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 18 September 2026 to 6 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 228
Compact Documentation for Coding Agents: A Benchmark, an Optimizer, and Why It Does Not Transfer
We investigate whether natural-language documentation helps coding agents resolve software issues, and we build the tools to construct and evaluate it.User Model Extraction via Belief Self-Distillation
Large language models (LLMs) implicitly infer attributes of their users and adapt their behavior accordingly, yet these beliefs remain difficult to inspect and causally manipulate.Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency
Reasoning models often generate very long reasoning traces, making inference computationally expensive.Omni-IO Skills: Harnessing Your Agent Omni-Native
General-purpose agents can plan, reason, and act over long horizons, yet their production capabilities remain fragmented across text, images, audio, video, documents, 3D assets, and code.IndustryLLM: Failure-Driven LLM Training for Industrial Procurement
Industrial procurement requires language models to bridge informal buyer jargon, sparse marketplace attributes, and authoritative engineering standards under strict safety tolerances.CueKFS: Agentic Cue-Driven Keyframe Selection for Long Video Understanding
Keyframe selection (KFS) has long produced compact video summaries for browsing and retrieval, and representative frames for thumbnails.Agents Can Use Base Models to Evade AI Detection
We show that coding agents equipped with a base language model can successfully assemble responses from its samples to evade detection.NVAlign: Direct-Gradient Optimization for Non-Verbal Control in Continuous Autoregressive Flow Matching Text-to-Speech
While modern text-to-speech (TTS) systems generate highly natural speech and support inline non-verbal vocalization (NVV) tags, accurate control over these events remains challenging.Choir: An Open Protocol for Distributed Multi-Agent Autoformalization
AI agents can now formalize entire textbooks and major theorems in proof assistants such as Lean, but current efforts are typically centralized: a single team runs all agents and bears the full…Improving Medical Calculation of LLMs with Embedded Coding
Large Language Models (LLMs) perform well on medical examinations and question-answering benchmarks, but remain unreliable on medical calculation tasks that require exact numerical outputs.Recipe-Matching, Not Equivalence
MathNet-Retrieve asks a retriever to find, for a math problem, a document stating the same problem.Transformer MLP Gate Thresholds Are Couplings to a Carried Reference Direction
The corpus-mean direction of a transformer's residual stream is a component shared across all inputs, and is commonly removed by mean-centering before representational analysis.Improving Audiovisual Speech Recognition through Synthetic Visual Data Augmentation
Audiovisual Speech Recognition (AVSR) is a multimodal approach to speech recognition that incorporates visual information from lip movements to enhance model performance.IndicFDB: Benchmarking Full-Duplex Voice Agents across Indian Languages
Full-duplex voice agents must handle pauses, take turns, backchannel, and respond to user interruptions in real time.Extraction of clinical findings from mammography and breast ultrasound reports: a comparison between specialists and Artificial Intelligence
Breast cancer is the leading cause of cancer-related death among women in Brazil, and the time between the request and the release of mammography reports directly influences adherence to screening…Toward Embedding-Based Psychometrics: Structural Modeling of Assessment-Item Semantics With Contextual Scores
Contextual scores represent assessment items through their similarities to reference words in an external corpus.Communication between Frozen Large Language Models via Prompt Optimization in a Referential Game
We study communication between two frozen large language models from different providers, with different tokenizers, accessed through their API endpoints.Before the Rollout Ends: Early Terminal Reward Prediction for Long-horizon Coding Agents
Long-horizon coding agents receive verifiable rewards only after completing expensive sequences of tool calls.Who Governs Data in the AI Era? A Computational Analysis of the U.S. Privacy Workforce in Job Postings
Privacy protection now spans legal, technical, and managerial duties, and demand for privacy professionals is growing across sectors.Amnesia by Design, Memory By Necessity: Persistent State for Document Intelligence
Modern Document AI reads contracts, extracts fields, reasons over tables, and grounds answers to page regions, then forgets everything.