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)

11,101 to 11,160 of 11,238

Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability
Sizhe Zhou, Sheldon Yu, Hui Wei +8
cs.CLcs.AIarXiv:2607.26637v12026
SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch
Yihao Chen, Shi Chang, Feng Lin +4
cs.SEcs.CLarXiv:2607.27167v12026
Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing
Laurin Wagner, Mario Zusag, Bernhard Thallinger
cs.CLarXiv:2607.18934v12026
Memory for Large Language Models
Sining Zhoubian, Dan Zhang, Evgeny Kharlamov +1
cs.CLarXiv:2607.25380v12026
Novel Claim or Déjà Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-Checking
Haorui He, Xinwen Chen, Dacheng Wen +3
cs.CLcs.AIcs.MMarXiv:2607.23514v12026
Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning
Junyao Yang, Yucheng Shi, Zongxia Li +6
cs.LGcs.CLarXiv:2607.18722v32026
Shieldstral
Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli +273
cs.CLcs.CVarXiv:2607.25857v22026
MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis
Yihao Chen, Shi Chang, Khaled Chawa +4
cs.SEcs.CLcs.LGarXiv:2607.27146v12026
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents
Kunlun Zhu, Xuyan Ye, Zhiguang Han +9
cs.AIcs.CLarXiv:2607.18754v12026
Envs-FORGE: Frontier-Optimized Reward-Grounded Environment Synthesis for Agent RL
Xiaojun Wu, Cehao Yang, Honghao Liu +7
cs.CLarXiv:2608.14312v12026
You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model
Ziyang Luo, Zhongyao Chu, Xinjie He +4
cs.CLcs.LGarXiv:2608.14465v12026
Measuring Fairness in Large Audio Language Models via Semantic-Aware Bias Estimation
Zhe Liu
cs.CLcs.AIcs.SDarXiv:2608.13624v12026
Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking
Kailin Jiang, Lei Liu, Jian Xi +7
cs.CLarXiv:2607.19747v22026
OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding
Jingbo Zhou, Yusai Zhao, Qi Bao +12
cs.AIcs.CLcs.HCarXiv:2607.27155v12026
CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition
Lai Wei, Chengqi Li, Jiapeng Li +3
cs.CVcs.AIcs.CLarXiv:2607.25294v12026
Progress Reward Modeling for Robotic Learning: A Comprehensive Survey
Jianshu Zhang, Keliang Wu, Haoran Lu +8
cs.ROcs.CLarXiv:2607.21655v12026
Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning
Jian Hu, Huiying Li, Hao Zhang +8
cs.LGcs.CLcs.DCarXiv:2607.21653v12026
Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory
Ruizhe Li, Mingxuan Du, Benfeng Xu +1
cs.CLarXiv:2607.24368v12026
K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs
Hao Liang, Qihan Lin, Zhaoyang Han +5
cs.CLarXiv:2605.09635v32026
BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms
Pengyu Wang, Benfeng Xu, Shaohan Wang +5
cs.CLarXiv:2607.26497v32026
Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation
Yuhang Zhu, Mingxuan Du, Benfeng Xu +3
cs.CLcs.AIarXiv:2607.27816v22026
EMBL AI Librarian: Life-Sciences Knowledge Layer for AI Agents
Luigi Sigillo, Matteo Silvestri, Francesco Tabaro +9
cs.CLcs.AIcs.IRarXiv:2607.28229v12026
GigaChat Audio: Time-aware Large Audio Language Model
Aleksandr Kutsakov, Mariia Sadovina, Georgii Gospodinov +4
eess.AScs.CLarXiv:2607.10387v12026
GigaAM Multilingual: Foundation Model for Underrepresented Languages
Andrei Kuzmenko, Alexandr Maximenko, Aleksandr Kutsakov +5
eess.AScs.CLarXiv:2607.10371v12026
Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation
Alexi Gladstone, Heng Ji, Yilun Du
cs.LGcs.AIcs.CLarXiv:2607.27372v12026
UEmbed: Unified Sparse and Dense Multimodal Embeddings
Tingyu Song, Mingxin Li, Yanzhao Zhang +5
cs.CVcs.AIcs.CLarXiv:2608.02583v12026
Pass the Baton: Trajectory-Relayed On-Policy Distillation
Haolei Xu, Xiaowen Xu, Haiwen Hong +5
cs.CLcs.AIarXiv:2607.26057v12026
AISPA: User-Centric System Prompt Auditing for Large Language Model Applications
Xiangning Lin, Shenzhe Zhu, Shu Yang +23
cs.AIcs.CLcs.CYarXiv:2607.28617v22026
The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads
Yushi Sun, Yanjie Zhang, Rui Sheng
cs.CLarXiv:2608.04570v12026
A New Role for Relevance: Guiding Corpus Interaction in Agentic Search
Jiangnan Li, Yuqing Li, Mo Yu +2
cs.CLarXiv:2607.24223v22026
When Top-K Misses the Decision: Tool-Call Drift in Multi-Teacher On-Policy Distillation
Jiabin Shen, Guang Chen, Chengjun Mao
cs.CLcs.LGarXiv:2607.07050v42026
Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making
Amirhosein Ghasemabadi, Ruichen Chen, Bahador Rashidi +1
cs.CLarXiv:2607.14277v12026
Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model
Senqiao Yang, Kaichen Zhang, Zhaoyang Jia +20
cs.CVcs.CLarXiv:2607.24904v12026
AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis
Bing Yan, Gregory Wolfe, Stefano Martiniani +1
cs.CLcs.AIcs.IRarXiv:2607.28618v12026
An Exam for Active Observers
Jiarui Zhang, Muzi Tao, Shangshang Wang +3
cs.CVcs.AIcs.CLarXiv:2607.16165v12026
Metis: Memory Foundation Model
Zeyu Zhang, Ziliang Guo, Yihang Sun +14
cs.CLcs.LGarXiv:2607.26760v22026
Can Multimodal Large Language Models Understand OCT?
Baochen Fu, Wenzhi Deng, Baihao Jin +5
cs.CVcs.CLarXiv:2607.16609v12026
Multi-Turn On-Policy Distillation with Prefix Replay
Baohao Liao, Hanze Dong, Christof Monz +3
cs.LGcs.AIcs.CLarXiv:2607.04763v32026
Agentic Transaction: Towards ACID-Compliant Agent Systems
Zhaoyan Sun, Xiaoxiao Wang, Guoliang Li
cs.DBcs.AIcs.CLarXiv:2608.13900v12026
Split the Labor: Separating Evidence Interpretation from Decision Aggregation
Zhelun Wu
cs.AIcs.CLcs.LGarXiv:2608.14509v12026
LLMs Don't Pay for the Jump
Paras Balani, Subhrakanta Panda
cs.AIcs.CLarXiv:2608.14397v12026
Never the Number: Structural Abstention for AI Systems Whose Answers Are Consumed as Fact
Zhelun, Wu
cs.AIcs.CLcs.DBarXiv:2608.13926v12026
Reading Between The Lines: Modeling and Evaluating Behavioral Realism in Legal Simulation
Divya Vetticaden, Arya Gupta, Julian Nyarko +1
cs.CYcs.AIcs.CLarXiv:2608.13712v12026
Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements
Xinke Tong, Xuanming Zhang, Tianyi Tang +10
cs.CLarXiv:2607.28661v12026
When Activation Oracles Learn Not to Read: Concept-Specific Blind Spots in Fine-Tuned Oracles
Tobias Bersia, Tatiana Gaintseva
cs.CLcs.AIarXiv:2607.23379v12026
BM25-Augmented Many-Shot Translation for Low-Resource North-Eastern Indian Languages
Aashish Dhawan, Christopher Driggers-Ellis, Dzmitry Kasinets +2
cs.CLarXiv:2608.13722v12026
Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding
Ming Wang, Yuqing Zhang, Tingna Xie +5
cs.AIcs.CLcs.MMarXiv:2608.06501v12026
Zero-Mem: Zero-Token Memory Operations for LLM Agents
Yilin Xiao, Zhehan Zhu, Yujing Zhang +8
cs.CLarXiv:2607.29377v12026
DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialogues
Takyoung Kim, Kang-wook Kim, Sang Hoon Woo +3
cs.CLarXiv:2607.26178v12026
SIGNPOST-Bench: Benchmarking Text-Vision Conflict Resolution in Multimodal Large Language Models
Sirun Li, Minghao Liu, Ling Dai +4
cs.CVcs.CLarXiv:2608.04244v12026
When Lexical Change Misleads: Rethinking Dynamic Topic Model Evaluation with Traditional and LLM-Based Metrics
Charu Karakkaparambil James
cs.CLarXiv:2608.13835v12026
RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems
Haoran Ling, Yuecheng Li, Zeyu Song +5
cs.IRcs.AIcs.CLarXiv:2607.29241v12026
Geometric Filtering of LLM-Generated Samples for Few-Shot Text Classification
Benjamín Schindler, Gonzalo A. Ruz
cs.LGcs.CLarXiv:2608.13866v12026
Leading-Silence Augmentation and Multi-Stage Synthetic Supervision for the Second MLC-SLM Challenge
Kexin Shi, Renhe Sun, Yuge Huang +4
cs.CLarXiv:2608.14150v12026
AnchorBench: A Multi-Pathway Benchmark for the Anchoring Effect in LLMs
Yiderigun Borjigin, Alexander Hermann, Christian Cyron +1
cs.AIcs.CLarXiv:2608.14320v12026
Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance
Zhuowen Han, Jinwei Xiao, Zhengxi Lu +9
cs.CLarXiv:2608.00782v12026
Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning
Xinyan Guan, Jiali Zeng, Chunlei Xin +5
cs.CLarXiv:2607.29211v12026
RestoreKV: Recovering Full-Cache Behavior Under Aggressive Query-Agnostic KV Cache Eviction
Changwoo Baek, Seungjun Shin, Kyeongbo Kong
cs.CLcs.LGarXiv:2608.01247v12026
When Attention Goes Blind: Numerical Failure in ALiBi Positional Encodings
Christopher Schröder, Lukas Gienapp, Ferdinand Schlatt +2
cs.CLarXiv:2608.03994v12026
Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination
Ruijie Hou, Yueyang Jiao, Zhao Wang +1
cs.CLcs.AIarXiv:2608.07341v12026

Computation and Language

Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability

SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing

Memory for Large Language Models

Novel Claim or Déjà Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-Checking

Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning

Shieldstral

MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis

AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents

Envs-FORGE: Frontier-Optimized Reward-Grounded Environment Synthesis for Agent RL

You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model

Measuring Fairness in Large Audio Language Models via Semantic-Aware Bias Estimation

Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking

OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding

CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition

Progress Reward Modeling for Robotic Learning: A Comprehensive Survey

Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning

Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory

K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs

BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms

Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation

EMBL AI Librarian: Life-Sciences Knowledge Layer for AI Agents

GigaChat Audio: Time-aware Large Audio Language Model

GigaAM Multilingual: Foundation Model for Underrepresented Languages

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation

UEmbed: Unified Sparse and Dense Multimodal Embeddings

Pass the Baton: Trajectory-Relayed On-Policy Distillation

AISPA: User-Centric System Prompt Auditing for Large Language Model Applications

The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads

A New Role for Relevance: Guiding Corpus Interaction in Agentic Search

When Top-K Misses the Decision: Tool-Call Drift in Multi-Teacher On-Policy Distillation

Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis

An Exam for Active Observers

Metis: Memory Foundation Model

Can Multimodal Large Language Models Understand OCT?

Multi-Turn On-Policy Distillation with Prefix Replay

Agentic Transaction: Towards ACID-Compliant Agent Systems

Split the Labor: Separating Evidence Interpretation from Decision Aggregation

LLMs Don't Pay for the Jump

Never the Number: Structural Abstention for AI Systems Whose Answers Are Consumed as Fact

Reading Between The Lines: Modeling and Evaluating Behavioral Realism in Legal Simulation

Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements

When Activation Oracles Learn Not to Read: Concept-Specific Blind Spots in Fine-Tuned Oracles

BM25-Augmented Many-Shot Translation for Low-Resource North-Eastern Indian Languages

Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding

Zero-Mem: Zero-Token Memory Operations for LLM Agents

DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialogues

SIGNPOST-Bench: Benchmarking Text-Vision Conflict Resolution in Multimodal Large Language Models

When Lexical Change Misleads: Rethinking Dynamic Topic Model Evaluation with Traditional and LLM-Based Metrics

RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems

Geometric Filtering of LLM-Generated Samples for Few-Shot Text Classification

Leading-Silence Augmentation and Multi-Stage Synthetic Supervision for the Second MLC-SLM Challenge

AnchorBench: A Multi-Pathway Benchmark for the Anchoring Effect in LLMs

Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance

Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning

RestoreKV: Recovering Full-Cache Behavior Under Aggressive Query-Agnostic KV Cache Eviction

When Attention Goes Blind: Numerical Failure in ALiBi Positional Encodings

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination