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)

4,201 to 4,260 of 11,247

ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction
Yongqi Tong, Tan Li Hui Faith, Choy Zhen Wen Marcus +5
cs.AIcs.CLarXiv:2608.13622v12026
OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
Bobo Li, Hao Fei, Tianjie Ju +2
cs.AIcs.CLarXiv:2608.13558v12026
Summaries:한국어
LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure
Fanfei Li, Jana Zeller, Manuel Prada-Corral +4
cs.CLcs.AIcs.LGarXiv:2608.13545v12026
LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation
Dongfang Li, Zixuan Liu, Junmai Wang +5
cs.CLarXiv:2608.12990v12026
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
Mengru Wang, Junfeng Fang, Shuofei Qiao +16
cs.AIcs.CLcs.HCarXiv:2608.12036v12026
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
Cheng Qian, Wenting Zhao, Liangwei Yang +6
cs.LGcs.AIcs.CLarXiv:2608.12307v12026
Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation
Chris Han, Pengzhi Gao, Pei Fu +1
cs.CLcs.AIarXiv:2608.10812v22026
Claim-Level Reliability Assessment for Efficient Test-Time Reasoning
Sen Xu, Wei Wang, Shixi Liu +5
cs.AIcs.CLarXiv:2608.11994v12026
Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill
Zhuoyang Qian, Biao Wu, Yiran Wang +6
cs.CLarXiv:2608.11924v12026
Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing
Tianci Liu, Zihan Dong, Tianchun Li +8
cs.CLcs.AIcs.LGarXiv:2608.11660v12026
Ex-Omni-2D: Expressive Omni-Modal Dialogue Models with Native Visual Presence
Haoyu Zhang, Zhipeng Li, Xiaoying Tang +2
cs.AIcs.CLcs.CVarXiv:2608.10720v12026
DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation
Zhuchenyang Liu, Ziyi Wang, Yao Zhang +1
cs.IRcs.CLcs.CVarXiv:2608.10636v12026
Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference
Burc Gokden
cs.LGcs.CLarXiv:2608.10288v12026
Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design
Qing Zong, Jiayu Liu, Junhao Shen +9
cs.CLarXiv:2608.10299v12026
Multimodal Model Diffing for Feature Discovery and Control
Hunar Batra, Lachin Naghashyar, Ashkan Khakzar +4
cs.CVcs.AIcs.CLarXiv:2608.09928v12026
Simplex Relaxation for Discrete Diffusion
Jinya Sakurai, Patrick Pynadath, Satoshi Hayakawa +4
cs.CLarXiv:2608.10615v12026
Decoding-Level Taboo: A Diagnostic Stress Test for LLM Robustness
Tadanobu Chuyo Kamijo, Ori Rottenstreich, Javier Conde +2
cs.CLarXiv:2608.09900v22026
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
Mind Lab, :, Vin Bo +74
cs.LGcs.CLarXiv:2608.09819v12026
How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer Review
Ming Li, Chenguang Wang, Xirui Li +5
cs.CLcs.AIarXiv:2608.08975v12026
Summaries:한국어
Parameter Exploration for RLVR via Variational Learning
Vatsal Venkatkrishna, Nico Daheim, Iryna Gurevych
cs.LGcs.AIcs.CLarXiv:2608.09805v12026
Reading Cognition as Decisions Unfold in Words: A Factorized Inverse Decision Model
Jiawen Kang, Dongrui Han, Xixin Wu +1
cs.CLq-bio.NCarXiv:2608.09222v12026
Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization
Hyangsuk Min, Hwanjun Song
cs.CLcs.AIarXiv:2608.09043v12026
Scaling Inherently Interpretable Language Models
Guide Labs Team, Andreas Madsen, Aya Abdelsalam Ismail +7
cs.CLcs.AIarXiv:2608.07594v12026
Summaries:한국어
VectraYX-Vision-1B: A Sub-2B Spanish/LATAM Cybersecurity Vision-Language Model with Structured Visual Reasoning and Native Tool Use
Juan S. Santillana
cs.CLarXiv:2608.08477v12026
Vision-Language Grounding as Bidirectional Concept Correspondence
Jieyu Zhang, Ziqi Gao, Luke Zettlemoyer +1
cs.CVcs.AIcs.CLarXiv:2608.07886v12026
CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks
Fanzhe Meng, Guoxin Chen, Jiale Zhao +6
cs.LGcs.CLarXiv:2608.06352v12026
Kimi K3: Open Frontier Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +399
cs.CLcs.LGarXiv:2607.24653v22026
SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries
Xingyu Tan, Xiaoyang Wang, Qing Liu +4
cs.CLcs.AIarXiv:2608.05604v12026
Summaries:한국어
Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning
Yinghui He, Ling Yang, Jiarui Liu +6
cs.CLcs.LGarXiv:2608.05139v12026
PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents
Shuhan Xue, Zixin Ding, Yichen Shen +6
cs.CLarXiv:2608.04003v12026
RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States
Yi Yang, Zhennan Chen, Yihong Zhuang +5
cs.LGcs.CLarXiv:2608.02508v32026
DiffusionGemma Technical Report
DiffusionGemma Team, Adrien Ali Taïga, James Assiene +41
cs.CLcs.AIarXiv:2608.00146v12026
Verbalizable Representations Form a Global Workspace in Language Models
Wes Gurnee, Nicholas Sofroniew, Adam Pearce +13
cs.CLcs.AIcs.LGarXiv:2607.15495v12026
Summaries:한국어
Voice Memory for Agentic Speech Recognition
Chao-Han Huck Yang, Zih-Ching Chen, Piotr Zelasko +3
cs.CLcs.AIcs.SDarXiv:2607.26410v12026
Loop the Loopies!
Zitian Gao, Yilong Chen, Yihao Xiao +4
cs.CLcs.AIarXiv:2607.16051v22026
R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
Huatong Song, Jinhao Jiang, Yingqian Min +5
cs.AIcs.CLcs.IRarXiv:2503.05592v22025
Self-Improvements in Modern Agentic Systems: A Survey
Zhe Ren, Yimeng Chen, Dandan Guo +9
cs.AIcs.CLcs.LGarXiv:2607.13104v12026
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Jinyang Wu, Shuo Yang, Zhengxi Lu +8
cs.CLarXiv:2607.14777v12026
Summaries:한국어
xHC: Expanded Hyper-Connections
Xiangdong Zhang, Xiaohan Qin, Sunan Zou +10
cs.LGcs.CLarXiv:2607.14530v12026
Summaries:한국어
Tracing Agentic Failure from the Flow of Success
Samuel Yeh, Yiwen Zhu, Shaleen Deep +1
cs.AIcs.CLarXiv:2607.12747v12026
DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment
Xinyu Geng, Xuanhua He, Sixiang Chen +7
cs.CLarXiv:2607.07820v12026
Summaries:한국어
EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments
Deyao Zhu, Xin Zhou, Shengling Qin +44
cs.CLcs.LGarXiv:2607.05155v12026
TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training
Yuhang Zhou, Kai Zheng, Haoling Li +3
cs.AIcs.CLarXiv:2607.05804v12026
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
Xin Cheng, Xingkai Yu, Chenze Shao +30
cs.AIcs.CLarXiv:2607.05147v12026
Summaries:한국어
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
Xiang Hu, Xinyu Wei, Hao Gu +10
cs.CLcs.AIarXiv:2607.02980v12026
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
Zhilin Wang, Han Song, Runzhe Zhan +13
cs.AIcs.CLarXiv:2607.02440v12026
Denser $\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training
Meng Wang, Haohan Zhao, Wenzhuo Liu +7
cs.LGcs.CLarXiv:2607.01763v12026
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
Xiangchen Cheng, Yunwei Jiang, Jianwen Sun +7
cs.AIcs.CLarXiv:2607.02255v12026
MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering
Dang Quang Thien Tran, Quang V. Dang, Vinamra Tyagi +7
cs.CLcs.AIcs.CVarXiv:2607.01420v32026
AutoTrainess: Teaching Language Models to Improve Language Models Autonomously
Zhaojian Yu, Penghao Yin, Shuzheng Gao +3
cs.CLarXiv:2606.31551v12026
BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding
Hao Zhang, Yiming Hu, Yong Wang +3
cs.CLarXiv:2606.31315v12026
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
Lei Bai, Zongsheng Cao, Yang Chen +50
cs.CLarXiv:2606.30616v22026
Training Language Models to Reason Efficiently
Daman Arora, Andrea Zanette
cs.LGcs.CLarXiv:2502.04463v42025
Morphing into Hybrid Attention Models
Disen Lan, Jianbin Zheng, Yuxi Ren +5
cs.CLarXiv:2606.30562v12026
Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning
Sangmook Lee, Minbeom Kim, Jeonghye Kim +3
cs.CLarXiv:2606.29985v12026
Cross-lingual Annotation Projection for Semantic Roles
Sebastian Pado, Mirella Lapata
cs.CLarXiv:1401.5694v12014
Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs
Fahd Seddik, Fatemeh Fard
cs.CLcs.LGarXiv:2606.27378v12026
Summaries:한국어
Multi-Block Diffusion Language Models
Yijie Jin, Jiajun Xu, Yuxuan Liu +8
cs.LGcs.CLarXiv:2606.29215v22026
Summaries:한국어
Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement
Igor Itkin
cs.MAcs.CLcs.LGarXiv:2606.27409v12026
OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning
Shuo Yang, Jinyang Wu, Zhengxi Lu +8
cs.CLarXiv:2606.26790v12026

Computation and Language

ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction

OmniScientist: An Omni-Modal Omni-Discipline AI Scientist

LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure

LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation

Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence

AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses

Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation

Claim-Level Reliability Assessment for Efficient Test-Time Reasoning

Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill

Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing

Ex-Omni-2D: Expressive Omni-Modal Dialogue Models with Native Visual Presence

DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation

Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference

Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design

Multimodal Model Diffing for Feature Discovery and Control

Simplex Relaxation for Discrete Diffusion

Decoding-Level Taboo: A Diagnostic Stress Test for LLM Robustness

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer Review

Parameter Exploration for RLVR via Variational Learning

Reading Cognition as Decisions Unfold in Words: A Factorized Inverse Decision Model

Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization

Scaling Inherently Interpretable Language Models

VectraYX-Vision-1B: A Sub-2B Spanish/LATAM Cybersecurity Vision-Language Model with Structured Visual Reasoning and Native Tool Use

Vision-Language Grounding as Bidirectional Concept Correspondence

CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks

Kimi K3: Open Frontier Intelligence

SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents

RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States

DiffusionGemma Technical Report

Verbalizable Representations Form a Global Workspace in Language Models

Voice Memory for Agentic Speech Recognition

Loop the Loopies!

R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning

Self-Improvements in Modern Agentic Systems: A Survey

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

xHC: Expanded Hyper-Connections

Tracing Agentic Failure from the Flow of Success

DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment

EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments

TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training

DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments

Denser $\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training

AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents

MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering

AutoTrainess: Teaching Language Models to Improve Language Models Autonomously

BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

Training Language Models to Reason Efficiently

Morphing into Hybrid Attention Models

Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning

Cross-lingual Annotation Projection for Semantic Roles

Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs

Multi-Block Diffusion Language Models

Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement

OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning