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)

4,261 to 4,320 of 11,252

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
The Verification Horizon: No Silver Bullet for Coding Agent Rewards
Binghai Wang, Chenlong Zhang, Dayiheng Liu +10
cs.AIcs.CLarXiv:2606.26300v22026
Summaries:한국어
Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It
Yupu Hao, Zhuoran Jin, Huanxuan Liao +2
cs.CLcs.LGarXiv:2606.26027v12026
Autodata: An agentic data scientist to create high quality synthetic data
Ilia Kulikov, Chenxi Whitehouse, Tianhao Wu +12
cs.AIcs.CLcs.LGarXiv:2606.25996v32026
Summaries:한국어
Autodata: An agentic data scientist to create high quality synthetic data
Ilia Kulikov, Chenxi Whitehouse, Tianhao Wu +12
cs.AIcs.CLcs.LGarXiv:2606.25996v22026
Summaries:한국어
AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents
Zheyuan Zhang, Zehao Wen, Alvin Zhang +4
cs.CLarXiv:2606.24893v12026
Tmax: A simple recipe for terminal agents
Hamish Ivison, Junjie Oscar Yin, Rulin Shao +3
cs.CLarXiv:2606.23321v12026
Summaries:한국어
PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems
Jiayu Liu, Qihan Lin, Cheng Qian +8
cs.AIcs.CLarXiv:2606.22388v12026
KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking
Xinping Zhao, Jiaxin Xu, Ziqi Dai +7
cs.CLarXiv:2606.22807v22026
JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting
Lanxiang Hu, Zhaoxiang Feng, Yulun Wu +9
cs.CLarXiv:2606.18394v32026
RepSelect: Robust LLM Unlearning via Representation Selectivity
Filip Sondej, Yushi Yang, Adam Mahdi
cs.CLarXiv:2606.17168v22026
Understanding the Behaviors of Environment-aware Information Retrieval
Ruifeng Yuan, Chaohao Yuan, David Dai +4
cs.CLcs.IRarXiv:2606.16817v12026
Rethinking the Role of Efficient Attention in Hybrid Architectures
Ziqing Qiao, Yinuo Xu, Chaojun Xiao +6
cs.CLcs.LGarXiv:2606.15378v12026
Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffusion Language Models
Heecheol Yun, Joonhyung Park, Joowon Kim +1
cs.CLcs.AIarXiv:2606.16281v12026
Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
Sikuan Yan, Xiufeng Yang, Zuchao Huang +10
cs.CLcs.MAarXiv:2508.19828v52025
AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
Zhengxuan Wu, Aryaman Arora, Atticus Geiger +5
cs.CLcs.AIcs.LGarXiv:2501.17148v32025
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference
Wenbo Pan, Shujie Liu, Chin-Yew Lin +5
cs.AIcs.CLcs.LGarXiv:2606.05922v22026
Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions
Zhenting Qi, Huangyuan Su, Ao Qu +13
cs.CLcs.AIcs.MAarXiv:2606.02859v12026
Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning
Atoosa Chegini, Soheil Feizi
cs.CLcs.AIcs.LGarXiv:2606.01682v12026
From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors
Jiejun Tan, Zhicheng Dou, Xinyu Yang +4
cs.CRcs.AIcs.CLarXiv:2605.31042v12026
Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL
Jiaxuan Gao, Wei Fu, Minyang Xie +5
cs.CLcs.AIarXiv:2508.07976v42025
Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation
Zhifei Xie, Kaiyu Pang, Haobin Zhang +4
cs.SDcs.AIcs.CLarXiv:2605.19833v12026
On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation
Chaojun Wang, Rico Sennrich
cs.CLarXiv:2005.03642v12020
Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
Jiahang Lin, Shichun Liu, Chengjun Pan +8
cs.CLcs.SEarXiv:2604.25850v42026
Text2Action: Generative Adversarial Synthesis from Language to Action
Hyemin Ahn, Timothy Ha, Yunho Choi +2
cs.LGcs.CLcs.ROarXiv:1710.05298v22017
A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
Hamid Kazemi, Atoosa Chegini, Maria Safi
cs.CLcs.AIcs.LGarXiv:2605.08513v12026
Geometric Factual Recall in Transformers
Shauli Ravfogel, Gilad Yehudai, Joan Bruna +1
cs.CLarXiv:2605.12426v12026
Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR
Jeonghye Kim, Jiwon Jeon, Dongsheng Li +1
cs.LGcs.CLarXiv:2605.10781v12026
AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
Boxuan Zhang, Jianing Zhu, Zeru Shi +2
cs.CLcs.AIcs.MAarXiv:2605.08715v22026
AdaPreLoRA: Adafactor Preconditioned Low-Rank Adaptation
Ziyun Liu, Fengmiao Bian, Jian-Feng Cai
cs.LGcs.AIcs.CLarXiv:2605.08734v12026
IntentGrasp: A Comprehensive Benchmark for Intent Understanding
Yuwei Yin, Chuyuan Li, Giuseppe Carenini
cs.CLcs.AIcs.LGarXiv:2605.06832v12026
MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning
Ionut-Vlad Modoranu, Mher Safaryan, Dan Alistarh
cs.CLcs.AIcs.LGarXiv:2605.07850v12026
Sessa: Selective State Space Attention
Liubomyr Horbatko
cs.LGcs.AIcs.CLarXiv:2604.18580v22026
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Yaxuan Li, Yuxin Zuo, Bingxiang He +8
cs.LGcs.AIcs.CLarXiv:2604.13016v22026
LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling
Yuxin Chen, Chumeng Liang, Hangke Sui +4
cs.CLcs.LGarXiv:2604.11748v32026
How Far Can Unsupervised RLVR Scale LLM Training?
Bingxiang He, Yuxin Zuo, Zeyuan Liu +18
cs.LGcs.CLarXiv:2603.08660v12026
Initialisation Determines the Basin: Efficient Codebook Optimisation for Extreme LLM Quantization
Ian W. Kennedy, Nafise Sadat Moosavi
cs.CLcs.LGarXiv:2604.08118v12026
Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States
Yurun Yuan, Tengyang Xie
cs.LGcs.AIcs.CLarXiv:2603.19987v12026
Efficient Reasoning with Balanced Thinking
Yulin Li, Tengyao Tu, Li Ding +5
cs.AIcs.CLcs.LGarXiv:2603.12372v32026
Flow Map Language Models: One-step Language Modeling via Continuous Denoising
Chanhyuk Lee, Jaehoon Yoo, Manan Agarwal +6
cs.CLcs.AIarXiv:2602.16813v32026
Prescriptive Scaling Reveals the Evolution of Language Model Capabilities
Hanlin Zhang, Jikai Jin, Vasilis Syrgkanis +1
cs.LGcs.AIcs.CLarXiv:2602.15327v22026
Summaries:한국어
Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs
Yining Hong, Huang Huang, Manling Li +4
cs.LGcs.AIcs.CLarXiv:2602.21198v32026
Spilled Energy in Large Language Models
Adrian Robert Minut, Hazem Dewidar, Iacopo Masi
cs.AIcs.CLarXiv:2602.18671v42026
Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
Yu-Ang Lee, Ching-Yun Ko, Pin-Yu Chen +1
cs.LGcs.AIcs.CLarXiv:2602.04998v22026
Demystifying the Slash Pattern in Attention: The Role of RoPE
Yuan Cheng, Fengzhuo Zhang, Yunlong Hou +5
cs.LGcs.AIcs.CLarXiv:2601.08297v22026
UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities
Woongyeong Yeo, Kangsan Kim, Soyeong Jeong +2
cs.CLcs.AIcs.CVarXiv:2504.20734v52025
Summaries:한국어
FP8-RL: A Practical and Stable Low-Precision Stack for LLM Reinforcement Learning
Zhaopeng Qiu, Shuang Yu, Jingqi Zhang +4
cs.LGcs.CLarXiv:2601.18150v22026
Agentic Confidence Calibration
Jiaxin Zhang, Caiming Xiong, Chien-Sheng Wu
cs.AIcs.CLarXiv:2601.15778v12026
For-Value: Efficient Forward-Only Data Valuation for finetuning LLMs and VLMs
Wenlong Deng, Qi Zeng, Jiaming Zhang +5
cs.CLarXiv:2508.10180v32025
Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL
Zijin Hong, Zheng Yuan, Qinggang Zhang +4
cs.CLcs.AIcs.DBarXiv:2406.08426v82024
BLINK: Multimodal Large Language Models Can See but Not Perceive
Xingyu Fu, Yushi Hu, Bangzheng Li +7
cs.CVcs.AIcs.CLarXiv:2404.12390v42024
Llama 2: Open Foundation and Fine-Tuned Chat Models
Hugo Touvron, Louis Martin, Kevin Stone +65
cs.CLcs.AIarXiv:2307.09288v22023
Summaries:한국어
Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
Rishabh Bhardwaj, Soujanya Poria
cs.CLarXiv:2308.09662v32023
IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages
Jay Gala, Pranjal A. Chitale, Raghavan AK +11
cs.CLarXiv:2305.16307v32023
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Rafael Rafailov, Archit Sharma, Eric Mitchell +3
cs.LGcs.AIcs.CLarXiv:2305.18290v32023
Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
Zhiqing Sun, Yikang Shen, Qinhong Zhou +5
cs.LGcs.AIcs.CLarXiv:2305.03047v22023
Summaries:한국어

Computation and Language

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

The Verification Horizon: No Silver Bullet for Coding Agent Rewards

Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It

Autodata: An agentic data scientist to create high quality synthetic data

Autodata: An agentic data scientist to create high quality synthetic data

AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents

Tmax: A simple recipe for terminal agents

PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems

KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking

JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting

RepSelect: Robust LLM Unlearning via Representation Selectivity

Understanding the Behaviors of Environment-aware Information Retrieval

Rethinking the Role of Efficient Attention in Hybrid Architectures

Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffusion Language Models

Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning

AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference

Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions

Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning

From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors

Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL

Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation

On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation

Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses

Text2Action: Generative Adversarial Synthesis from Language to Action

A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models

Geometric Factual Recall in Transformers

Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR

AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems

AdaPreLoRA: Adafactor Preconditioned Low-Rank Adaptation

IntentGrasp: A Comprehensive Benchmark for Intent Understanding

MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning

Sessa: Selective State Space Attention

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling

How Far Can Unsupervised RLVR Scale LLM Training?

Initialisation Determines the Basin: Efficient Codebook Optimisation for Extreme LLM Quantization

Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States

Efficient Reasoning with Balanced Thinking

Flow Map Language Models: One-step Language Modeling via Continuous Denoising

Prescriptive Scaling Reveals the Evolution of Language Model Capabilities

Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs

Spilled Energy in Large Language Models

Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning

Demystifying the Slash Pattern in Attention: The Role of RoPE

UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities

FP8-RL: A Practical and Stable Low-Precision Stack for LLM Reinforcement Learning

Agentic Confidence Calibration

For-Value: Efficient Forward-Only Data Valuation for finetuning LLMs and VLMs

Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL

BLINK: Multimodal Large Language Models Can See but Not Perceive

Llama 2: Open Foundation and Fine-Tuned Chat Models

Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment

IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages

Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision