Large Reasoning Models

Follow this topic Ask about this topic

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

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

Jun 2, 2026

Reasoning Structure of Large Language Models

Large reasoning models (LRMs) are often evaluated using metrics such as final-answer accuracy or token count. However, identical scores on these metrics can hide fundamentally different reasoning structures. To address this limitation, we introduce a scalable LRM benchmark of logic puzzles and a pipeline that converts unstructured traces into verifiable reasoning graphs of claims and dependencies. This turns reasoning into a structured, measurable object whose topology can be quantitatively analyzed. Building on this, we define a reasoning efficiency metric that quantifies how concentrated the model's logical flow is. Our analysis on open-source reasoning models shows that structural measurements separate behaviors that token count and accuracy conflate, providing a practical tool for diagnosing failure modes and comparing how reasoning scales with puzzle difficulty.

Frédéric Berdoz, Luca A. Lanzendörfer, Fabian Farestam +1

1ETH Zurich, Switzerland.

Logical Reasoning LLM Evaluation LLM Reasoning with Graphs Structured Reasoning LLM Reasoning Large Reasoning Models

Jun 2, 2026

Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models

Large Reasoning Models (LRMs) have demonstrated impressive capabilities in many tasks, yet they struggle with reliably following multiple instructions, either by failing to satisfy individual constraints or by struggling to balance competing constraints simultaneously. We formalize this challenge as the Constraint Adherence Problem (CAP). This paper introduces a novel framework that addresses CAP by representing instructions as a structured knowledge graph of constraints. Our approach, Constraint Relationship Graph Completion (CRGC), explicitly models relationships between constraints, identifies adherence challenges, and discovers ``bridge constraints'' that help the model better focus on and reconcile requirements. Bridge constraints act as auxiliary instructions that make primary constraints more salient and compatible. Unlike existing approaches that enhance instruction following through general training methods, CRGC specifically improves constraint satisfaction by leveraging the model's own knowledge to create better pathways for generation. Experiments across three popular instruction following datasets demonstrate that our approach reduces constraint violations by 39% compared to standard prompting while maintaining reasoning abilities of large reasoning models.

Zhengyi Zhao, Shubo Zhang, Huimin Wang +7

The Chinese University of Hong Kong · Tencent Jarvis Lab · Westlake University +2

LLM Prompting Instruction Following Constraint Satisfaction Large Reasoning Models

Jun 2, 2026

ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning

Large Reasoning Models (LRMs) have achieved remarkable progress thanks to Reinforcement Learning with Verifiable Rewards (RLVR) on Chain-of-Thoughts (CoTs). However, since long CoTs naturally contain trial and errors and mainstream RLVR approaches choose outcome-correct CoT trajectories for memorization, the redundant explorations in long CoTs are inevitably reinforced, which results in the over-thinking issues of LRMs. Previous attempts to resolve this issue mainly give more advantage to shorter trajectories, yet their learning signals are still outcome-based and cannot reduce the memorization of redundant explorations in long CoTs. Therefore, we propose ThoughtFold, a framework that leverages fine-grained preference learning to mitigate redundant explorations for efficient reasoning. ThoughtFold employs an introspective strategy to identify redundancy within each correct trajectory, which yields a spectrum of candidate sub-trajectories. Leveraging this spectrum, we introduce a masked preference optimization objective that explicitly penalizes redundant explorations and encourages the model to directly bridge essential reasoning segments, effectively folding its reasoning chains into a more concise path. Extensive experiments show that ThoughtFold significantly enhances efficiency. It reduces the token usage of DeepSeek-R1-Distill-Qwen-7B by approximately 56% while maintaining state-of-the-art accuracy.

Ziyan Liu, Xueda Shen, Yuzhe Gu +7

Shanghai Artificial Intelligence Laboratory · University of Science and Technology of China · MMLab, The Chinese University of Hong Kong

Efficient Language Model Reasoning Preference Optimization Efficient Language Model Inference CoT Compression LLM Reasoning Large Reasoning Models

Jun 1, 2026

Thinking Past the Answer: Evaluating Harmful Overthinking in Large Reasoning Models

Large Reasoning Models (LRMs) improve performance by generating explicit intermediate reasoning traces through increased test-time compute, yet the assumption that longer reasoning is consistently beneficial remains under-examined. While recent evidence shows that additional reasoning can lead models to overthink, we ask: "Once a model has reached the correct answer, does further reasoning refine the solution, or deviate from it?" To study the dynamics after correctness, we introduce a prefix-level trajectory evaluation protocol grounded in reasoning sufficiency, defining the minimum reasoning budget required for a model to first generate the correct answer. This allows us to disentangle verbose overthinking, where additional reasoning is redundant but harmless, from harmful overthinking, where continued reasoning destabilizes an already-correct trajectory. Starting from multimodal benchmarks, we find that many instances considered reasoning-intensive require surprisingly little reasoning. Moreover, stopping at the first correct prefix improves accuracy over standard reasoning up to 21%, revealing that current models are limited not only by their ability to reason, but also by their inability to stop at the right time. Furthermore, while common efficiency strategies like early stopping substantially reduce verbose overthinking (up to 50%), they fail to mitigate harmful overthinking. Failure analysis reveals that correctness deviations are mainly driven by logical drift and visual reinterpretation. Finally, we show that our findings generalize to language-only reasoning benchmarks, highlighting harmful overthinking as a broader reliability risk. Code available at https://simonecaldarella.github.io/thinking-past-the-answer.

Simone Caldarella, Davide Talon, Rahaf Aljundi +2

University of Trento · 3Fondazione Bruno Kessler · 2Toyota Motor Europe

LLM Evaluation Overthinking in Language Models Reasoning Evaluation LLM Reliability Large Reasoning Models Reasoning Trace Analysis

Jun 1, 2026

A Primer in Post-Training Reasoning Data: What We Know About How It Works

Post-training has become a primary driver of recent progress in large reasoning models, and reasoning data are often the key variable determining whether this stage succeeds. Work on post-training reasoning data has grown rapidly, yet this literature remains scattered across dataset papers, reinforcement-learning recipes, reward-model studies, benchmarks, and frontier system reports. This paper is the first primer to synthesize over 150 key public studies and system reports on post-training reasoning data. We organize the field around four questions: what data objects exist, what makes them useful, how they are constructed, and how they scale. Together, this organization provides an attribution framework for future reasoning-data releases and post-training recipes.

Yaoming Li, Guangxiang Zhao, Qilong Shi +3

State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University · Qiyuan Tech · Tsinghua University

RL Post-Training LLM Post-Training Large Reasoning Models

Jun 1, 2026

Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery

Large Reasoning Models (LRMs) rely on long reasoning traces, making inference expensive. While low-bit quantization reduces per-token decoding cost, we show that aggressive 2-bit inference can fail to deliver end-to-end speedup because instability in the generation process inflates total token count. Instead of merely lowering answer accuracy, 2-bit quantization often produces much longer traces with repetitive loops, budget exhaustion, delayed commitment, and unclosed reasoning segments. We analyze full reasoning traces of Qwen3 reasoning models across mathematical and commonsense benchmarks and show that accuracy degradation is tightly linked to these process-level failures. To address them, we introduce two lightweight controls: FP16 planning, which gives the 2-bit model a short high-precision outline, and loop rescue, which detects repetitive traces and either commits to an earlier answer or falls back to FP16. On MATH-500, loop rescue improves Qwen3-8B accuracy from 17.2% to 74.2%, while planning plus loop rescue improves Qwen3-32B from 65.0% to 87.2%. Overall, our results show that extreme low-bit reasoning becomes practical when its failures are treated as controllable generation pathologies: with lightweight detection and selective FP16 support, 2-bit inference can recover accuracy while preserving real end-to-end speed. Our code is available at: https://github.com/brain-lab-research/quantized-reasoning.

Ekaterina Alimaskina, Darya Rudas, Denis Shveykin +3

BRAIn Lab, Moscow, Russia

LLM Quantization Repetition in Language Generation Efficient Language Model Reasoning LLM Inference Acceleration Low-Bit Quantization Large Reasoning Models

May 31, 2026

An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models

Studies of human reasoning have shown that people are typically stronger at evaluating reasoning than producing it from scratch. In contrast, large reasoning models (LRMs) are trained to excel at producing long chains of reasoning to solve complex problems. How then do LRMs perform at evaluating reasons? We investigate this with the Valid-Answer-Invalid-Reasoning (VAIR) dataset: math problems and solutions with trivial reasoning flaws but valid answers, designed to isolate reasoning evaluation from the confound of reasoning production. Unlike humans, who we find are only 6% worse at grading than solving such problems, we find a substantial production-evaluation gap in LRMs: frontier models score as low as 48% when evaluating VAIR solutions, despite near-perfect solution production. Why this enigma? Through chain-of-thought (CoT) analysis, we find evidence of an answer confirmation bias: LRMs often produce then check for the correct answer instead of carefully verifying each step, fabricating rationalizations even when noticing anomalous reasoning. Linear probes corroborate this, showing that while LRM activations encode some representation of valid reasoning, they fail to robustly represent VAIR solutions as invalid. Causal patching of the final answer's representations causes LRM verdicts and activations to flip, demonstrating that answer validity is responsible for models' confirmation biases. These findings indicate an outstanding limitation in dominant approaches to reasoning training, which incentivize LRMs to produce and confirm reasoning towards correct answers, but not to robustly evaluate the underlying reasons.

Mingzhong Sun, Teresa Yeo, Armando Solar-Lezama +1

1NUS Department of Computer Science · 4Singapore-MIT Alliance for Research and Technology (SMART) · 2MIT EECS +1

Reasoning Evaluation LLM Interpretability Large Reasoning Models Reasoning Verification

May 31, 2026

Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches

While Reasoning Language Models (RLMs) are rapidly emerging as powerful tools for scientific research, their impact is primarily concentrated in "hard science" fields. The slow -- or lack of -- adoption of RLMs in other branches of science is causing a widening gap in research productivity. In this survey, we provide the first comprehensive analysis of RLM adoption across 28 scientific disciplines following the classification used by the European Research Council (ERC), spanning the Social Sciences and Humanities, Physical Sciences and Engineering, and Life Sciences. We examine how RLMs are developed, evaluated, and applied across disciplines. Furthermore, we introduce a maturity-oriented assessment framework based on available domain-specific development and evaluation resources, revealing substantial disparities in RLM maturity that become even more pronounced when only publicly available resources are considered. Finally, we highlight current implementation paradigms that are gaining popularity across disciplines, current challenges, and future directions in enabling RLM adoption across science.

Teddy Ferdinan, Bartłomiej Koptyra, Mikołaj Langner +42

AI for Science Scientific Reasoning Scientific Reasoning in Language Models Large Language Model-Guided Scientific Discovery Large Reasoning Models

May 29, 2026

Quantized Reasoning Models Think They Need to Think Longer, but They Do Not

Post-training quantization (PTQ) is widely used to deploy large language models efficiently, but its effect on reasoning models is not well understood. Across math, coding, and science QA, we find that aggressive PTQ reduces accuracy while increasing chain-of-thought (CoT) length. Surprisingly, we show that in up to 52% of the quantized models' failures, models reach the right answer in intermediate reasoning steps but do not output it as a final answer. To understand why quantization leads to this increase in overthinking errors, we measure the token-level KL divergence between quantized and full-precision output distributions. Positions with high KL divergence correlate strongly with high next-token entropy, and at these positions quantized models disproportionately sample overthinking markers such as "wait", "but", and "alternatively". We show that simply introducing a training-free logit penalty on a curated set of overthinking markers can reduce CoT length by 12--23% while preserving or improving accuracy across 5 models (1.5B-32B parameters), 3 quantization methods, and 5 benchmarks, yielding a favorable Pareto frontier of accuracy against reasoning cost compared to penalizing other token sets. Overthinking errors produced by quantized models are particularly reduced by up to 58%.

Sanae Lotfi, Polina Kirichenko, Steven Li +1

1FAIR at Meta · 2Meta AI

Logit Adjustment Overthinking in Language Models CoT Reasoning Efficient Language Model Reasoning Post-Training Quantization LLM Reasoning+1

May 29, 2026

Unlocking Fine-Grained Translation Quality Estimation in LRMs through Mutually Boosting Implicit and Explicit Reasoning

Large Reasoning Models (LRMs) still struggle with fine-grained translation quality estimation (QE), even with long reasoning chains. We argue that LRMs already possess strong multilingual capabilities, while the core challenge stems from the intrinsic difficulty of learning the fine-grained QE task. In this paper, we propose

\textbf{RIEQE}

(

\textbf{R}

easoning both

\textbf{I}

mplicitly and

\textbf{E}

xplicitly for

\textbf{QE}

), a simple two-stage training framework that enables the mutually boosting of implicit (layer-wise) and explicit (token-wise) reasoning capabilities. To make implicit reasoning feasible, we first decompose the complex QE task into straightforward subtasks. Based on this, our two-stage approach applies: (1)

\textit{NonThinking-SFT}

, Supervised Fine-Tuning (SFT) without reasoning chains to directly boost the model's implicit reasoning tendency and capability; and (2)

\textit{Thinking-RLVR}

, standard Reinforcement Learning with Verifiable Reward (RLVR) to subsequently strengthen explicit reasoning. On the WMT test sets, RIEQE based on Qwen3-4B-Thinking-2507 surpasses all baselines in explicit reasoning performance, while its implicit reasoning capability is also comparable to the best current encoder-based models. We further provide evidence for the mutually boosting between implicit and explicit reasoning, showing how they benefit each other in a bidirectional manner. Our code is available at https://github.com/NJUNLP/RIEQE.

Renfei Dang, Xinye Wang, Zhejian Lai +5

National Key Laboratory for Novel Software Technology, Nanjing University · Huawei Translation Services Center, Beijing, China

MT Evaluation Large Reasoning Models

May 29, 2026

AdaptR1: Reinforcement Learning Based Adaptive Interleaved Thinking in Multi-hop Question Answering

Large Language Models (LLMs) have achieved remarkable performance in complex reasoning tasks through Chain-of-Thought (CoT) prompting. However, this approach often leads to ``over-thinking,'' where models generate unnecessarily long reasoning traces for simple queries and incur avoidable inference cost. While recent work has explored adaptive reasoning, existing methods typically make a single query-level decision about whether to reason. This overlooks the dynamic nature of multi-step tasks, where the need for explicit reasoning varies across intermediate stages. To address this limitation, we introduce AdaptR1, a Reinforcement Learning (RL) based framework for adaptive interleaved thinking in multi-hop Question Answering (QA). Unlike previous approaches that require Supervised Fine-Tuning (SFT) for cold-start initialization, AdaptR1 uses a fully RL-based strategy with a quality-gated efficiency reward to dynamically allocate reasoning budgets at each step. Under the Graph-R1 setting, AdaptR1 reduces average think tokens by 69.71%, with a 90.35% reduction on HotpotQA, while maintaining performance comparable to or better than standard baselines. Furthermore, our analysis reveals that overthinking in multi-hop reasoning is not uniformly distributed but occurs predominantly during the initial planning stages, highlighting the effectiveness of step-wise adaptive budget allocation.

Yuxin Wang, Jiahao Lu, Qifeng Wu +5

1Computer Science, Fudan University · Institute of Modern Languages and Linguistics, Fudan University · 3Shanghai Innovation Institute +1

Multi-Hop QA Adaptive Reasoning in Language Models RL for Language Model Reasoning LLM Inference Acceleration Large Reasoning Models

May 29, 2026

SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning

Recent advances in Large Reasoning Models have significantly improved chain-of-thought (CoT) capabilities via reinforcement learning (RL). However, generated reasoning chains frequently suffer from structural redundancy (i.e., overthinking), incurring high computational overhead without improving answer correctness. Existing mitigation strategies typically rely on token-uniform length penalties, which provide coarse, segment-agnostic pressure toward shorter outputs and can inadvertently suppress useful reasoning alongside redundancy. To address this, we demonstrate that inefficiency concentrates in high-probability segments with low marginal utility. We derive a theoretical characterization of segment suboptimality under the correctness-length trade-off objective and propose SLAT (Segment-Level Adaptive Trimming), an RL framework that selectively suppresses redundant segments based on this criterion. Empirical results on standard benchmarks indicate that SLAT establishes a superior accuracy-efficiency Pareto frontier, reducing reasoning length by

50\%

relative to uncompressed baselines while maintaining competitive accuracy. Overall, our results suggest that theoretically grounded, segment-aware trimming is a promising direction for efficient CoT reasoning in large language models.

Jian Yao, Xiongcai Luo, Ran Cheng +1

Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University · Bytedance · The Hong Kong Polytechnic University-Daya Bay Technology and Innovation Research Institute, Huizhou,Guangdong Province, China.

RL for Language Model Reasoning Efficient Language Model Inference CoT Compression Large Reasoning Models

May 28, 2026

ReasonOps: Operator Segmentation for LLM Reasoning Traces

Chain-of-thought traces from large reasoning models can span tens of thousands of tokens, yet we lack a vocabulary for describing their internal structure. Previous methods developed to analyze chain-of-thought traces are either too rigid or not expressive enough, failing to capture features across domains and models. To remedy this, we develop ReasonOps, an unsupervised, expressive method for annotating chain-of-thought traces, providing succinct universal operators. Using ReasonOps, we analyze 44,662 traces from 12 thinking LLMs spanning 6 families across 8 reasoning benchmarks and discover that they share a common compositional structure: 7 recurring reasoning operators -- discourse-level moves such as backtracking, inferring, and hypothesizing -- that emerge from unsupervised clustering of sentence-initial 3-token pivots. These operators appear across every model family and benchmark domain, confirmed by three independent LLM judges who classify held-out samples at 70 -76% accuracy. We analyze the structure of operators on easy vs. hard problems, revealing that reflective operators are more helpful on hard problems and harm performance on easy problems. Operator sequences are highly model-identifying: a classifier trained on operator distributions alone recovers the source model with macro-AUC, revealing that each model family has a distinctive reasoning fingerprint. Structural operator features predict within-problem answer correctness well above baselines. Classifiers built on these operators reach WP-AUC and on AIME specifically. ReasonOps further enables early quality estimation well before the trace completes: we predict at WP-AUC for only 50% of the trace. The ReasonOps pipeline is unsupervised and annotation-free, enabling deep insights into LLM reasoning traces as well as strong downstream results on model identification and correctness prediction.

Daniel Lee, Owen Queen, James Zou

Stanford University

LLM Reasoning Reasoning Trace Analysis CoT Evaluation CoT Reasoning Structured Reasoning Large Reasoning Models+4

May 27, 2026

CosmicFish-HRM: Adaptive Reasoning via Hierarchical Recurrent Mechanisms in Compact Language Models

Large language models have achieved strong reasoning capabilities, though often at the cost of massive parameter counts and expensive inference. In this work, we explore a different direction: adaptive reasoning depth in compact language models. We present CosmicFish-HRM, a compact language model built around a Hierarchical Reasoning Module (HRM) that dynamically allocates computational effort during inference. Instead of applying fixed computation to every input, the model iterates through high-level and low-level reasoning cycles and learns when to halt based on input complexity. CosmicFish-HRM combines this adaptive reasoning core with modern transformer components including Grouped Query Attention, RoPE, and SwiGLU activations. While the additional reasoning infrastructure introduces overhead at small scale, we hypothesize that this tradeoff becomes increasingly favorable as model size grows and the relative cost of the HRM core diminishes. Our results show that the model learns non-uniform reasoning behavior, allocating different numbers of reasoning steps across tasks and inputs. These findings suggest that adaptive reasoning depth may offer a promising alternative to relying solely on parameter scale for reasoning capability.

Venkat Akhil Lakkapragada

Mistyoz AI Hyderabad, India

Small Language Models LLM Reasoning Adaptive Computation Large Reasoning Models

May 27, 2026

Reasoning that Travels: Dissecting How Chain-of-Thought Transfers Across Models

Large reasoning models (LRMs) often generate extensive chain-of-thought (CoT) traces before producing a final answer. As explicit textual artifacts, these traces can be passed to other models to solve the same task, enabling cross-model reasoning transfer. Yet successful transfer alone does not reveal how the provided CoT contributes to another model's answer. We study this question with a controlled provider--receiver framework, where a provider generates a reasoning trace and a receiver solves the same problem from increasingly longer trace prefixes. We compare force-answer, where the receiver answers directly from the prefix, with free-generation, where it may continue reasoning before answering. Across models and benchmarks, full traces often transfer successfully, but prefix trajectories reveal distinct mechanisms. In force-answer mode, AIME transfer is largely driven by explicit answer availability. MMLU-Pro instead reflects a larger role for receiver competence, while ZebraLogic depends on partial structured-answer information rather than complete-answer leakage alone. In free-generation mode, partial CoTs improve performance across benchmarks, indicating that prefixes can guide continued reasoning. Finally, answer agreement among receivers provides a gold-free signal for stopping provider reasoning early. Overall, cross-model CoT transfer is not a single phenomenon: it can reflect answer extraction, reasoning scaffolding, or receiver-dependent competence.

Xinyuan Cheng, Beiduo Chen, Philipp Mondorf +1

UMaiNLP, Center for Information and Language Processing, LMU Munich, Germany · ÆMunich Center for Machine Learning, Germany

LLM Prompting LLM Reasoning Large Reasoning Models Reasoning Trace Analysis

May 27, 2026

Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training

As LLMs gain stronger reasoning capabilities, their extended chain-of-thought introduces new degrees of complexity for defending against adversarial jailbreaks and prompt injection. We study consistency training, a family of fine-tuning objectives that enforce identical behavior on clean prompts and adversarial rewrites, and evaluate its two main variants, output-level (BCT) and activation-level (ACT), across five reasoning models. We formulate both methods as a prompt injection defense and find ACT to be competitive with other training-based defenses while requiring only self-supervised pairs of clean and wrapped prompts. Our experiments also generalize both techniques within the jailbreak setting, demonstrating that ACT remains more robust to adaptive attacks. We also provide mechanistic evidence that ACT's defense against jailbreaks is encoded as a roughly linear shift in activation space at the assistant-turn boundary. After ACT training, we can recover a single steering direction that controls refusal on reasoning models with minimal effect on benign inputs. We find that ACT remains robust even when the model's chain-of-thought is replaced with a compliant trace from the undefended base model, pivoting to refuse prefilled jailbreaks. Together, these results suggest that supervising internal representations is a surprisingly effective and interpretable approach to various forms of safety training in reasoning models.

Avidan Shah, Jannik Brinkmann, Rico Angell

New York University · Technical University Clausthal

Prompt Injection Defense Adversarial Robustness of Language Models Activation Steering Large Reasoning Models

May 27, 2026

HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs

Hybrid-reasoning large language models (LLMs) expose explicit controls over reasoning effort, allowing users or systems to trade off answer quality against inference cost. However, existing methods for adaptive thinking-mode selection are typically evaluated under different models, datasets, and implementation assumptions, making it difficult to compare their practical behavior. We introduce HRBench, a unified evaluation framework for studying thinking-mode switching in hybrid-reasoning LLMs. HRBench organizes the design space along two axes: three switching strategy families, prompt-based selection, external routing, and speculative execution, and four training regimes, training-free, SFT, offline and online RL, yielding 12 controlled evaluation settings. We evaluate these settings across 6 LLMs, from Qwen3.5-2B to Kimi-K2.5-1.1T, and 5 reasoning benchmarks covering mathematics, science, and code, while reimplementing 12+ representative prior methods within the same pipeline. Our analysis characterizes how different switching strategies occupy distinct effectiveness-efficiency trade-off regions: prompt-based methods often provide favorable token-accuracy trade-offs, routing methods offer more stable cost reduction, and speculative methods tend to improve accuracy at higher token cost. We further find that training affects strategies differently, and that the preferred strategy varies with model scale and task domain. HRBench provides reference implementations and a unified evaluation platform to support more controlled research on efficient reasoning in hybrid-reasoning LLMs. Our data, code and repository are available at https://github.com/usail-hkust/HRBench.

Yansong Ning, Mianpeng Liu, Jingwen Ye +2

AI Thrust, The Hong Kong University of Science and Technology (Guangzhou) · AIPD, Tencent

LLM Evaluation Adaptive Inference LLM Routing Efficient Language Model Inference Large Reasoning Models

May 27, 2026

Bridging the Detection-to-Abstention Gap in Reasoning Models under Insufficient Information

We highlight a failure mode of large reasoning models on questions with insufficient information: models may recognize that a problem is under-specified, yet still continue reasoning and produce unsupported final answers instead of abstaining. We formalize this mismatch as the detection-to-abstention gap, where detected insufficiency fails to translate into final abstention. This gap is especially concerning in high-risk domains such as medical AI, where answers based on incomplete evidence can be more harmful than refusal. To close this gap, we propose Judge-Then-Solve (JTS), a trajectory-level reasoning-control framework that trains models to make an explicit answerability commitment before solution generation. Rather than treating abstention as a final-answer style, JTS casts it as a control decision: the model either proceeds to solve or terminates early based on its answerability judgment. We instantiate this policy through supervised warm-up and missing-premise reinforcement learning with consistency and length-shaping rewards. Experiments on dense and MoE reasoning models show that JTS substantially improves reliable abstention across datasets and pushes Abstention@Detection (A@D) to near-saturation, indicating that models not only detect missing information but also act on that detection. By terminating unanswerable trajectories immediately after the answerability judgment, JTS reduces unnecessary reasoning and improves inference efficiency when continued deliberation would amplify unsupported assumptions. We also observe that missing-premise training can alter reasoning behavior on difficult but answerable problems, reducing unproductive self-reflection. These results suggest that abstention under insufficient information is a key form of reasoning control for deploying reasoning models safely and efficiently.

Renjie Gu, Jiaxu Li, Yihao Wang +8

1Fudan University · 4Tsinghua University · 2Ant Group +1

LLM Abstention Large Reasoning Models

May 27, 2026

The Shape of Overthinking: Backtracking Bursts in Long Reasoning Traces

Reasoning models often generate long traces in which useful self-correction and unproductive revision are hard to distinguish. We study this distinction through backtracking dynamics: local reconsideration, retraction, or re-derivation inside long-form reasoning traces. On 6{,}000 Qwen3-8B AIME traces, we annotate segment-level backtrack severity and analyze event timing, normalized depth, and local burst structure. We find that early isolated repair is often compatible with correct reasoning, whereas incorrect traces more often show moderate-to-severe backtracks that persist and cluster late. Cross-corpus checks show the same qualitative asymmetry across additional model/domain pairs. Filtering analyses instantiate the signal as a prefix-causal selective early-exit policy: at shallow and intermediate depths, burst-aware filtering outperforms fixed length-based filtering while using only prefix-available features. Moderate length cutoffs remain strong completed-trace baselines, but burst-aware control provides a deployable mechanism for separating recoverable repair from likely instability.

Navid Rezazadeh, Arash Gholami Davoodi

University of California, Irvine · Carnegie Mellon University

Reasoning Evaluation Efficient Language Model Inference LLM Reasoning Large Reasoning Models Reasoning Trace Analysis

May 26, 2026

Beyond Input Understanding: Diagnosing Multilingual Mathematical Reasoning with Directed Acyclic Trace Graphs

Large reasoning models (LRMs) achieve strong mathematical reasoning performance in English, but remain much less reliable in many low- and medium-resource languages. This gap is often explained as a failure to understand non-English problem statements. We show that this view is incomplete: even when the problem is given in English, controlling the model's reasoning language can substantially reduce accuracy, suggesting that language also affects reasoning execution itself. To study this effect, we introduce DATG, a Directed Acyclic Trace Graph framework that maps reasoning traces to language-independent mathematical anchors and dependencies. This allows us to align target-language traces with reference DAGs and measure whether they cover required mathematical nodes, respect dependency edges, and avoid harmful mathematical actions. Experiments on the Qwen3 series across 12 languages show that non-English reasoning often suffers from reduced anchor coverage and weaker dependency fidelity, especially in low-resource languages. Motivated by this diagnosis, we propose Loop-Retry and Formula-Retry, two simple test-time controls targeting DATG-exposed failure modes, and show that they consistently improve target-language reasoning performance in low-resource languages.

Jiaqiao Zhang, Zhuojun Li, Raoyuan Zhao +5

Southwest University · LMU Munich & MCML

Mathematical Reasoning Low-Resource Language Processing LLM Mathematical Reasoning Large Reasoning Models Reasoning Trace Analysis

May 26, 2026

Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models

Post-training Large Language Models (LLMs) for reasoning typically focuses on deductive tasks such as mathematics and coding where correctness is verifiable. Yet, many real-world reasoning problems are inductive: agents must infer uncertain beliefs from sparse, ambiguous observations. There are challenges to using standard fine-tuning methods for inductive reasoning, including difficulties in curating large-scale, high-quality labeled datasets and in handling targets that are inherently distributional. In this work, we introduce a novel approach, called Program-based Posterior Training (PPT), to address these limitations: we use an LLM to generate diverse open-world scenarios as probabilistic programs, run probabilistic inference to produce distributional target responses to queries, and then fine-tune on these probabilistic soft labels. Using this approach, we fine-tune LLMs on 10,000 programmatically generated scenarios and evaluate on held-out motifs, human-labeled judgments, and external benchmarks. Overall, PPT substantially improves estimation accuracy on held-out inductive tasks, increases alignment with human judgments, and transfers to external benchmarks for estimation and calibration. Additionally, the gains in raw calibration are not subsumed by post-hoc temperature scaling, showing that the models have more deeply internalized uncertainty compared to output rescaling. Together, these results suggest that probabilistic-program-mediated fine-tuning is a promising approach for post-training LLMs to reliably perform approximate inductive inference.

Liyi Zhang, Akshay K. Jagadish, Brenden M. Lake +1

Department of Computer Science Princeton University · Princeton AI Lab Princeton University · Department of Psychology and Computer Science Princeton University

Language Model Calibration LLM Uncertainty Estimation LLM Post-Training Probabilistic Programming Inductive Reasoning in Language Models Large Reasoning Models

May 26, 2026

In LLM Reasoning, there is Irrationality on top of Value Misalignment

Significant progress has been made in aligning LLMs with target value functions. We argue that, even when an LLM has been well aligned in (post-)training, it may still fail to maximise the aligned value in reasoning. We mathematically formalise this gap as rational value risk: the utility discrepancy between a model's deployed reasoning strategy and its rational counterpart whose responses maximise utility in the steepest direction. The estimation error of rational value risk is further decomposed into three components from bounded prompts, bounded responses, and imperfect verifiers. Extensive experiments are conducted, covering models Llama-3.1, Qwen-2.5, Tülu-3 families (7B-72B), GPT-5.2, GPT-5.5, and DeepSeek-V4, and benchmarks UltraFeedback, AlpacaEval, GSM8K, MATH, HumanEval, and MathArena. The results validate that (1) rational value risk is widespread; (2) value alignment can reduce, but cannot avoid, it; (3) self-consistency can improve rationality; and (4) a longer chain of thought improves rationality but with diminishing returns. The code is at https://github.com/EVIEHub/LLM-Rationality

Kejiang Qian, Fengxiang He

University of Edinburgh

LLM Alignment LLM Reasoning Large Reasoning Models

May 26, 2026

Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal

Large reasoning models (LRMs) generate chain-of-thought (CoT) traces before producing final outputs, introducing a dynamic internal state that may complicate control mechanisms such as refusal. Unlike instruction-tuned LLMs, where refusal is mediated by a single directional subspace, refusal in large reasoning models (LRMs) additionally depends on the CoT. In DeepSeek-R1-Distill-LLaMA-8B, activation steering reverses refusal in only 39% of cases when the CoT is kept fixed, but removing the CoT entirely increases this to 70%, indicating that the CoT actively reinforces refusal. In a two-stage intervention where the model regenerates its CoT under activation steering, refusal is reversed in 94% of cases, while the resulting CoT alone retains 48% of this effect even after steering is removed. This suggests that the CoT can carry and reconstruct the compliance signal independently. These findings indicate that refusal in LRMs is jointly encoded in residual stream activations and CoT. This joint activation makes LRM more robust against activation-level interventions alone, but exposes CoT to a possible alternative surface attack.

Kia-Jüng Yang, Dominik Meier, Jiachen Zhao +2

University of Göttingen, Germany · LKA NRW, Germany · Northeastern University, Boston, MA, USA.

Reasoning Trace Analysis LLM Refusal Behavior Causal Interventions in Language Models Refusal Behavior in Language Models Activation Steering CoT Reasoning+2

May 25, 2026

Harmony in Diversity: Multi-domain Contrastive Policy Optimization for Large Reasoning Models

Post-training via Reinforcement Learning (RL) has enabled Large Reasoning Models (LRMs) to achieve strong performance in individual domain. However, real-world applications increasingly require general-purpose reasoners rendering strong performance across diverse domains. Mixed-domain post-training aims to achieve this goal by jointly training with mixed domain data, but this often induces capability compromise and degradation among different domains. Existing methods attribute this performance degradation to harmful cross-domain interactions and propose various strategies to mitigate them, but these strategies may also impede beneficial knowledge sharing across domains and in turn fail to match or surpass single-domain performance. To address this problem, we propose Multi-domain Contrastive Policy Optimization (MCPO), which uses contrastive learning to utilize both positive and negative cross-domain interactions for knowledge sharing and competition. Specifically, we partition each rollout generated by LRMs according to its underlying reasoning structures and use reasoning segments to capture these structures. We thus formulate positive and negative pairs of reasoning segments as mutually augmented examples, which provide supportive and competing signals for knowledge sharing. Subsequently, we design complementary contrastive objectives for cross-domain knowledge sharing and intra-domain knowledge consolidation, targeting compatibility across domains and discriminability within each domain to form a harmonious reasoning space. Experimental results across a broad range of domains show that MCPO alleviates performance degradation caused by mixed-domain training and outperforms single-domain training in most cases.

Zongji Yu, Wenshui Luo, Yiliu Sun +5

Shanghai Jiao Tong University · Shanghai AI Laboratory · Shandong University

Reinforcement Learning RL for Language Model Reasoning Cross-Domain Transfer Learning Multi-Task RL Contrastive RL Large Reasoning Models

May 24, 2026

Better, Faster: Harnessing Self-Improvement in Large Reasoning Models

Self-improvement training enables the large reasoning models (LRMs) to improve themselves by self-generating reasoning trajectories as training data without external supervision. However, we find that this method often falls short in complex reasoning tasks and even leads to model collapse. Through a series of preliminary analyses, we reveal two problems: (1) data imbalance, where most training samples are simple, but the challenging yet crucial samples are scarce; (2) overthinking, where many undesired samples with redundant reasoning steps are used for self-training. To this end, we propose HSIR, which effectively Harnesses Self-Improvement in large Reasoning models via two simple-yet-effective approaches. Specifically, HSIR introduces a verify-then-exit sampling strategy to mitigate data imbalance by efficiently collecting more accurate solutions for difficult queries, and designs an Intrinsic Diversity score to quantify overthinking and filter out the undesired solutions. We apply HSIR to various post-training paradigms, among which we further propose H-GRPO, an enhanced GRPO algorithm that leverages the intrinsic diversity as an external reward to encourage concise and diverse reasoning via reinforcement learning. Extensive results show that HSIR not only effectively enhances the reasoning performance, i.e., bringing up to +10.9% average performance gains, but also significantly improves the reasoning efficiency by reducing up to 42.4% relative inference overhead.

Qihuang Zhong, Liang Ding, Juhua Liu +3

1Nanyang Technological University, Singapore · 2Alibaba Group · School of Computer Science, Wuhan University, China +1

Overthinking in Language Models RL for Language Model Reasoning Language Model Self-Improvement LLM Reasoning Large Reasoning Models

May 23, 2026

Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in reasoning and generation tasks and are increasingly deployed in real-world applications. However, their explicit chain-of-thought (CoT) mechanism introduces new security risks, making them particularly vulnerable to jailbreak attacks. Existing approaches often rely on static CoT templates to elicit harmful outputs, but such fixed designs suffer from limited diversity, adaptability, and effectiveness. To overcome these limitations, we propose an adaptive evolutionary CoT jailbreak framework, called AE-CoT. Specifically, the method first rewrites harmful goals into mild prompts with teacher role-play and decomposes them into semantically coherent reasoning fragments to construct a pool of CoT jailbreak candidates. Then, within a structured representation space, we perform multi-generation evolutionary search, where candidate diversity is expanded through fragment-level crossover and a mutation strategy with an adaptive mutation-rate control mechanism. An independent scoring model provides graded harmfulness evaluations, and high-scoring candidates are further enhanced with a harmful CoT template to induce more destructive generations. Extensive experiments across multiple models and datasets demonstrate the effectiveness of the proposed AE-CoT, consistently outperforming state-of-the-art jailbreak methods.

Jianan Li, Simeng Qin, Xiaojun Jia +5

Northeastern University · The University of Hong Kong, Hong Kong, China · BraneMatrix AI, China +7

Adversarial Attacks on LLMs LLM Jailbreak Attacks Large Reasoning Models

May 23, 2026

ChaosBench-Logic v2: Evaluating LLM Logical Reasoning over Dynamical Systems at Scale

Standard accuracy on binary reasoning benchmarks hides critical failure modes: prior collapse, inconsistency under paraphrase, and inability to reason about parameter-dependent dynamics. We present ChaosBench-Logic v2, a 40,886-question benchmark over 165 dynamical systems with 27 FOL predicates and 78 axiom edges, together with CARE (Calibration- and Adversarial-Robust Evaluation), a protocol that surfaces these pathologies. Evaluating 14 models, we find that regime-transition reasoning remains near random (MCC = 0.05) even for frontier models, whereas FOL deduction with given premises reaches MCC = 0.52. Per-family decomposition shows that the proprietary-model advantage concentrates on cross-indicator (+0.40) and consistency tasks, while open-source Qwen 2.5-32B dominates indicator diagnostics (0.91 vs. 0.45). Two models exhibit negative MCC on bifurcation questions, confirmed as systematic anti-correlation via confusion-matrix analysis.

Noel Thomas

Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE

LLM Evaluation Language Model Robustness LLM Reasoning Large Reasoning Models

May 22, 2026

Limited Marginal Benefit of Reasoning-Heavy LLM Deployment in ESG Narrative Scoring: A 4-Model Consensus Study on Japanese Listed Firms

Automated scoring of ESG narrative disclosures with large language models (LLMs) is gaining traction, yet whether reasoning-heavy frontier models add value commensurate with their cost remains empirically unsettled. We evaluate this question on a corpus of ten Japanese listed firms across three rubric axes -- quantitative targets, progress-tracking infrastructure, and external-standard alignment -- using a four-model consensus design that combines a reasoning-on frontier model with three reasoning-off contemporaries. Across 120 firm x axis x model scores, the pooled mean absolute deviation between the reasoning-on model and each reasoning-off counterpart is 0.38 on a 5-point scale; only 2% of pairwise comparisons reach a two-point deviation, and none exceeds two points. Per-firm cost accounting shows the reasoning-on arm alone costs roughly 5.6x as much as the three-provider reasoning-off ensemble, for outcomes that differ only within small margins. We conclude that in span-based ESG narrative scoring, reasoning-heavy deployment does not materially improve outcomes relative to reasoning-off consensus, while substantially increasing operational cost. We discuss implications for cost-effective ESG auto-scoring pipelines and LLM deployment governance in applied accountability settings. An earlier version of this work is available on SSRN (Abstract ID 6683303).

Hiroyuki Kokubu

Kansai University

LLM Evaluation Language Model Ensembles Efficient Language Model Inference Large Reasoning Models

May 21, 2026

PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning

Large Reasoning Language Models (LRMs) tackle complex tasks through test-time scaling, generating long-form Chain-of-Thought (CoT) trajectories during inference. These trajectories contain reflection markers such as wait, but, and alternatively, accompanying hesitation, revision, and alternative explorations. Recent test-time control methods use these markers to steer reasoning, but treating them as one coarse-grained category can obscure their distinct intervention effects. We study how marker identity and reasoning context shape these effects. Type-wise suppression produces different accuracy--length tradeoffs, while fixed-prefix interventions show that the relative benefit of continuation and revision varies across prefixes and tasks. Motivated by these findings, we introduce PathCal, a training-free controller that adjusts the strength of a fixed continuation bias using instantaneous competition among continuation, revision, and alternative-opening markers. It applies finite logit adjustments without additional model forward passes. An exact log-odds identity and frozen-prefix probes establish its local directional effect. Experiments show that PathCal improves the accuracy--length tradeoff in many mathematical reasoning settings and also reduces generation length in coding and multilingual mathematics.

Lingyu Jiang, Zirui Li, Lingyu Xu +7

Tohoku University · Texas A&M University · Worcester Polytechnic Institute

Efficient Language Model Reasoning Efficient Language Model Inference Inference-Time Guidance LLM Reasoning Large Reasoning Models Reasoning Trace Analysis

May 20, 2026

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning

Explicit reasoning models are trained to produce intermediate reasoning traces before final answers, but downstream fine-tuning is often performed on ordinary instruction--response data that contains no such traces. We show that this mismatch can induce reasoning-trace collapse: a fine-tuned model continues to produce plausible final answers while losing the structurally valid explicit reasoning traces that made it a reasoning model in the first place. We introduce a structural evaluation framework that separates answer correctness from reasoning-trace validity, measuring valid, empty, missing, and truncated reasoning alongside reasoning-conditioned task performance. Using this framework, we study four open-weight reasoning models and find that standard supervised fine-tuning can rapidly suppress valid reasoning traces, and that answer-only metrics can substantially obscure this failure: in several settings, performance conditional on valid reasoning remains high while the rate of valid reasoning falls sharply. We further show that simple loss-masking strategies can substantially mitigate collapse without requiring teacher-generated reasoning traces. These results suggest that evaluations of fine-tuned reasoning models should report structural reasoning reliability metrics in addition to final-answer performance, especially when adaptation data does not contain explicit reasoning traces.

Lukas Twist, Helen Yannakoudakis, Jie M. Zhang

King’s College London London, UK

Supervised Fine-Tuning Reasoning Evaluation Structured Reasoning Large Reasoning Models Reasoning Trace Analysis