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 123
Improving the Evaluation of Biomedical Question Answering with Few Human Preference Signals
Retrieval-Augmented Generation (RAG) systems are increasingly used for biomedical Question Answering (QA).Of Errors and Echoes: Responsibility-Aware Credit Assignment for Tool-Use Agents
Reinforcement learning improves tool-use agents, yet fine-grained credit assignment remains challenging even with step-level feedback.When Agents Talk, Secrets Travel: Topology-Driven Leakage and Recipient-Conditioned Sanitization in Multi-Agent LLM Systems
Multi-agent LLM systems (MALS) introduce a privacy-leakage problem that conventional sensitivity-based defenses miss, since information disclosed to one authorized agent can propagate through…Beyond the greenwash: do LLMs' ecologically sound decisions hold up under pressure?
Humans are increasingly using large language models (LLMs) in decision making processes throughout society.Dream2Discern: Learning from Hard Latent Variants for Runtime Failure Prediction in Multi-Agent Systems
Reliable deployment of LLM-based multi-agent systems calls for runtime auditors that predict terminal outcomes from observed execution prefixes.GUIDE: Computationally Augmented Consensus for Trustworthy Clinical Practice Guidelines
Maintaining up-to-date clinical practice guidelines (CPGs) is essential for evidence-based medicine, but rapid evidence growth and complex expert consensus formation limit timely updates.Scaling Multi-Agent Intelligence with Substrate-Centric Coordination
Existing large language model (LLM) based multi-agent systems have been shown to scale poorly, and we identify three problems: reading burden that grows with the group, useful information diluted by…PID-Gated Continual Prompt Adaptation Under Noisy Feedback
Deploying LLM agents in non-stationary environments requires continually revising their instructions as the task drifts, yet rewriting after every reported mistake can turn noisy feedback into…Query Your Way Out: Benchmarking Multi-Turn Knowledge Reasoning through Generalized Puzzle Solving
Puzzles offer a natural testbed for Large Language Models (LLMs) reasoning because they pose verifiable goals under partial information and require multi-step decisions to reach a solution.Omni-Modal LLMs Know More Than They Say
Omni-modal large language models (Omni-LLMs) extend LLMs to process heterogeneous modalities (e.g., vision, audio, and IMU signals) alongside language, enabling a broader range of multimodal tasks.Phantom Merge: When Your Large Language Model Agents Pick One but Tell You About Another
LLM agents increasingly operate over multiple entities, where reliable response generation requires not only retrieving relevant evidence but also preserving its association with the correct entity.Hashrope: A Persistent Data Structure for Mechanisms of LLM Context Management
Serving stacks for large language models manage context through four recurring mechanisms: incremental edits to a growing context, branching and snapshotting for tree search, identification of…Think Before You Speak: Enabling Training-Free Latent Communication Between Language Models
Large language models (LLMs) have demonstrated remarkable capabilities in solving complex tasks in coding, mathematical logic, and iterative reasoning, especially by coordinating effectively within…DeepThink: A Conceptual Model for Knowledge-Addressable Recurrent Language Modeling
This manuscript presents DeepThink, a knowledge-addressable framework for recurrent language modeling.Lüshi-1840: Building and Probing a Knowledge Cutoff for a Classical Chinese Language Model
Language models trained only on text from before a given year are useful for studying hindsight and historical language, but the open collections of pre-modern Chinese carry no publication dates and…Avoiding What Your Teacher Already Knows: Entity Familiarity for Deep-Search Distillation
Deep-search agents are commonly trained by distilling tool-use trajectories from stronger teacher models.Error Correction in Trained TTT Layers
Test-time-training (TTT) layers update fast-weight memory while processing an input sequence.Deep Speech Representations Track Word Timing along a Low-Dimensional Circular Trajectory
Speech timing is fundamental for speech models to recognize words accurately, but how word-timing information is represented in speech models remains underexplored.agent-risk: Risk Assessment for Changes to AI Agents
Before changing a deployed AI agent (a stricter safety gate, a new model), organizations must approve the change, starting from existing logs.RelLedger: Relational Information Governance for LLM Agent Organizations
In LLM agent organizations, shared records determine which facts are available for later decisions.