LLM Reasoning

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

68 papers in the last four weeks, up 143% on the four weeks before. 0.7% of all new papers.

Jul 13Week of Sep 28

Latest papers 650

All topics

Decouple before Integration: Test-time Synthesis of SFT and RLVR Task Vectors
May 1, 2026Chaohao Yuan, Chenghao Xiao, Yu Rong +2Task Arithmetic Language Model Merging
Department of Systems Engineering and Engineering Management, Chinese University of Hong Kong, Hong Kong, China · DAMO Academy, Alibaba Group, Hangzhou, China · Hupan Lab, Hangzhou, China +1
Impact of Task Phrasing on Presumptions in Large Language Models
May 1, 2026Kenneth J. K. OngPrompt Sensitivity LLM Prompting
AI.DA STC · ST Engineering, Singapore
Assert, don't describe: Linguistic features that shift LLM reasoning about animal welfare
Apr 30, 2026Jasmine Brazilek, Harper DunnMoral Reasoning in Language Models Language Model Post-Training
Compassion Aligned Machine Learning (CaML) · Independent researcher
Retrieval-Augmented Reasoning for Chartered Accountancy
Apr 30, 2026Jatin Gupta, Akhil Sharma, Saransh Singhania +1Retrieval-Augmented Generation Financial QA
Dept. of Computer Science and Engineering Sharda University, Greater Noida, India · Sharda University, Greater Noida, India
TUR-DPO: Topology- and Uncertainty-Aware Direct Preference Optimization
Apr 30, 2026Abdulhady Abas Abdullah, Fatemeh Daneshfar, Seyedali Mirjalili +1LLM Alignment Direct Preference Optimization
Artificial Intelligence and Innovation Centre, University of Kurdistan, Erbil, Iraq · Department of Computer Engineering, University of Kurdistan, Iran · Centre for Artificial Intelligence Research and Optimisation, Torrens University Australia, Brisbane, Australia +2
RSAT: Structured Attribution Makes Small Language Models Faithful Table Reasoners
Apr 30, 2026Jugal Gajjar, Kamalasankari SubramaniakuppusamyTable QA LLM Grounding
Department of Computer Science, The George Washington University, USA
Investigating LLM's Problem Solving Capability -- a Study on Statics Questions
Apr 30, 2026Tanner Culleton, Hung-Fu ChangLLM Evaluation Physical Reasoning
1R. B, Annis School of Engineering, University of Indianapolis, Indianapolis, IN, 46227, USA
Reasoning over Object Descriptions Improves Coreference Resolution in Task-Based Dialogue Systems
Apr 30, 2026Oier Ijurco, Oier Lopez de LacalleCoreference Resolution Conversational Agents
HiTZ Center - Ixa, University of the Basque Country UPV/EHU
Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models
Apr 29, 2026Xingwei Tan, Marco Valentino, Mahmud Elahi Akhter +3LLM Interpretability Instruction Following
School of Computer Science, University of Sheffield · School of EECS, Queen Mary University of London · The Alan Turing Institute
Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation
Apr 29, 2026Shouren Wang, Wang Yang, Chuang Ma +7Mixture-of-Experts Language Models LLM Reasoning
1Case Western Reserve University · 2NII LLMC, Japan · 3Michigan State University
Select to Think: Unlocking SLM Potential with Local Sufficiency
Apr 29, 2026Wenxuan Ye, Yangyang Zhang, Xueli An +2Small Language Models Efficient Language Model Reasoning
1Technical University of Munich · 3Ludwig Maximilian University of Munich · 2Huawei Technologies +2
PAINT: Partial-Solution Adaptive Interpolated Training for Self-Distilled Reasoners
Apr 29, 2026Zhiquan Tan, Yinrong HongLanguage Model Distillation LLM Reasoning
Tsinghua University · Beihang University
Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokens
Apr 29, 2026Zhenyu Zhao, Sander Land, Daniel M. Bikel +1LLM Compression LLM Interpretability
Writer, Inc.
Assistants, Not Architects: The Role of LLMs in Networked Systems Design
Apr 28, 2026Pratyush Sahu, Rahul Bothra, Venkat Arun +3Satisfiability Modulo Theories Hardware-Software Co-Design
Georgia Tech · UIUC · UT Austin +1
One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement
Apr 28, 2026Yixiao Zhou, Dongzhou Cheng, zhiliang wu +3LLM Alignment RL for Language Model Reasoning
Zhejiang University · Shanghai Innovation Institute · 1Zhejiang University, 2Shanghai Innovation Institute +9
Dual-Track CoT: Budget-Aware Stepwise Guidance for Small LMs
Apr 27, 2026Sagnik Chatterjee, Atharva Patil, Sricharan RameshCoT Reasoning Small Language Models
AdapTime: Enabling Adaptive Temporal Reasoning in Large Language Models
Apr 27, 2026Yimin Deng, Yejing Wang, Zhenxi Lin +8Temporal Reasoning Temporal QA
Xi’an Jiaotong University · City University of Hong Kong · Tencent Jarvis Lab +1
Pruning via Causal Attribution Preserves Reasoning Performance in Large Language Models
Apr 27, 2026Amogh Sheth, Biruk Assefa, Yi Wen Huang +2LLM Pruning Self-Attention
Edison Academy Magnet School · State University of New York College at Plattsburgh · The University of Texas at Austin +2
Knowledge Vector of Logical Reasoning in Large Language Models
Apr 26, 2026Zixuan Wang, Yuanyuan LeiLLM Interpretability Representation Engineering
Department of Computer & Information Science and Engineering University of Florida, Gainesville, FL, United States
SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
Apr 26, 2026Alexis Limozin, Eduard Durech, Torsten Hoefler +2RL for Language Model Reasoning Policy Optimization
ETH AI Center, ETH Zürich · EPFL · Allen Institute for AI
Tandem: Riding Together with Large and Small Language Models for Efficient Reasoning
Apr 26, 2026Zichuan Fu, Xian Wu, Guojing Li +7Efficient Language Model Reasoning LLM Inference Acceleration
City University of Hong Kong · Tencent Jarvis Lab · Renmin University of China +1
Ulterior Motives: Detecting Misaligned Reasoning in Continuous Thought Models
Apr 25, 2026Sharan RamjeeLLM Backdoor Attacks Moral Reasoning in Language Models
Stanford University
When Corrective Hints Hurt: Prompt Design in Reasoner-Guided Repair of LLM Overcaution on Entailed Negations under OWL2DL
Apr 25, 2026Yijiashun Qi, Xiang Xu, Yuxuan LiLLM Self-Correction Logical Reasoning
University of Michigan · ByteDance Inc. · University of Pennsylvania
VeriLLMed: Interactive Visual Debugging of Medical Large Language Models with Knowledge Graphs
Apr 25, 2026Yurui Xiang, Xingyi Mao, Rui Sheng +7Healthcare LLM Auditing
Small Language Model Helps Resolve Semantic Ambiguity of LLM Prompt
Apr 25, 2026Zhenzhen Huang, Chaoning Zhang, Fachrina Dewi Puspitasari +4LLM Prompting Prompt Optimization
School of Computer Science and Engineering, University of Electronic Science and Technology of China · Department of Electronic Engineering, Kyung Hee University
Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought
Apr 24, 2026Keshav Ramji, Tahira Naseem, Ramón Fernandez AstudilloEfficient Language Model Reasoning Implicit Reasoning in Language Models
IBM Research AI
Large Language Models Decide Early and Explain Later
Apr 24, 2026Ayan Datta, Zhixue Zhao, Bhuvanesh Verma +3Efficient Language Model Reasoning LLM Inference Acceleration
IIIT Hyderabad · University of Sheffield, UK · Goethe University, Frankfurt am Main, Germany
Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models
Apr 24, 2026Prakul Sunil Hiremath, Harshit R. HiremathConfidence Estimation in Language Models CoT Reasoning
Department of Computer Science and Engineering Visvesvaraya Technological University, Belagavi · Department of Computer Science and Business System SG Balekundri Institute of Technology, Belagavi
Thinking with Reasoning Skills: Fewer Tokens, More Accuracy
Apr 23, 2026Guangxiang Zhao, Qilong Shi, Xusen Xiao +3Efficient Language Model Reasoning Efficient Language Model Inference
Qiyuan Tech · Tsinghua University · The University of Hong Kong +1
To See the Unseen: on the Generalization Ability of Transformers in Symbolic Reasoning
Apr 23, 2026Nevena Lazić, Liam Fowl, András György +1Logical Reasoning Decoder-Only Language Models

May 1, 2026, cs.LGJ/K move · Enter open · S save

Decouple before Integration: Test-time Synthesis of SFT and RLVR Task Vectors

Chaohao Yuan, Chenghao Xiao, Yu Rong, Hong Cheng+1

Department of Systems Engineering and Engineering Management, Chinese University of Hong Kong, Hong Kong, China · DAMO Academy, Alibaba Group, Hangzhou, China · Hupan Lab, Hangzhou, China+1

Task Arithmetic Language Model Merging LLM Post-Training LLM Reasoning

Open paper AskPDF arXiv

SFT and RLVR represent two fundamental yet distinct paradigms for LLM post-training, each excelling in distinct dimensions. SFT expands knowledge breadth while RLVR enhances reasoning depth. Yet integrating these complementary strengths remains a formidable challenge. Sequential training can cause catastrophic forgetting, and joint optimization often suffers from severe gradient conflicts. We analyze SFT and RLVR through the lens of task vectors and reveal three structural properties behind these failures: a 30* magnitude disparity, 45* sign interference, and heterogeneous module-wise update distributions. These findings show SFT and RLVR are difficult to integrate directly, but they also suggest that the two paradigms modify partly complementary components of the model. Motivated by these observations, we propose Decoupled Test-time Synthesis (DoTS), a post-hoc framework allows SFT and RLVR checkpoints to be trained independently and synthesizes their capabilities only at inference time via task vector arithmetic, without updating model parameters. To reduce interference, DOTS applies selective sparsification with norm-preserving rescaling. It then uses Bayesian optimization on a small set of unlabeled queries to search for combination coefficients on the Pareto frontier of consistency and perplexity. Empirically, \ours matches or exceeds the performance of training-based SFT--RLVR integration methods across multiple mathematical reasoning benchmarks, incurring only

\sim

3% of the computational cost. When applied to stronger post-trained checkpoints, DOTS surpasses SOTA models and generalizes to out-of-domain benchmarks without re-tuning. Code is available at https://github.com/chaohaoyuan/DoTS.

Momentum

Related topics

Latest papers 650