Large Language Model Reasoning

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

35 new papers

A weekly snapshot of new work published in Large Language Model Reasoning.

Period ending 2026-09-14

23 new papers

A weekly snapshot of new work published in Large Language Model Reasoning.

Period ending 2026-09-07

41 new papers

A weekly snapshot of new work published in Large Language Model Reasoning.

Inside this field

Focused directions

Focused topic

Large Language Model Reasoning

Within Large Language Model Reasoning

617 papersExplore

Focused topic

Chain-of-Thought Reasoning

Within Large Language Model Reasoning

231 papersExplore

Focused topic

Reasoning Benchmark

Within Large Language Model Reasoning

228 papersExplore

Focused topic

Large Reasoning Models

Within Large Language Model Reasoning

222 papersExplore

Focused topic

Reasoning Traces

Within Large Language Model Reasoning

138 papersExplore

Focused topic

Efficient Latent Reasoning

Within Large Language Model Reasoning

113 papersExplore

Focused topic

Thinking

Within Large Language Model Reasoning

75 papersExplore

Focused topic

Table Reasoning Datasets

Within Large Language Model Reasoning

71 papersExplore

Focused topic

Reasoning Trajectory

Within Large Language Model Reasoning

62 papersExplore

Focused topic

Rationales

Within Large Language Model Reasoning

48 papersExplore

Focused topic

Efficient Chain-Of-Thought Reasoning

Within Large Language Model Reasoning

45 papersExplore

Focused topic

Reasoning Chain

Within Large Language Model Reasoning

39 papersExplore

1,670 papers

Latest in Large Language Model Reasoning

Browse all topics →

Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning
May 14, 2026Jingjing Wang, Xiwen Chen, Wenhui Zhu +6Coding Agents Efficient Latent Reasoning
Training on Documents About Monitoring Leads to CoT Obfuscation
May 14, 2026Reilly Haskins, Bilal Chughtai, Joshua EngelsObfuscation Chain-of-Thought Reasoning
OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation
May 14, 2026Shang Zhou, Wenhao Chai, Kaiyuan Liu +3Large Language Model Reasoning Test-Time Scaling
Natural Synthesis: Outperforming Reactive Synthesis Tools with Large Reasoning Models
May 14, 2026Frederik Schmitt, Matthias Cosler, Niklas Metzger +4Constraint-Aware Synthesis Formal Verification
Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Scaling
May 14, 2026Rongman Xu, Yifei Li, Tianzhe Zhao +3LLM Inference Efficiency Large Language Model Reasoning
Case-Based Calibration of Adaptive Reasoning and Execution for LLM Tool Use
May 14, 2026Renning Pang, Tian Lan, Leyuan Liu +3Large Language Model Reasoning Multi-Turn Tool-Use Agent
Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy
May 14, 2026Langzhou He, Junyou Zhu, Yue Zhou +7Agentic Reinforcement-Learning Framework Token-Level Uncertainty
From Table to Cell: Attention for Better Reasoning with TABALIGN
May 14, 2026Tung Sum Thomas Kwok, Zeyong Zhang, Xinyu Wang +6Tabular Data Large Language Model Reasoning
Stateful Reasoning via Insight Replay
May 14, 2026Bin Lei, Caiwen Ding, Jiachen Yang +2Chain-of-Thought Reasoning Reasoning Trajectory
Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning
May 14, 2026Taebong Kim, Youngsik Hong, Minsik Kim +4Large Language Model Reasoning Model Merging
Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces
May 14, 2026Sanjoy Chowdhury, Dinesh ManochaReasoning Traces Reasoning Benchmark
Dynamic Latent Routing
May 14, 2026Fangyuan Yu, Xin Su, Amir AbdullahEfficient Latent Reasoning Markov Decision Processes
Minimal-Intervention KV Retention via Set-Conditioned Diversity
May 14, 2026Libo Sun, Po-wei Harn, Peixiong He +1Key-Value Cache Compression Cache
Agentic Systems as Boosting Weak Reasoning Models
May 13, 2026Varun Sunkaraneni, Pierfrancesco Beneventano, Riccardo Neumarker +2Large Reasoning Models Agentic Systems
Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning
May 13, 2026Yu Gu, Zijun Yu, Vahid Partovi Nia +1Chain-of-Thought Reasoning Self-Consistency
Distribution Corrected Offline Data Distillation for Large Language Models
May 13, 2026Yumeng Zhang, Zhengbang Yang, Yevin Nikhel Goonatilake +1Reasoning Traces
PolitNuggets: Benchmarking Agentic Discovery of Long-Tail Political Facts
May 13, 2026Yifei ZhuPolitical Discourse Fact-Checking
An LLM-Based System for Argument Mining
May 13, 2026Paulo Pirozelli, Victor Hugo Nascimento Rocha, Fabio G. Cozman +1Abstract Argumentation Reasoning Graphs
Guide, Think, Act: Interactive Embodied Reasoning in Vision-Language-Action Models
May 13, 2026Yiran Ling, Qing Lian, Jinghang Li +6Vision-Language-Action Models Executable Robot Behavior
How to Interpret Agent Behavior
May 13, 2026Jie Gao, Kaiser Sun, Jen-tse Huang +8Reasoning Trajectory
Multilingual OCR-Aware Fine-Tuning and Prompt-Guided Chain-of-Thought Reasoning for Multimodal Large Language Models
May 13, 2026Qinwu Xu, Yifan Jiang, Haoyu RenMulti-Modal Large Language Models Deepseek-Ocr
Many-Shot CoT-ICL: Making In-Context Learning Truly Learn
May 13, 2026Tsz Ting Chung, Lemao Liu, Mo Yu +1In-Context Learning In-Context
Why We Need World Models for AGI: Where LLMs Fail and How World Models May Outperform
May 13, 2026Feisal Alaswad, Batoul Aljaddouh, Maher Alrahhal +2Latent World Models Efficient Latent Reasoning
Teaching and Learning under Deductive Errors
May 13, 2026Jan Arne Telle, Brigt Håvardstun, Jose Hernandez-OralloReasoning Errors Errors
STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning
May 13, 2026Junjie Zhang, Guozheng Ma, Shunyu Liu +5Large Language Model Reasoning Reasoning Benchmark
Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models
May 13, 2026Shuqiang Wang, Wei Cao, Jiaqi Weng +4Large Language Model Reasoning Large Reasoning Models
What properties of reasoning supervision are associated with improved downstream model quality?
May 13, 2026Mikołaj Langner, Dzmitry Pihulski, Jan Eliasz +5Table Reasoning Datasets Downstream Fine-Tuning
Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning
May 13, 2026Junlong Ke, Zichen Wen, Weijia Li +2Unsupervised On-Policy Self-Distillation On-Policy Distillation
An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing
May 13, 2026Hanwen Zhang, Dusit Niyato, Wei Zhang +2Edge Computing Last Mile
Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics
May 13, 2026Moritz Firsching, Paul Lezeau, Salvatore Mercuri +8Conjecture Mathematics
Strikingness-Aware Evaluation for Temporal Knowledge Graph Reasoning
May 13, 2026Rikui Huang, Shengzhe Zhang, Wei WeiTemporal Knowledge Graphs Information Retrieval Metrics
AcquisitionSynthesis: Targeted Data Generation using Acquisition Functions
May 13, 2026Ishika Agarwal, Sofia Stoica, Emre Can Acikgoz +4Synthetic Data Data Generation
Knowledge Distillation for Low-Resource Open-source Text-to-SQL Model
May 13, 2026Tianhao Qiu, Xiaojun ChenText-To-Sql Table Reasoning Datasets
Retrieval-Augmented Tutoring for Algorithm Tracing and Problem-Solving in AI Education
May 13, 2026Mragisha Jain, Tirth Bhatt, Griffin Pitts +6Tutors Socratic Dialogue
Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation
May 13, 2026Jiashuo Sun, Jimeng Shi, Yixuan Xie +10Multi-Hop Reasoning Reasoning Trajectory
Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective
May 13, 2026Feng Zhang, Xinhong Ma, Ziqiang Dong +5Group Relative Policy Optimization Reinforcement Learning With Verifiable Reward
From Instance Selection to Fixed-Pool Data Recipe Search for Supervised Fine-Tuning
May 13, 2026Haodong Wu, Jiahao Zhang, Lijie Hu +1Supervised Fine-Tuning Table Reasoning Datasets
CommonWhy: A Dataset for Evaluating Entity-Based Causal Commonsense Reasoning in Large Language Models
May 13, 2026Armin Toroghi, Faeze Moradi Kalarde, Scott SannerTable Reasoning Datasets Knowledge Graphs
CoT-Guard: Small Models for Strong Monitoring
May 12, 2026Nirav Diwan, Han Wang, Berkcan Kapusuzoglu +6Guard Small Models
CHAL: Council of Hierarchical Agentic Language
May 12, 2026Tommaso Giovannelli, Griffin D. KentMulti-Agent Debate Abstract Argumentation
LGMT: Logic-Grounded Metamorphic Testing for Evaluating the Reasoning Reliability of LLMs
May 12, 2026Zenghui Zhou, Man Li, Xiaoke Fang +3Reasoning Benchmark
Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents
May 12, 2026Nishad Singhi, Christian Bialas, Snehal Jauhri +4Mllm-Based Action Selection
OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning
May 12, 2026Yuxiao Yang, Xiaoyun Wang, Weitong ZhangUnsupervised On-Policy Self-Distillation On-Policy Distillation
Context Convergence Improves Answering Inferential Questions
May 12, 2026Jamshid Mozafari, Bhawna Piryani, Adam JatowtLarge Language Model Reasoning Large Language Model Performance
MedHopQA: A Disease-Centered Multi-Hop Reasoning Benchmark and Evaluation Framework for LLM-Based Biomedical Question Answering
May 12, 2026Rezarta Islamaj, Robert Leaman, Joey Chan +13Multi-Hop Question Answering Benchmarks Biomedical Knowledge
Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics
May 12, 2026Jishnu Sethumadhavan Nair, Patrice Bechard, Rishabh Maheshwary +14Enterprise Systems World Models
Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model
May 12, 2026Chenfeng Wang, Wei He, Xuhan Zhu +10Latent Visual Reasoning Large Vision Language Models
Intermediate Artifacts as First-Class Citizens: A Data Model for Durable Intermediate Artifacts in Agentic Systems
May 12, 2026Josh Rosen, Seth RosenAgentic Systems Content Provenance
Property-Level Reconstructability of Agent Decisions: An Anchor-Level Pilot Across Vendor SDK Adapter Regimes
May 12, 2026Oleg SolozobovAgent Decisions Reasoning Traces
LLMs and the ZPD
May 12, 2026Peter WallisLarge Language Thinking
From Noise to Diversity: Random Embedding Injection in LLM Reasoning
May 12, 2026Heejun Kim, Seungpil Lee, Jewon Yeom +5Large Language Model Reasoning Instruction-Tuned Models
Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training
May 12, 2026Qihuang Zhong, Liang Ding, Wenjie Xuan +3Multimodal Reasoning Multimodal Learning
UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
May 12, 2026Houcheng Jiang, Jiajun Fu, Junfeng Fang +4Latent Visual Reasoning Visual Reasoning
When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel
May 12, 2026Wenkai Li, Fan Yang, Ananya Hazarika +2Reasoning Traces Chain-of-Thought Reasoning
Persistent and Conversational Multi-Method Explainability for Trustworthy Financial AI
May 12, 2026Georgios Makridis, Georgios Fatouros, John Soldatos +2Explainable Artificial Intelligence Xai
Evolutionary Task Discovery: Advancing Reasoning Frontiers via Skill Composition and Complexity Scaling
May 12, 2026Liqin Ye, Yanbin Yin, Michael Galarnyk +3Large Language Model Reasoning Curriculum Reinforcement Learning
Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation
May 12, 2026Seonghoon Yu, Dongjun Nam, Byung-Kwan Lee +1Multimodal Reasoning Benchmarks Thinking
Seirênes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning
May 12, 2026Chi Zhang, Haibo Qiu, Qiming Zhang +3Large Language Model Reasoning Recursive Reasoner
OmniThoughtVis: A Scalable Distillation Pipeline for Deployable Multimodal Reasoning Models
May 12, 2026Yuanhao Yue, Chengyu Wang, Yuanjie Lyu +2Multimodal Reasoning Benchmarks Multi-Modal Large Language Models
Nice Fold or Hero Call: Learning Budget-Efficient Thinking for Adaptive Reasoning
May 12, 2026Zhaomeng Zhou, Lan Zhang, Junyang Wang +2Thinking Hard

May 14, 2026 · cs.AIJ/K move · Enter open · S save

Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning

Jingjing Wang, Xiwen Chen, Wenhui Zhu, Huayu Li+5

Clemson University · Morgan Stanley · Arizona State University · University of Arizona

LLM-powered coding agents spend the majority of their token budget reading repository files, yet much of the retrieved code is irrelevant to the task at hand. Existing learned pruners compress this context with a single-objective sequence labeler, collapsing all facets of code relevance into one score and one transition matrix. We show that this formulation creates a modeling bottleneck: a single CRF transition prior must serve heterogeneous retention patterns, including contiguous semantic spans and sparse structural support lines. We propose LaMR (Latent Multi-Rubric), a structured pruning framework that decomposes code relevance into two interpretable quality dimensions, semantic evidence and dependency support, each modeled by a dedicated CRF with dimension-specific transition dynamics. A mixture-of-experts gating network dynamically weights the per-rubric emissions conditioned on the query, and a final CRF layer on the fused emissions produces the aggregate keep-or-prune decision. To supervise each dimension without additional annotation cost, we derive multi-rubric labels from the existing training corpus via AST-based program analysis, simultaneously denoising the teacher's binary labels. By effectively filtering distracting noise, LaMR frequently matches or even outperforms unpruned full-context baselines. Experiments on four benchmarks (SWE-Bench Verified, SWE-QA, LCC, LongCodeQA) show that LaMR wins 12 of 16 head-to-head multi-turn comparisons. It saves up to 31% more tokens on multi-turn agent tasks and improves Exact Match by up to +3.5 on single-turn tasks, while performance is frequently enhanced by denoising the context, and any remaining drops are marginal.

Coding Agents Efficient Latent Reasoning Rubrics Relevance Hidden Markov Models

Open paper Ask about it PDF