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 139
RUBATO: Decoupled Clocks Allow Full-Duplex Models to Think as Fast as They Can
Recent Speech Full-Duplex (FDX) models are capable of engaging in naturalistic conversation by listening and speaking at the same time.ASSET: Adaptive Speech Segmentation via Reinforcement Learning
Speech large language models (LLMs) are often built using pretrained acoustic encoders as an audio interface to an LLM decoder.Which Metadata Matters for LLM Tool Selection in MCP? Evidence from Controlled Factor-Level Interventions
In Model Context Protocol (MCP) systems, LLMs select tools from metadata rather than from their implementations.Evaluating LLMs as Agentic Workflow Executors in Real-World Customer Support Skills
Enterprise customer-support agents increasingly rely on Large Language Models (LLMs) to execute bounded, tool-using workflows.Multimodal Co-Generation With Continuous Bitstream Diffusion
We show that continuous bitstream diffusion (CoBit), originally developed for language modeling, provides a unified framework for joint and conditional multimodal generation using the same training…Tokenization-Invariant Watermarking: A Byte-Local Method for LLM Text
We introduce Tokenization-Invariant Watermarking (TI-WM), a method that embeds a watermark during token generation but keys and scores it on canonicalized UTF-8 bytes.SciCurateBench: Curating Experimental Data from Heterogeneous Scientific Literature with Verbal-Action Agents
Scientific research increasingly depends on curating experimental data from literature.RealityBench: Simulated Environments to Evaluate a Vision Language Model's Ability to Document Human Physical Work
Augmenting worker capabilities in the physical world through guidance has been a decades-long goal for AI agents.SPROUT: Scaling Agentic Reinforcement Learning for Long-Horizon Software Engineering
Reinforcement learning (RL) has driven substantial progress in coding agents by relying on verified successful trajectories as learning signals.FedAlphaEdit: Null-Space-Aligned Merging for Collaborative Knowledge Editing
Multiple institutions may each hold their own private knowledge edits and wish to integrate them into a single large language model without sharing raw edit requests.Measuring and Mitigating Solution Mode Collapse in RLVR
A language model (LM) can usually answer the same question in more than one way, but reinforcement learning with verifiable rewards (RLVR) is indifferent to which correct answer a model produces.Clinician use of language models diverges from how the models are evaluated
Large language model (LLM) assistants are being deployed to clinicians across health systems, and judgments about their readiness rest largely on benchmark scores, most of them derived from…Lapras: Latent Reasoning for Time Series Language Models
Time Series Language Models (TSLMs) offer a promising path toward time series understanding by reasoning over temporal signals and producing natural language answers and explanations.GameCommBench: A Unified Benchmark and Type-Aware Evaluation for AI-Generated Game Commentary
Game commentary is an open-ended generation task requiring multimodal perception, strategic reasoning, and contextual knowledge.SFT-as-Context Mitigates Forgetting in Supervised Fine-Tuning
Supervised fine-tuning (SFT) equips large language models (LLMs) with specialized capabilities, but often comes at the cost of forgetting the general capabilities of their parent models (i.e., the…Can a System-One LLM Perform Knowledge Tracing When Few or No Learners Are Logged?
Knowledge tracing (KT) models need many logged learners, so a new course or platform starts without a usable model.The "10th Juror": Open-Set Standpoint Screening for Bureaucratic Bias Detection
Presupposing the boundaries of bias is itself a form of bias.ActiveMedAgent: Cost-Aware Trajectory Learning for Multimodal Medical Diagnosis
Clinical diagnosis is inherently sequential: clinicians escalate from cheap to costly tests only when additional evidence is expected to resolve diagnostic uncertainty.Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context RL
LLM agents increasingly improve at inference time by accumulating experience in context rather than by updating parameters.Local Prototype Reconstruction for Text-Compatible Speech-to-LLM Bridge Pretraining
Speech-to-LLM systems often connect a frozen speech encoder to a frozen large language model (LLM) through a small trainable bridge.