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)

3,841 to 3,900 of 11,199

MIRIX: Multi-Agent Memory System for LLM-Based Agents
Yu Wang, Xi Chen
cs.CLcs.AIarXiv:2507.07957v12025
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Yaxin Luo, Haobin Jiang, Jialv Zou +11
cs.CVcs.AIcs.CLarXiv:2608.13560v12026
Summaries:한국어
Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs
Jasper Dekoninck, Nikola Jovanović, Tim Gehrunger +4
cs.CLarXiv:2605.00674v22026
Modular Cognitive Architecture Emerges in Large Language Models
Pengrui Han, Jacob Andreas, Evelina Fedorenko +1
cs.AIcs.CLcs.LGarXiv:2608.13567v12026
When More is Less: Understanding Chain-of-Thought Length in LLMs
Yuyang Wu, Yifei Wang, Ziyu Ye +3
cs.AIcs.CLcs.LGarXiv:2502.07266v32025
From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Compound Answer Options
Obed Junias, Maria Leonor Pacheco
cs.CLcs.AIarXiv:2608.12836v12026
AVA-Encoder: Towards Agent-Native Video Representation Learning
Chuyue Li, Jinpeng Yu, Haozhe Wang +7
cs.CVcs.CLarXiv:2608.12313v12026
Separating Syntax from Language: A Mechanistic Account of Translation in Multilingual LLMs
Mikhail Sonkin, Tanja Baeumel, Daniil Gurgurov +2
cs.CLarXiv:2609.01356v12026
Preference Tree Optimization: Enhancing Goal-Oriented Dialogue with Look-Ahead Simulations
Lior Baruch, Moshe Butman, Kfir Bar +1
cs.CLcs.AIarXiv:2608.12062v12026
ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents
Yutao Mou, Pengfei Yang, Zhe Yin +6
cs.CRcs.CLarXiv:2608.11878v12026
AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset
Ivan Moshkov, Darragh Hanley, Ivan Sorokin +5
cs.AIcs.CLcs.LGarXiv:2504.16891v12025
ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning
Bill Yuchen Lin, Ronan Le Bras, Kyle Richardson +4
cs.AIcs.CLcs.LGarXiv:2502.01100v22025
InSight-doc: Agentic Visual Perception for Long-Document Understanding
Kaican Li, Weiyan Xie, Lewei Yao +4
cs.CVcs.CLcs.LGarXiv:2608.10628v12026
DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?
Mizanur Rahman, Mohammed Saidul Islam, Ridwan Mahbub +3
cs.AIcs.CLarXiv:2608.10366v12026
SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring
Yuling Shi, Jinghan Xu, Kelin Fu +12
cs.CLcs.SEarXiv:2608.09802v12026
Evo-Bench: Can Language Models Improve Agent Harness?
Lisheng Huang, Chen Yang, Hao Zhou +6
cs.CLarXiv:2608.09096v22026
Cultivar: A Contrastive and Locale-Oriented Translation Benchmark for Investigating Contamination and Localisation Robustness
Pinzhen Chen, Koel Dutta Chowdhury, Xiaoya Xu +20
cs.CLcs.AIarXiv:2608.09766v12026
LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers
Tao Feng, Fangxu Yu, Haozhen Zhang +9
cs.CLarXiv:2608.06867v12026
DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text
Xianjun Yang, Wei Cheng, Yue Wu +3
cs.CLcs.AIarXiv:2305.17359v22023
RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder
Shitao Xiao, Zheng Liu, Yingxia Shao +1
cs.CLarXiv:2205.12035v22022
General-Reasoner: Advancing LLM Reasoning Across All Domains
Xueguang Ma, Qian Liu, Dongfu Jiang +3
cs.CLarXiv:2505.14652v52025
Delving into LLM-assisted writing in biomedical publications through excess vocabulary
Dmitry Kobak, Rita González-Márquez, Emőke-Ágnes Horvát +1
cs.CLcs.AIcs.CYarXiv:2406.07016v52024
Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist Domains
Ayoub Kirouane, Christos Petrocheilos
eess.AScs.AIcs.CLarXiv:2608.05138v12026
VisualPatchWorld: Code World Models as Latent Structured Representations for Planning
Jiaxin Bai, Jiaxuan Xiong
cs.CLcs.ROarXiv:2607.25236v12026
When Tokenization is Secretly Output Supervision
Tanja Baeumel, Josef van Genabith, Simon Ostermann
cs.CLarXiv:2609.01386v12026
OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
Mengkang Hu, Yuhang Zhou, Wendong Fan +13
cs.AIcs.CLarXiv:2505.23885v22025
ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation
Qingyu Zhang, Qianhao Yuan, Hongyu Lin +5
cs.LGcs.AIcs.CLarXiv:2607.13124v22026
Summaries:한국어
Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models
Yubo Wang, Jiarong Liang, Yuxuan Zhang +5
cs.AIcs.CLarXiv:2607.12463v32026
Classification and Clustering of Arguments with Contextualized Word Embeddings
Nils Reimers, Benjamin Schiller, Tilman Beck +3
cs.CLarXiv:1906.09821v12019
Explore Before Committing: Hypothesis-Guided Search for Deep Research Agents
Ruochen Zhou, Zhengyu Chen, Luan Zhang +3
cs.CLarXiv:2609.01294v12026
LLMPEDIA: Browsing, Verifying, and Comparing the Parametric Encyclopedic Knowledge of LLMs
Muhammed Saeed, Simon Razniewski
cs.CLarXiv:2609.01182v12026
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
Chen Tang, Yizhou Wang, Jianyu Wu +26
cs.CLcs.AIcs.CEarXiv:2607.07708v12026
Summaries:한국어
What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness
Raphaël Sarfati, Pratyush Ranjan Tiwari, Siddharth Boppana +3
cs.CLcs.AIarXiv:2607.08046v12026
Phrase-Localized Language-Contrastive Guidance: Training-Free Localized Accent Control for Code-Switching Text-to-Speech
Che Hyun Lee, Sangkwon Park, Donghun Kang +4
cs.CLcs.SDarXiv:2609.01016v12026
PACE: A Proxy for Agentic Capability Evaluation
Yueqi Song, Lintang Sutawika, Jiarui Liu +8
cs.AIcs.CLarXiv:2607.02032v22026
Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads
Aryo Pradipta Gema, Beatrice Alex, Pasquale Minervini
cs.CLcs.AIcs.LGarXiv:2607.01002v12026
QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents
Sergio Hernández-Gutiérrez, Matteo Merler, Ilze Amanda Auzina +3
cs.LGcs.AIcs.CLarXiv:2606.32034v12026
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs
Gabrielle Kaili-May Liu, Avi Caciularu, Gal Yona +2
cs.CLcs.AIarXiv:2606.32032v12026
JAMER: Project-Level Code Framework Dataset and Benchmark on Professional Game Engines
Jianwen Sun, Chuanhao Li, Zizhen Li +5
cs.SEcs.CLarXiv:2606.19830v22026
Plans Don't Persist: Why Context Management Is Load Bearing for LLM Agents
Aman Mehta, Anupam Datta
cs.AIcs.CLarXiv:2606.22953v12026
Reinforcement Learning from Rich Feedback with Distributional DAgger
Rishabh Agrawal, Jacob Fein-Ashley, Paria Rashidinejad
cs.LGcs.AIcs.CLarXiv:2606.05152v22026
AI Research Agents Narrow Scientific Exploration
Yixuan Tang, Yi Yang
cs.CLarXiv:2605.27905v22026
Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
Mingkai Deng, Jinyu Hou, Lara Sá Neves +4
cs.AIcs.CLcs.LGarXiv:2605.22138v12026
From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
Xitai Jiang, Zihan Tang, Wenze Lin +3
cs.LGcs.AIcs.CLarXiv:2605.22074v12026
FutureSim: Replaying World Events to Evaluate Adaptive Agents
Shashwat Goel, Nikhil Chandak, Arvindh Arun +5
cs.LGcs.AIcs.CLarXiv:2605.15188v12026
The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs
Xin Li, Hao Jiang, Annan Wang +2
cs.LGcs.CLarXiv:2605.08737v12026
Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer
Rafał Powalski, Łukasz Borchmann, Dawid Jurkiewicz +3
cs.CLcs.LGarXiv:2102.09550v32021
Automating Database-Native Function Code Synthesis with LLMs
Wei Zhou, Xuanhe Zhou, Qikang He +4
cs.DBcs.AIcs.CLarXiv:2604.06231v12026
The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning
Yubo Li, Lu Zhang, Tianchong Jiang +2
cs.CLcs.AIarXiv:2603.29025v32026
Omnilingual MT: Machine Translation for 1,600 Languages
Omnilingual MT Team, Belen Alastruey, Niyati Bafna +29
cs.CLarXiv:2603.16309v32026
A Unified Mechanistic Analysis of Knowledge- and Safety-Based Refusals
Yuri Son, Seunghee Kim, Hyuhng Joon Kim +1
cs.CLarXiv:2609.00760v12026
Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails
Shaona Ghosh, Prasoon Varshney, Makesh Narsimhan Sreedhar +4
cs.CLarXiv:2501.09004v12025
MMTEB: Massive Multilingual Text Embedding Benchmark
Kenneth Enevoldsen, Isaac Chung, Imene Kerboua +83
cs.CLcs.AIcs.IRarXiv:2502.13595v42025
Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
Yufeng Du, Minyang Tian, Srikanth Ronanki +7
cs.CLcs.AIarXiv:2510.05381v12025
End-to-End Knowledge-Routed Relational Dialogue System for Automatic Diagnosis
Lin Xu, Qixian Zhou, Ke Gong +3
cs.CLarXiv:1901.10623v22019
Motivation in Large Language Models
Omer Nahum, Asael Sklar, Ariel Goldstein +1
cs.CLcs.CYarXiv:2603.14347v12026
MedMentions: A Large Biomedical Corpus Annotated with UMLS Concepts
Sunil Mohan, Donghui Li
cs.CLcs.LGarXiv:1902.09476v12019
ELEPHANT: Measuring and understanding social sycophancy in LLMs
Myra Cheng, Sunny Yu, Cinoo Lee +3
cs.CLcs.AIcs.CYarXiv:2505.13995v22025
WebDancer: Towards Autonomous Information Seeking Agency
Jialong Wu, Baixuan Li, Runnan Fang +10
cs.CLarXiv:2505.22648v32025
Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions
Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
cs.CVcs.CLarXiv:1811.10652v32018

Computation and Language

MIRIX: Multi-Agent Memory System for LLM-Based Agents

AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design

Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs

Modular Cognitive Architecture Emerges in Large Language Models

When More is Less: Understanding Chain-of-Thought Length in LLMs

From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Compound Answer Options

AVA-Encoder: Towards Agent-Native Video Representation Learning

Separating Syntax from Language: A Mechanistic Account of Translation in Multilingual LLMs

Preference Tree Optimization: Enhancing Goal-Oriented Dialogue with Look-Ahead Simulations

ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents

AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset

ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning

InSight-doc: Agentic Visual Perception for Long-Document Understanding

DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?

SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring

Evo-Bench: Can Language Models Improve Agent Harness?

Cultivar: A Contrastive and Locale-Oriented Translation Benchmark for Investigating Contamination and Localisation Robustness

LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers

DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text

RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder

General-Reasoner: Advancing LLM Reasoning Across All Domains

Delving into LLM-assisted writing in biomedical publications through excess vocabulary

Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist Domains

VisualPatchWorld: Code World Models as Latent Structured Representations for Planning

When Tokenization is Secretly Output Supervision

OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

Classification and Clustering of Arguments with Contextualized Word Embeddings

Explore Before Committing: Hypothesis-Guided Search for Deep Research Agents

LLMPEDIA: Browsing, Verifying, and Comparing the Parametric Encyclopedic Knowledge of LLMs

Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness

Phrase-Localized Language-Contrastive Guidance: Training-Free Localized Accent Control for Code-Switching Text-to-Speech

PACE: A Proxy for Agentic Capability Evaluation

Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads

QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents

Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs

JAMER: Project-Level Code Framework Dataset and Benchmark on Professional Game Engines

Plans Don't Persist: Why Context Management Is Load Bearing for LLM Agents

Reinforcement Learning from Rich Feedback with Distributional DAgger

AI Research Agents Narrow Scientific Exploration

Efficient Agentic Reasoning Through Self-Regulated Simulative Planning

From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning

FutureSim: Replaying World Events to Evaluate Adaptive Agents

The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs

Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer

Automating Database-Native Function Code Synthesis with LLMs

The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning

Omnilingual MT: Machine Translation for 1,600 Languages

A Unified Mechanistic Analysis of Knowledge- and Safety-Based Refusals

Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails

MMTEB: Massive Multilingual Text Embedding Benchmark

Context Length Alone Hurts LLM Performance Despite Perfect Retrieval

End-to-End Knowledge-Routed Relational Dialogue System for Automatic Diagnosis

Motivation in Large Language Models

MedMentions: A Large Biomedical Corpus Annotated with UMLS Concepts

ELEPHANT: Measuring and understanding social sycophancy in LLMs

WebDancer: Towards Autonomous Information Seeking Agency

Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions