AI & Machine Learning · Computer Science & AI
Computation & Language / NLP
The newest papers in Computation & Language / NLP that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 17 September 2026 to 5 November 2026: 5,000 arXiv preprints.
Get the few papers worth your time in Computation & Language / NLP every morning.
Follow Computation & Language / NLP and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 73
CAPSafe: A Benchmark for Contextual Action and Plan Safety Reasoning in Embodied Agents
Reasoning about safety is essential for embodied agents powered by large language models (LLMs).When Copying Is Hard: Copy-Constrained Decoding for Exact Span Reproduction
Precisely reproducing a target span verbatim within a long context is a fundamental capability test for LLMs: even when the target string is present in context, models often still drift within the…MAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM Systems
Agentic AI extends large language models (LLMs) from generating responses to planning and executing complex workflows, substantially expanding their utility while exposing applications to unsafe…The Instruction Tax on Factual Recall: Base Models Can Beat Their Instruction-Tuned Counterparts
We present our solution to the AKBC LM-KBC 2026 Shared Task, where we achieved a score of 0.6836 on the official leaderboard, more than double the baseline of 0.2964.Every Model Leaves a Trace: Multi-Resolution LLM Fingerprinting
Large language models leave model-specific traces in their generated text, but it remains unclear how finely these fingerprints can distinguish related models and which signals remain informative as…MythoSemantic: An Interactive System for Discovering Semantic Parallels Across Mythological and Religious Traditions
We present a tool for the comparative study of mythological and religious texts.Toolflation: Seller Agents Distort Tool Markets Through Spontaneous Generative Engine Optimization
Agents are starting to sell to other agents.GPT-6-Astra Understands Touch and Outperform Vision--Tactile--Language--Action Models
General-purpose multimodal models have shown promise as direct robot action policies, yet whether they grasp the physics underlying real-world interactions and can apply that understanding to guide…Asymmetric Looped Transformers: Fixed Global Representations for an Iterative Decoder
Looped Transformers increase effective depth by repeatedly applying shared layers, offering a way to scale computation without increasing parameter count.OptionWorld: A Benchmark for Diagnosing Failures of LLMs as Long-Term Personal Assistants
Long-term assistants must follow unfinished tasks across days as information and circumstances change.Present but Hard to Read: Probing Latent Reasoning with Minimal Pairs
Probing studies of latent reasoning often read a model's state where the answer begins and take a failed probe as evidence that a value is absent.BitMTP: When Multi-Token Prediction Meets Low-Bit Large Language Models
For efficient deployment of large language models (LLMs), methods of ultra-low-bit backbones reduce weight storage, memory traffic, and linear-layer execution cost, while multi-token prediction…Binary Discrete Diffusion: Candidate-Set Diffusion for Logic and Planning Tasks
Discrete diffusion models iteratively denoise a noisy sequence of categorical data such as text, enabling any-order generation with self-correction and in-filling capabilities.Large Flow Language Models
Continuous flow language models offer a path to parallel generation with tools for control and acceleration unavailable to discrete diffusion, yet effective techniques for building them at the…Cache Engineering for Agents
Large Language Model (LLM) agents can handle increasingly complex tasks, navigating long trajectories of observations and actions.Capable Teacher, Myopic Scorer: Reward-Free Teacher Repair for Agentic On-Policy Distillation
Agentic on-policy distillation (OPD) trains a student agent on its own trajectories while a teacher scores every token.Benchmarking Arabic Dialects for Math Problems
Mathematical reasoning remains underexplored for low-resource languages, including Dialectal Arabic.NarraSpace: Multimodal Scene-Grounded Evidence for Picture-Description Dementia Classification
Picture-description dementia classification uses a shared visual scene, but a transcript-level prediction alone does not identify the scene evidence underlying its inputs.Translation and data ethics
This chapter introduces data ethics for translation and discusses a number of ethical issues regarding data.Qwen-Audio-3.1-ASR Technical Report
We present Qwen-Audio-3.1-ASR, a family of audio-language models that builds upon its predecesor Qwen-Audio-3.0-ASR with improved speech recognition and expanded capabilities in speaker-diarized…