTSR), a novel framework for efficient reasoning that enables the model to dynamically assess the sufficiency of its chain-of-thought (CoT) and determine the optimal point for early exit. Inspired by human metacognition, DTSR operates in two stages: (1) Reflection Signal Monitoring, which identifies reflection signals as potential cues for early exit, and (2) Thought Sufficiency Check, which evaluates whether the current CoT is sufficient to derive the final answer. Experimental results on the Qwen3 models show that DTSR reduces reasoning length by 28.9%-34.9% with minimal performance loss, effectively mitigating overthinking. We further discuss overconfidence in LRMs and self-evaluation paradigms, providing valuable insights for early-exit reasoning.

Yang Xiang, Yixin Ji, Ruotao Xu +4

Soochow University · ByteDance

Efficient Language Model ReasoningLarge Reasoning ModelsOverthinking in Language Models
AskPDF
Apr 8, 2026

Reasoning Fails Where Step Flow Breaks

Large reasoning models (LRMs) that generate long chains of thought now perform well on multi-step math, science, and coding tasks. However, their behavior is still unstable and hard to interpret, and existing analysis tools struggle with such long, structured reasoning traces. We introduce Step-Saliency, which pools attention--gradient scores into step-to-step maps along the question--thinking--summary trajectory. Across several models, Step-Saliency reveals two recurring information-flow failures: Shallow Lock-in, where shallow layers over-focus on the current step and barely use earlier context, and Deep Decay, where deep layers gradually lose saliency on the thinking segment and the summary increasingly attends to itself and the last few steps. Motivated by these patterns, we propose StepFlow, a saliency-inspired test-time intervention that adjusts shallow saliency patterns measured by Step-Saliency via Odds-Equal Bridge and adds a small step-level residual in deep layers via Step Momentum Injection. StepFlow improves accuracy on math, science, and coding tasks across multiple LRMs without retraining, indicating that repairing information flow can recover part of their missing reasoning performance.

Xiaoyu Xu, Yulan Pan, Xiaosong Yuan +4

Shanghai Jiao Tong University · Fuzhou University · Jilin University

LLM ReasoningLarge Reasoning ModelsInference-Time InterventionLLM Interpretability
AskPDF
Apr 7, 2026

Multi-objective Evolutionary Merging Enables Efficient Reasoning Models

Reasoning models achieve strong performance on complex problems by leveraging long chains of thought, but this deliberate reasoning incurs substantial inference-time cost. The Long-to-Short (L2S) reasoning problem seeks to preserve accuracy while reducing generated tokens. Yet, current training-free model merging approaches rely on brittle, fixed-hyperparameter arithmetic methods that force suboptimal compromises. We introduce Evo-L2S, a multi-objective evolutionary model merging framework that explicitly optimizes accuracy and output length to recover a Pareto front of merged models. To make this search computationally tractable, we propose an entropy-based subset sampling technique that substantially reduces fitness-estimation overhead. Across six mathematical reasoning benchmarks, Evo-L2S reduces reasoning length by over 50% at the 1.5B and 7B scales while preserving or improving problem-solving accuracy; at 14B, the steeper Pareto front reveals that attainable compression depends on the intrinsic compressibility of the reasoning model. Overall, Evo-L2S shows that reasoning models can be made substantially more concise while preserving strong problem-solving performance.

Mario Iacobelli, Adrian Robert Minut, Tommaso Mencattini +4

Independent Researcher · Sapienza University of Rome · EPFL +2

Efficient Language Model ReasoningLanguage Model MergingLarge Reasoning ModelsMulti-Objective Optimization
AskPDF
Apr 7, 2026

Understanding Performance Gap Between Parallel and Sequential Sampling in Large Reasoning Models

Large Reasoning Models (LRMs) have shown remarkable performance on challenging questions, such as math and coding. However, to obtain a high quality solution, one may need to sample more than once. In principal, there are two sampling strategies that can be composed to form more complex processes: sequential sampling and parallel sampling. In this paper, we first compare these two approaches with rigor, and observe, aligned with previous works, that parallel sampling seems to outperform sequential sampling even though the latter should have more representation power. To understand the underline reasons, we make three hypothesis on the reason behind this behavior: (i) parallel sampling outperforms due to the aggregator operator; (ii) sequential sampling is harmed by needing to use longer contexts; (iii) sequential sampling leads to less exploration due to conditioning on previous answers. The empirical evidence on various model families and sizes (Qwen3, DeepSeek-R1 distilled models, Gemini 2.5) and question domains (math and coding) suggests that the aggregation and context length do not seem to be the main culprit behind the performance gap. In contrast, the lack of exploration seems to play a considerably larger role, and we argue that this is one main cause for the performance gap.

Xiangming Gu, Soham De, Larisa Markeeva +2

Google DeepMind · National University of Singapore

Parallel Reasoning in Language ModelsLarge Reasoning ModelsInference-Time Scaling
AskPDF
Apr 6, 2026

Early Stopping for Large Reasoning Models via Confidence Dynamics

Large reasoning models rely on long chain-of-thought generation to solve complex problems, but extended reasoning often incurs substantial computational cost and can even degrade performance due to overthinking. A key challenge is determining when the model should stop reasoning and produce the final answer. In this work, we study the confidence of intermediate answers during reasoning and observe two characteristic behaviors: correct reasoning trajectories often reach high-confidence answers early, while incorrect rollouts tend to produce long, unproductive reasoning traces and exhibit less reliable confidence dynamics. Motivated by these observations, we propose CoDE-Stop (Confidence Dynamics Early Stop), an early stopping method that leverages the dynamics of intermediate answer confidence to decide when to terminate reasoning, requiring no additional training and easily integrating into existing models. We evaluate CoDE-Stop on diverse reasoning and science benchmarks across multiple models. Compared to prior early stopping methods, it achieves a more favorable accuracy-compute tradeoff and reduces total token usage by 25-50% compared to standard full-length reasoning. In addition, we provide analyses of confidence dynamics during reasoning, offering insights into how confidence changes in both correct and incorrect trajectories.

Parsa Hosseini, Sumit Nawathe, Mahdi Salmani +2

University of Maryland · University of Southern California

Early Stopping for Language Model ReasoningEarly StoppingEfficient Language Model ReasoningLarge Reasoning ModelsOverthinking in Language ModelsConfidence Estimation in Language Models
AskPDF
Apr 6, 2026

What Makes Good Multilingual Reasoning? Disentangling Traces with Measurable Features

Large Reasoning Models (LRMs) still exhibit large performance gaps between English and other languages, yet much current work assumes these gaps can be closed simply by making reasoning in every language resemble English reasoning. This work challenges this assumption by asking instead: what actually characterizes successful reasoning traces in multilingual settings, and to what extent do English-derived reasoning features genuinely help in other languages? We first define a suite of measurable reasoning features spanning multilingual alignment, reasoning step, and reasoning flow aspects of reasoning traces, and use logistic regression to quantify how each feature associates with final answer accuracy. We further train sparse autoencoders over multilingual traces to automatically discover latent reasoning concepts that instantiate or extend these features. Finally, we use the features to re-rank traces and measure their impact on accuracy at test time. Across two mathematical reasoning benchmarks, four LRMs, and ten languages, we find that most features are positively associated with accuracy, but the strength of association varies considerably across languages and can even reverse in some. Our findings challenge English-centric reward designs and point toward adaptive objectives that accommodate language-specific reasoning patterns, with concrete implications for multilingual benchmark and reward design.

Dayeon Ki, Kevin Duh, Marine Carpuat

University of Maryland · Johns Hopkins University

Multilingual Language Model EvaluationCross-Lingual Reasoning in Language ModelsMathematical ReasoningLarge Reasoning ModelsReasoning Trace Analysis
AskPDF
Apr 5, 2026

Towards Unveiling Vulnerabilities of Large Reasoning Models in Machine Unlearning

Large language models (LLMs) possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models (LRMs), which provide explicit multi-step reasoning traces. On the other hand, the growing need for the right to be forgotten has driven the development of machine unlearning techniques, which aim to eliminate the influence of specific data from trained models without full retraining. However, unlearning may also introduce new security vulnerabilities by exposing additional interaction surfaces. Although many studies have investigated unlearning attacks, there is no prior work on LRMs. To bridge the gap, we first in this paper propose LRM unlearning attack that forces incorrect final answers while generating convincing but misleading reasoning traces. This objective is challenging due to non-differentiable logical constraints, weak optimization effect over long rationales, and discrete forget set selection. To overcome these challenges, we introduce a bi-level exact unlearning attack that incorporates a differentiable objective function, influential token alignment, and a relaxed indicator strategy. To demonstrate the effectiveness and generalizability of our attack, we also design novel optimization frameworks and conduct comprehensive experiments in both white-box and black-box settings, aiming to raise awareness of the emerging threats to LRM unlearning pipelines.

Aobo Chen, Chenxu Zhao, Chenglin Miao +1

Iowa State University, Ames IA 50011, USA

Machine UnlearningLLM UnlearningLarge Reasoning ModelsAdversarial Attacks on LLMs
AskPDF
Apr 4, 2026

Selective Forgetting for Large Reasoning Models

Large Reasoning Models (LRMs) generate structured chains of thought (CoTs) before producing final answers, making them especially vulnerable to knowledge leakage through intermediate reasoning steps. Yet, the memorization of sensitive information in the training data such as copyrighted and private content has led to ethical and legal concerns. To address these issues, selective forgetting (also known as machine unlearning) has emerged as a potential remedy for LRMs. However, existing unlearning methods primarily target final answers and may degrade the overall reasoning ability of LRMs after forgetting. Additionally, directly applying unlearning on the entire CoTs could degrade the general reasoning capabilities. The key challenge for LRM unlearning lies in achieving precise unlearning of targeted knowledge while preserving the integrity of general reasoning capabilities. To bridge this gap, we in this paper propose a novel LRM unlearning framework that selectively removes sensitive reasoning components while preserving general reasoning capabilities. Our approach leverages multiple LLMs with retrieval-augmented generation (RAG) to analyze CoT traces, identify forget-relevant segments, and replace them with benign placeholders that maintain logical structure. We also introduce a new feature replacement unlearning loss for LRMs, which can simultaneously suppress the probability of generating forgotten content while reinforcing structurally valid replacements. Extensive experiments on both synthetic and medical datasets verify the desired properties of our proposed method.

Tuan Le, Wei Qian, Mengdi Huai

Iowa State University, Ames IA 50011, USA

LLM UnlearningLarge Reasoning ModelsPrivacy Leakage in Language Models
AskPDF
Apr 3, 2026

NeuReasoner: Towards Explainable, Controllable, and Unified Reasoning via Mixture-of-Neurons

Large Reasoning Models (LRMs) have recently achieved remarkable success in complex reasoning tasks. However, closer scrutiny reveals persistent failure modes compromising performance and cost: I) Intra-step level, marked by calculation or derivation errors; II) Inter-step level, involving oscillation and stagnation; and III) Instance level, causing maladaptive over-thinking. Existing endeavors target isolated levels without unification, while their black-box nature and reliance on RL hinder explainability and controllability. To bridge these gaps, we conduct an in-depth white-box analysis, identifying key neurons (Mixture of Neurons, MoN) and their fluctuation patterns associated with distinct failures. Building upon these insights, we propose NeuReasoner, an explainable, controllable, and unified reasoning framework driven by MoN. Technically, NeuReasoner integrates lightweight MLPs for failure detection with a special token-triggered self-correction mechanism learned via SFT. During inference, special tokens are inserted upon failure detection to actuate controllable remedial behaviors. Extensive evaluations across six benchmarks, six backbone models (8B~70B) against nine competitive baselines, demonstrate that NeuReasoner achieves performance gains of up to 27.0% while reducing token consumption by 19.6% ~ 63.3%.

Haonan Dong, Kehan Jiang, Haoran Ye +3

State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · School of Software and Microelectronics, Peking University

Large Reasoning ModelsEfficient Language Model ReasoningLLM Self-CorrectionLLM Interpretability
AskPDF
Apr 3, 2026

FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models

Recent Large Reasoning Models (LRMs) like DeepSeek-R1 have demonstrated remarkable success in complex reasoning tasks, exhibiting human-like patterns in exploring multiple alternative solutions. Upon closer inspection, however, we uncover a surprising phenomenon: The First is The Best, where alternative solutions are not merely suboptimal but potentially detrimental. This observation challenges widely accepted test-time scaling laws, leading us to hypothesize that errors within the reasoning path scale concurrently with test time. Through comprehensive empirical analysis, we characterize errors as a forest-structured Forest of Errors (FoE) and conclude that FoE makes the First the Best, which is underpinned by rigorous theoretical analysis. Leveraging these insights, we propose RED, a self-guided efficient reasoning framework comprising two components: I) Refining First, which suppresses FoE growth in the first solution; and II) Discarding Subs, which prunes subsequent FoE via dual-consistency. Extensive experiments across five benchmarks and six backbone models demonstrate that RED outperforms eight competitive baselines, achieving performance gains of up to 19.0% while reducing token consumption by 37.7% ~ 70.4%. Moreover, comparative experiments on FoE metrics shed light on how RED achieves effectiveness.

Kehan Jiang, Haonan Dong, Zhaolu Kang +2

School of Software and Microelectronics, Peking University · State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University

Efficient Language Model ReasoningLarge Reasoning ModelsTest-Time ScalingReasoning Consistency in Language Models
AskPDF
Apr 2, 2026

Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning

Building general-purpose reasoning models using reinforcement learning with verifiable rewards (RLVR) across diverse domains has been widely adopted by frontier open-weight models. However, their training recipes and domain mixtures are often not disclosed. Joint optimization across domains poses significant challenges: domains vary widely in rollout length, problem difficulty, and sample efficiency. Further, models with long chain-of-thought traces increase inference cost and latency, making efficiency critical for practical deployment. We present Apriel-Reasoner, trained with a reproducible multi-domain RL post-training recipe on Apriel-Base, a 15B-parameter open-weight LLM, across five domains using public datasets: mathematics, code generation, instruction following, logical puzzles, and function calling. We introduce adaptive domain sampling that preserves target completed-rollout ratios despite heterogeneous rollout dynamics, and a difficulty-aware length penalty that, at no additional training overhead, encourages longer reasoning for difficult problems and shorter traces for easy ones. Trained with a strict 16K-token output budget, Apriel-Reasoner remains effective at a 32K output budget and improves over Apriel-Base on AIME 2025, GPQA, MMLU-Pro, and LiveCodeBench while producing 30-50% shorter reasoning traces. Among the evaluated open-weight models of similar scale, it improves the accuracy-token tradeoff using a fully public-data recipe.

Rafael Pardinas, Ehsan Kamalloo, David Vazquez +1

ServiceNow AI Research

LLM Inference EfficiencyRL for Language Model ReasoningEfficient Language Model ReasoningReinforcement Learning with Verifiable RewardsRL Post-TrainingLarge Reasoning Models
AskPDF
Apr 1, 2026

Scaling Reasoning Tokens via RL and Parallel Thinking: Evidence From Competitive Programming

We study how to scale reasoning token budgets for competitive programming through two complementary approaches: training-time reinforcement learning (RL) and test-time parallel thinking. During RL training, we observe an approximately log-linear relationship between validation accuracy and the average number of generated reasoning tokens over successive checkpoints, and show two ways to shift this training trajectory: verification RL warmup raises the starting point, while randomized clipping produces a steeper trend in the observed regime. As scaling single-generation reasoning during RL quickly becomes expensive under full attention, we introduce a multi-round parallel thinking pipeline that distributes the token budget across threads and rounds of generation, verification, and refinement. We train the model end-to-end on this pipeline to match the training objective to the test-time structure. Starting from Seed-OSS-36B, the full system with 16 threads and 16 rounds per thread matches the underlying RL model's oracle pass@16 at pass@1 using 7.6 million tokens per problem on average, and surpasses GPT-5-high on 456 hard competitive programming problems from AetherCode.

Qianfan Zhang, Tianyu Guo, Xuandi Ren +4

Princeton University · UC Berkeley · Stanford University +1

Parallel Reasoning in Language ModelsTest-Time ScalingLarge Reasoning ModelsRL for Code GenerationCompetitive Programming
AskPDF
Apr 1, 2026

Reasoning Shift: How Context Silently Shortens LLM Reasoning

Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remarkable performance on complex, long-term reasoning tasks. However, the robustness of these reasoning behaviors remains underexplored. To investigate this, we conduct a systematic evaluation of multiple reasoning models across three scenarios: (1) problems augmented with lengthy, irrelevant context; (2) multi-turn conversational settings with independent tasks; and (3) problems presented as a subtask within a complex task. We observe an interesting phenomenon: reasoning models tend to produce much shorter reasoning traces (up to 74%) for the same problem under different context conditions compared to the traces produced when the problem is presented in isolation. A finer-grained analysis reveals that this compression is associated with a decrease in self-verification and uncertainty management behaviors, such as double-checking. Importantly, we show that even when additional self-checks are forced, their efficiency depends not only on the content of the reasoning traces, but also on the presence of redundant context. We hope our findings draw additional attention to both the robustness of reasoning models and the problem of context management for LLMs.

Gleb Rodionov, Roman Garipov, George Yakushev

Yandex · HSE University

Language Model RobustnessLLM Context ManagementLLM ReasoningLarge Reasoning Models
AskPDF
Apr 1, 2026

CogRAG: Tackling Heterogeneous Cognitive Demands in RAG via Stratified Retrieval and Reasoning

Retrieval-Augmented Generation (RAG) frameworks typically process all queries through a one-size-fits-all pipeline, ignoring the heterogeneous cognitive demands of different tasks. This cognitive-blind approach causes two failure modes: cascading errors when low-level factual gaps trigger hallucinated reasoning, and reasoning-answer inconsistency in higher-order analytical tasks. We introduce CogRAG, a training-free, domain-agnostic framework that tackles these heterogeneous cognitive demands via stratified retrieval and reasoning. Inspired by Bloom's Taxonomy, CogRAG uses the predicted cognitive load of a query as a central control signal that coordinates two modules: Cognition-Adaptive Evidence Refinement supplements missing context via fact-centric or option-centric paths, and Cognition-Stratified Structured Reasoning replaces unconstrained chain-of-thought with cognition-aligned reasoning templates. We evaluate CogRAG on a demanding professional testbed, the Registered Dietitian qualification examination. CogRAG effectively reduces early-stage factual errors and eliminates reasoning-answer inconsistency, raising Qwen3-8B accuracy from 73.4% to 85.8% in single-choice mode and from 63.3% to 80.5% in scenario mode. These results highlight cognitive-stratified control as an effective, generalizable paradigm for reliable complex reasoning in large language models.

Xudong Wang, Zilong Wang, Kui Su +1

School of Computer and Computing Science, Hangzhou City University, Hangzhou, Zhejiang 310015, China · Institute of Digital Twin, Eastern Institute of Technology, Ningbo, Zhejiang 315200, China · Innovation Center of Yangtze River Delta, Zhejiang University, Jiaxing, Zhejiang 314100, China

Structured Reasoning in Language ModelsAdaptive RAGRAG RobustnessReasoning Consistency in Language ModelsLarge Reasoning Models
AskPDF
Mar 30, 2026

ERPO: Token-Level Entropy-Regulated Policy Optimization for Large Reasoning Models

Reinforcement learning from verifiable rewards has significantly advanced the reasoning capabilities of large language models. However, Group Relative Policy Optimization (GRPO) typically assigns a uniform, sequence-level advantage to all tokens, thereby overlooking the intrinsic information heterogeneity along reasoning chains. We show that this coarse-grained credit assignment leads to premature entropy collapse and encourages the model to generate redundant, low-quality reasoning paths. Through systematic empirical analysis, we identify Critical Decision Pivots (CDPs): transient high-entropy states where the policy's trajectory is most sensitive to perturbations. These pivots represent the "forks in the road" where effective multi-path exploration is most crucial yet often suppressed by uniform advantage signals. Building on these insights, we propose Entropy-Regulated Policy Optimization (ERPO), which transitions the optimization focus from coarse sequences to fine-grained token dynamics. ERPO introduces three synergistic components: (i) Entropy-aware Gating, which adaptively amplifies exploration at CDPs to facilitate diverse path discovery; (ii) Bucket-based Implicit Normalization, which mitigates difficulty bias by aligning token progress windows; and (iii) Result-anchored Advantage Synthesis, which re-weights token-level signals via outcome-driven anchors. Extensive experiments on competitive mathematical benchmarks demonstrate that ERPO significantly outperforms GRPO. Notably, ERPO not only boosts reasoning accuracy but also yields significantly more concise and robust derivation paths, while achieving performance comparable to large models with orders of magnitude more parameters.

Song Yu, Li Li, Wenwen Zhao +1

School of Computer and Information Science, Southwest University, Chongqing, 400715, China

RL for Language Model ReasoningRL for Language ModelsLLM ReasoningLarge Reasoning Models
AskPDF
Mar 27, 2026

RASPRef: Retrieval-Augmented Self-Supervised Prompt Refinement for Large Reasoning Models

Recent reasoning-focused language models such as DeepSeek R1 and OpenAI o1 have demonstrated strong performance on structured reasoning benchmarks including GSM8K, MATH, and multi-hop question answering tasks. However, their performance remains highly sensitive to prompt formulation, and designing effective prompts is typically a manual and iterative process that does not scale well across tasks or domains. To address this limitation, we introduce Retrieval-Augmented Self-Supervised Prompt Refinement (RASPRef), a framework that improves prompts without requiring human annotations or task-specific supervision. The approach retrieves relevant examples and previously generated reasoning trajectories, and leverages signals such as multi-sample consistency, verifier feedback, and model-generated critiques to iteratively refine the prompt. Unlike prior approaches that focus primarily on improving model outputs, RASPRef directly treats the prompt as the optimization target and improves it through an iterative retrieval-guided refinement process. Experiments on GSM8K-style mathematical reasoning tasks show that retrieval-guided prompting improves performance compared with a static prompting baseline. We further discuss how retrieval quality, trajectory selection, and self-supervised feedback signals may influence the effectiveness of prompt refinement. These findings suggest that prompt design remains a critical factor for reasoning-oriented language models, and that self-improving prompts offer a practical and scalable strategy for improving reasoning performance.

Rahul Soni

Independent Researcher

LLM Input OptimizationLLM PromptingLLM Self-RefinementLarge Reasoning Models
AskPDF
Mar 27, 2026

Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models

Extended-thinking models expose a second text-generation channel ("thinking tokens") alongside the user-visible answer. This study examines 12 open-weight reasoning models on MMLU and GPQA questions paired with misleading hints. Among the 10,506 cases where models actually followed the hint (choosing the hint's target over the ground truth), each case is classified by whether the model acknowledges the hint in its thinking tokens, its answer text, both, or neither. In 55.4% of these cases the model's thinking tokens contain hint-related keywords that the visible answer omits entirely, a pattern termed thinking-answer divergence. The reverse (answer-only acknowledgment) is near-zero (0.5%), confirming that the asymmetry is directional. Hint type shapes the pattern sharply: sycophancy is the most transparent hint, with 58.8% of sycophancy-influenced cases acknowledging the professor's authority in both channels, while consistency (72.2%) and unethical (62.7%) hints are dominated by thinking-only acknowledgment. Models also vary widely, from near-total divergence (Step-3.5-Flash: 94.7%) to relative transparency (Qwen3.5-27B: 19.6%). These results show that answer-text-only monitoring misses more than half of all hint-influenced reasoning and that thinking-token access, while necessary, still leaves 11.8% of cases with no verbalized acknowledgment in either channel.

Richard J. Young

University of Nevada, Las Vegas, Department of Management, Entrepreneurship and Technology, Lee Business School, Las Vegas, NV, USA · DeepNeuro AI, Las Vegas, NV, USA

CoT FaithfulnessLarge Reasoning ModelsFaithfulness of Language Model Explanations
AskPDF
Mar 25, 2026

The Price Reversal Phenomenon: When Cheaper Reasoning Models Cost More

Developers and consumers increasingly choose reasoning models (RMs) based on their listed API prices. However, how accurately do these prices reflect actual inference costs? We conduct the first systematic study of this question, evaluating 8 frontier RMs across 12 diverse tasks covering competition math, science QA, code generation, and multi-domain agents. We uncover the pricing reversal phenomenon: in 32% of model-pair comparisons, the model with a lower listed price actually incurs a higher total cost, with reversal magnitude reaching up to 28x. For example, Gemini 3 Flash's listed price is 80% cheaper than GPT-5.4's, yet its actual cost across all tasks is 38% higher. We build a formal cost attribution framework based on Shapley value, and leverage it to trace the dominating contributors to vast heterogeneity in thinking token consumption and number of interaction turns: on the same query, one model may use 900% more thinking tokens than another, or 10x more turns of environment interactions. We further show that per-query cost prediction is fundamentally difficult: repeated runs of the same query yield thinking token variation up to 9.7x, establishing an irreducible noise floor for any predictor. Thus, we propose cost distribution prediction as an open challenge. Our findings demonstrate that listed API pricing is an unreliable proxy for actual cost, calling for cost-aware model selection and transparent per-request cost monitoring.

Lingjiao Chen, Chi Zhang, Yeye He +3

Stanford University · Microsoft Research · CMU +1

Cost-Aware InferenceLarge Reasoning Models
AskPDF
Mar 24, 2026

How Utilitarian Are OpenAI's Models Really? Replicating and Reinterpreting Pfeffer, Krügel, and Uhl (2025)

Pfeffer, Krügel, and Uhl (2025) report that OpenAI's reasoning model o1-mini produces more utilitarian responses to the trolley problem and footbridge dilemma than the non-reasoning model GPT-4o, and they raise the question whether growing reasoning capabilities bring about a "utilitarian turn" in LLMs. I extend their exploratory study in a direction they call for: with four current OpenAI models and systematic prompt variation. On the trolley dilemma, the hypothesized utilitarian turn is not confirmed. GPT-4o's low utilitarian rate reflects safety refusals triggered by the prompt's advisory framing rather than a deontological commitment; on reformulated prompt variants -- for instance, agent-neutral "Is it morally permissible...?" instead of advisory "Should I...?" -- all four models, reasoning or not, converge on utilitarian answers. The footbridge finding is partially confirmed: reasoning models tend to give more utilitarian responses than non-reasoning models across prompt variations, but they often refuse to answer or answer non-utilitarian. These results demonstrate that single-prompt evaluations of LLM moral responses are unreliable: multi-prompt robustness testing should be standard practice for any empirical claims about LLM behavior.

Johannes Himmelreich

Prompt SensitivityMoral Reasoning in Language ModelsLanguage Model Safety EvaluationLLM Refusal BehaviorLarge Reasoning ModelsMoral Reasoning
AskPDF