Computation and Language

Papers filed under cs.CL on arXiv, each one already summarized by Paperlayer. Open any of them to read the summary beside the original PDF, with every point linked to the line, figure, or table it came from.

Search paper metadata (including unsummarized papers)

10,381 to 10,440 of 11,270

Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models
Yanming Zhang, Yihan Bian, Jingyuan Qi +3
cs.CLarXiv:2606.16700v12026
LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching
Jaward Sesay, Yue Yu, Siwei Dong +1
cs.CLcs.AIcs.HCarXiv:2606.16428v32026
Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion
Yi Lu, Zhuofeng Li, Ping Nie +7
cs.AIcs.CLarXiv:2606.14885v12026
ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages
Tanmoy Kanti Halder, Akash Ghosh, Subhadip Baidya +2
cs.CLcs.AIarXiv:2606.13572v22026
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
Mengyu Zheng, Kai Han, Boxun Li +13
cs.LGcs.CLarXiv:2606.12344v12026
Measuring Epistemic Resilience of LLMs Under Misleading Medical Context
Hongjian Zhou, Xinyu Zou, Jinge Wu +19
cs.CLarXiv:2606.12291v22026
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code
Yitong Zhang, Shiteng Lu, Jia Li
cs.CRcs.AIcs.CLarXiv:2606.11817v12026
Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories
Kevin Qinghong Lin, Batu EI, Yuhong Shi +3
cs.CVcs.CLcs.CYarXiv:2606.11176v12026
N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization
Xukun Zhu, Hang Yu, Peng Di +1
cs.LGcs.CLarXiv:2606.10768v12026
When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models
Sai Kartheek Reddy Kasu, Nils Lukas, Samuele Poppi
cs.AIcs.CLcs.LGarXiv:2606.10740v22026
WebChallenger: A Reliable and Efficient Generalist Web Agent
Jayoo Hwang, Xiaowen Zhang, Vedant Padwal
cs.CLarXiv:2606.10423v12026
Unsupervised Skill Discovery for Agentic Data Analysis
Zhisong Qiu, Kangqi Song, Shengwei Tang +4
cs.AIcs.CLcs.LGarXiv:2606.06416v12026
Compress-Distill: Reasoning Trace Compression for Efficient Knowledge Distillation
Maxime Griot, Paul Steven Scotti, Tanishq Mathew Abraham
cs.LGcs.CLarXiv:2606.05988v12026
Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data
XiuYu Zhang, Yi Shan, Junfeng Fang +1
cs.CLarXiv:2606.05122v12026
The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?
Xinyu Lu, Tianshu Wang, Pengbo Wang +8
cs.AIcs.CLarXiv:2606.04455v12026
Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill
Tao Chen, Gangwei Jiang, Pengyu Cheng +10
cs.LGcs.CLarXiv:2606.03980v12026
Trust Region On-Policy Distillation
Xingrun Xing, Haoqing Wang, Boyan Gao +2
cs.LGcs.CLarXiv:2606.01249v32026
OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration
Xinchen Zhang, Bowei Liu, Jiale Liu +7
cs.CLcs.AIcs.CVarXiv:2605.28805v12026
Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations
Sachin Kumar
cs.CLcs.AIcs.LGarXiv:2605.27958v12026
When Gradients Collide: Failure Modes of Multi-Objective Prompt Optimization for LLM Judges
Parth Darshan, Abhishek Divekar
cs.CLcs.AIcs.LGarXiv:2605.26046v22026
AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild
Baiyu Chen, Zechen Li, Wilson Wongso +5
cs.CVcs.AIcs.CLarXiv:2605.22715v22026
Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents
Asaf Yehudai, Lilach Eden, Michal Shmueli-Scheuer
cs.CLcs.AIarXiv:2605.22608v12026
Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles
Jinyang Wu, Guocheng Zhai, Ruihan Jin +7
cs.LGcs.CLarXiv:2605.22177v12026
PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents
Zhuohan Gu, Qizheng Zhang, Omar Khattab +1
cs.AIcs.CLcs.LGarXiv:2605.19932v12026
GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment
Minxuan Lv, Tiehua Mei, Tanlong Du +9
cs.CLarXiv:2605.19577v12026
Self-Improving CAD Generation Agents with Finite Element Analysis as Feedback
Guijin Son, Jehyun Park, Seyeon Park +2
cs.GRcs.CLarXiv:2605.17448v22026
Nexus : An Agentic Framework for Time Series Forecasting
Sarkar Snigdha Sarathi Das, Palash Goyal, Mihir Parmar +6
cs.AIcs.CLcs.LGarXiv:2605.14389v12026
Auditing Agent Harness Safety
Chengzhi Liu, Yichen Guo, Yepeng Liu +8
cs.CLcs.CYarXiv:2605.14271v22026
Learning Agentic Policy from Action Guidance
Yuxiang Ji, Zengbin Wang, Yong Wang +6
cs.CLarXiv:2605.12004v12026
Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient?
Tz-Huan Hsu, Jheng-Hong Yang, Jimmy Lin
cs.IRcs.AIcs.CLarXiv:2605.10848v12026
Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs
Guijin Son, Seungone Kim, Catherine Arnett +73
cs.CLarXiv:2605.09063v32026
RewardHarness: Self-Evolving Agentic Post-Training
Yuxuan Zhang, Penghui Du, Bo Li +11
cs.AIcs.CLcs.CVarXiv:2605.08703v12026
A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models
Zeru Shi, Zhenting Wang, Fan Yang +2
cs.CLarXiv:2605.08504v22026
InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search
Bohan Hou, Jiuning Gu, Jiayan Guo +5
cs.CVcs.CLcs.IRarXiv:2605.07510v12026
Summaries:한국어
Teaching Language Models to Think in Code
Hyeon Hwang, Jiwoo Lee, Jaewoo Kang
cs.CLarXiv:2605.07237v22026
Summaries:한국어
RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation
Ivan Bondarenko, Roman Derunets, Oleg Sedukhin +3
cs.CLcs.AIcs.LGarXiv:2605.04523v12026
Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
Chenchen Zhang
cs.CLarXiv:2605.02801v12026
InfoLaw: Information Scaling Laws for Large Language Models with Quality-Weighted Mixture Data and Repetition
Fengze Liu, Weidong Zhou, Binbin Liu +7
cs.CLarXiv:2605.02364v12026
Summaries:한국어
FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments
Amir Saeidi, Venkatesh Mishra, Souradeep Mukhopadhyay +4
cs.CLarXiv:2604.25135v12026
The Power of Scale for Parameter-Efficient Prompt Tuning
Brian Lester, Rami Al-Rfou, Noah Constant
cs.CLarXiv:2104.08691v22021
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Yinhan Liu, Myle Ott, Naman Goyal +7
cs.CLarXiv:1907.11692v12019
Parameter-Efficient Transfer Learning for NLP
Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski +5
cs.LGcs.CLstat.MLarXiv:1902.00751v22019
Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning
Sanket Badhe, Deep Shah
cs.CLcs.IRarXiv:2602.21103v22026
Diffusion-Pretrained Dense and Contextual Embeddings
Sedigheh Eslami, Maksim Gaiduk, Markus Krimmel +3
cs.LGcs.CLcs.IRarXiv:2602.11151v22026
Summaries:한국어
FollowUpBot: An LLM-Based Conversational Robot for Automatic Postoperative Follow-up
Chen Chen, Jianing Yin, Jiannong Cao +5
cs.HCcs.CLcs.ROarXiv:2507.15502v12025
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Zhihong Shao, Peiyi Wang, Qihao Zhu +8
cs.CLcs.AIcs.LGarXiv:2402.03300v32024
Qwen Technical Report
Jinze Bai, Shuai Bai, Yunfei Chu +45
cs.CLarXiv:2309.16609v12023
RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
Anthony Brohan, Noah Brown, Justice Carbajal +51
cs.ROcs.CLcs.CVarXiv:2307.15818v12023
Large Language Models Encode Clinical Knowledge
Karan Singhal, Shekoofeh Azizi, Tao Tu +27
cs.CLarXiv:2212.13138v12022
Robust Speech Recognition via Large-Scale Weak Supervision
Alec Radford, Jong Wook Kim, Tao Xu +3
eess.AScs.CLcs.LGarXiv:2212.04356v12022
Large Language Models are Zero-Shot Reasoners
Takeshi Kojima, Shixiang Shane Gu, Machel Reid +2
cs.CLcs.AIcs.LGarXiv:2205.11916v42022
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Yuntao Bai, Andy Jones, Kamal Ndousse +28
cs.CLcs.LGarXiv:2204.05862v12022
TruthfulQA: Measuring How Models Mimic Human Falsehoods
Stephanie Lin, Jacob Hilton, Owain Evans
cs.CLcs.AIcs.CYarXiv:2109.07958v22021
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
Suchin Gururangan, Ana Marasović, Swabha Swayamdipta +4
cs.CLcs.LGarXiv:2004.10964v32020
Dense Passage Retrieval for Open-Domain Question Answering
Vladimir Karpukhin, Barlas Oğuz, Sewon Min +5
cs.CLarXiv:2004.04906v32020
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Jacob Devlin, Ming-Wei Chang, Kenton Lee +1
cs.CLarXiv:1810.04805v22018
Summaries:한국어 简体中文 Français
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
Shaojie Bai, J. Zico Kolter, Vladlen Koltun
cs.LGcs.AIcs.CLarXiv:1803.01271v22018
DeepTCM1.0: A Multi-Expert AI Agent for Deciphering Mechanisms of Chinese Herbal Formulae Based on General Large Language Models
Wenxin Duan, Hanwei Wang, Zhongying Peng +4
cs.CLcs.AIarXiv:2608.18103v12026
LLMs for Medical Consultation Are Evaluated Too Late: The Preformulation Gap
Yining Hua, Cyrus Ayubcha, Hongbin Na +4
cs.AIcs.CLcs.CYarXiv:2608.17330v12026
Perturbation-based Regional Interpretability through Subtraction Mapping (PRISM): naming-error dissociations in language models and post-stroke aphasia
Xiang Guan, Roger D. Newman-Norlund, Yong Yang +8
cs.LGcs.CLarXiv:2608.12717v12026

Computation and Language

Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models

LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching

Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion

ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages

Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks

Measuring Epistemic Resilience of LLMs Under Misleading Medical Context

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories

N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization

When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models

WebChallenger: A Reliable and Efficient Generalist Web Agent

Unsupervised Skill Discovery for Agentic Data Analysis

Compress-Distill: Reasoning Trace Compression for Efficient Knowledge Distillation

Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data

The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?

Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill

Trust Region On-Policy Distillation

OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration

Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations

When Gradients Collide: Failure Modes of Multi-Objective Prompt Optimization for LLM Judges

AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild

Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents

Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles

PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents

GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment

Self-Improving CAD Generation Agents with Finite Element Analysis as Feedback

Nexus : An Agentic Framework for Time Series Forecasting

Auditing Agent Harness Safety

Learning Agentic Policy from Action Guidance

Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient?

Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs

RewardHarness: Self-Evolving Agentic Post-Training

A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models

InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search

Teaching Language Models to Think in Code

RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation

Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces

InfoLaw: Information Scaling Laws for Large Language Models with Quality-Weighted Mixture Data and Repetition

FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments

The Power of Scale for Parameter-Efficient Prompt Tuning

RoBERTa: A Robustly Optimized BERT Pretraining Approach

Parameter-Efficient Transfer Learning for NLP

Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning

Diffusion-Pretrained Dense and Contextual Embeddings

FollowUpBot: An LLM-Based Conversational Robot for Automatic Postoperative Follow-up

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Qwen Technical Report

RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

Large Language Models Encode Clinical Knowledge

Robust Speech Recognition via Large-Scale Weak Supervision

Large Language Models are Zero-Shot Reasoners

Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

TruthfulQA: Measuring How Models Mimic Human Falsehoods

Don't Stop Pretraining: Adapt Language Models to Domains and Tasks

Dense Passage Retrieval for Open-Domain Question Answering

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling

DeepTCM1.0: A Multi-Expert AI Agent for Deciphering Mechanisms of Chinese Herbal Formulae Based on General Large Language Models

LLMs for Medical Consultation Are Evaluated Too Late: The Preformulation Gap

Perturbation-based Regional Interpretability through Subtraction Mapping (PRISM): naming-error dissociations in language models and post-stroke aphasia