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 105
Not All Graphs Are Maps: A Task-Agnostic Exploration Framework for Mobile GUI Navigation
Modern mobile GUI agents can perceive visible screens and execute local actions, but they still lack persistent app-specific navigation knowledge: where functions live, which pages contain them, and…Multimodal Filesystem Memory For Long-Horizon Embodied Agents
Agents operating over long horizons need an effective memory that allows them to reuse their experience throughout long interactions.Explore Separately, Adopt Selectively: Execution-Guided Tool Use over Large Tool Libraries
Large language model agents must discover relevant tools from large libraries, e.g., thousands of tools, as new needs arise during task execution.GlobeBench: Evaluating Text-Based World Model Capabilities for Scalable Environment Simulations
Text-based world models have recently shown potential to simulate complex RL environment state transitions for a diverse set of use cases.First Passage Attention
Augmenting softmax attention with forget gates typically relies on summing decay contributions along the key--query path.Risk and Refusal: Mechanisms of LLM Responses to Suicidal Ideation
Refusal is a common safety mechanism in large language models (LLMs), yet in contexts of suicidal ideation (SI), refusing to engage can itself constitute a safety failure.ARBOR: Locating Reasoning Failures in Long Chains of Thought through Reasoning State Tracking
Large reasoning models solve complex problems through long chains of thought, in which prior work has documented failure modes such as overthinking, underthinking, and unsupported deductions.CoLU: Confidence-Weighted Layerwise Unlearning for Large Language Models
Large language model (LLM) unlearning aims to forget certain information while preserving others, without retraining from scratch.A misinformation playbook sharpens judgement without breeding cynicism
Misinformation harms public health and democracy, and generative artificial intelligence now writes falsehoods as persuasive as people's.TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents
Advances in frontier coding agents have sharply increased the token costs of AI-assisted software engineering.Thunder-DeID+: Boundary-Aware Korean De-identification from Court Judgments to Broader Sensitive Documents
This study examines the transferability of a de-identification model developed for Korean court judgments to a broader range of sensitive documents, focusing on boundary precision, label…Reading the News Without Hindsight: NoLBERT Topics and the Cross-Section of Stock Returns
Language models that read financial news are usually trained on text from the same years used to test them, so a backtest can reward hindsight.Disentangling Depression from Cognitive Decline in Elderly Speech Using Concurrent Clinical Assessments
Detecting depression from speech in elderly patients with mild cognitive impairment (MCI) is complicated by overlapping acoustic effects of cognitive decline.PW-Pruning: Phase-Aware Expert Selection for Speech-Centric Omni-Modal Models
Sparse routing reduces per-token computation but leaves the full expert bank resident in memory.TopicMerge: A Divide and Conquer Approach to Topic Modeling
Recent advancements in topic modeling have split into two main paths: efficient embedding-based methods that offer scalability but are often outperformed on standard clustering metrics, and Large…LLM-jp-4 Technical Report
This paper presents LLM-jp-4, a family of Japanese sovereign large language models (LLMs) developed with an emphasis on transparency, reproducibility, and practical usability.Counterfactual Gate-Support Decomposition: Separating Selection from Redistribution in Training-Data Filtering
A training-data quality gate changes both which examples survive within regions of the input space and how training mass is distributed across those regions, so a gate-versus-random comparison does…Target-Token Asymmetry Can Masquerade As Depth Specialization
Layer-ablation studies often perturb early or late layers of a language model, compare the damage to prediction on two corpora, and read a larger early-layer effect on one corpus as early-layer…Where to Start, How to Move: Analyzing Curricula under GRPO for Long-Horizon LLM Agents
Group Relative Policy Optimization (GRPO) provides no reward-relative learning signal when all rollouts receive identical rewards.Steering Vectors for Competing Ethical Frameworks Are Interchangeable: A Competing-Target Test for Activation Steering
Activation steering adds a vector to a model's hidden states to control a named behaviour.