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 206
SALMONN-duo: Adaptive Dual-System Coordination for Full-Duplex Voice Agents
Full-duplex speech large language models (LLMs) enable low-latency, natural voice interaction.DreamingGoose: Staged Distillation from Autoregressive Transformers to Bidirectional Recurrent Diffusion Language Models
Pretrained autoregressive Transformers represent a large sunk investment in compute.Recursive LLM Degradation in Biomedical Question Answering: A Cross-Generation Study
Repeatedly training language models on their own generated data may create a synthetic-data feedback loop in which errors and distributional biases are reintroduced into subsequent training datasets.BIABench: Evaluating AI agents on real-world bioimage analysis tasks
Artificial-intelligence (AI) agents hold promise for automating bioimage analysis, yet no benchmark evaluates whether they can carry out real-world analyses end to end.Over-Personalization Is a Decision Failure: Generation-Induced Apply Bias in LLMs
Personalized LLMs must decide, for each stored preference, whether the current context calls for applying or suppressing it, which we call its applicability.ReScraper: Unified Scraping and Cleaning of Web Data for Effective LLM Pretraining
LLM pretraining corpora are normally cleaned by a stack of hand-written heuristics.Dr.Credit: Rubric-Grounded Process Credit Assignment for Deep Research Agents
Rubric-based tasks are increasingly addressed through reinforcement learning (RL), with rubric scores used as training rewards.ControlScope: Workflow Revision and Reliability in LLM Agents
How much of a running workflow should a language model agent revise?PlaylistEval: Can Video-Language Judges Be Trusted at Day Scale and Beyond?
Video-language models are increasingly used as judges of video understanding, both for evaluating model outputs and for training reward models.Certified Selective Automation of LLM Agent Evaluation
Evaluating LLM agents still ends with a human reading trajectories, because automatic judges carry no guarantee on how often they are wrong.Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge
Scaling test-time computation is a powerful way to improve language-model reasoning, and is particularly appealing for small reasoning models (sRMs) that are cheap to serve.CRISP: Cultural Reward Modeling for Implicit Situated Propriety
As large language models (LLMs) are increasingly deployed across countries and regions, the ability to recognize and respond appropriately to diverse cultural contexts becomes increasingly important.Commutator Memory: Sparse, Path-Local Reading and Steering in Language Models
Gradient updates on different data generally do not commute: training a language model on two data sources in opposite orders gives different weights, even with the same data and total exposure.FORGE: Form-Optimal Routing of Grounded Evidence for Frozen LLM Agents
In agentic AI systems, frozen foundation models are increasingly deployed as closed-weight API endpoints, making downstream adaptation possible only through the inputs and inference procedures…When Harness Beats Scale, and When Reading Beats Both
We describe our system for DocSem, the document-grounded quantitative reasoning shared task at DocInsights 2026, and analyze why it succeeded on labeled data and failed on the test set.Just-In-Time Agent Memory with Runtime Agentic Research
Memory is critical for AI agents.Look Before You Select: Rethinking Vocabulary Sparsification in On-Policy Distillation
On-policy distillation (OPD) uses teacher correction on student-generated responses.Reciprocal Guidance: Orchestrating Draft and Verify Budgets for Advancing the Diffusion-AR Self-Speculation Frontier
Diffusion drafting with autoregressive (AR) verification has emerged as a promising paradigm for efficient speculative decoding.Coding Agent Memory Post-training: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via Reinforcement Learning
Language-model agents increasingly tackle long-horizon tasks whose interaction histories exceed the model's active context.Zero-Shot Cue-Grounded Topic Segmentation of Spoken Documents
Topic segmentation structures spoken documents into coherent sections, facilitating navigation and downstream understanding.