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 145
OnTrack: Real-Time Monitoring and Intervention in LLM Agent Trajectories via Streaming Structure-Aware Optimal Transport
Agents are deployed in applications from trip planners and stock trading to IT incident triage.Latent Core Tokenizer: Compress, but Meaningfully
Tokenizers are commonly optimized for compression, but a compact vocabulary does not necessarily distribute its capacity evenly across languages.Long Text to Predictive Features: LLM-Guided Blockwise Feature Engineering via Executable Program Search
Industrial risk-control systems typically rely on structured-data models for efficient prediction, yet substantial valuable information remains embedded in unstructured long text.SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models
Existing spatial reasoning benchmarks mainly test spatial perception: reading off relations already visible in the input.ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills
Skill-augmented agents improve sample efficiency by distilling successful trajectories into reusable strategies.Predicting Alignment Generalization with Value Representations
LLM developers post-train their models to exhibit prosocial values and behavioral traits, which are enumerated in an alignment target.WOVEN: Weaving Visual World Modeling into Multimodal LLMs
Multimodal large language models (MLLMs) struggle with spatial, embodied, physical, and temporal reasoning.FastBench: Can Streaming VLMs Perceive High-Dynamic Real-World Streams?
Streaming Video Large Language Models (VLMs) enable continuous video understanding, yet existing benchmarks focus on low-dynamic scenarios.AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of Edits
Autoregressive decoding is less suited to non-causally ordered data, e.g., cross-references or future dependencies, since their outputs cannot be revised post hoc, unlike iterative human reasoning.SWE-Duel: Towards a Self-Scaling Arena for Coding Agents
Static coding benchmarks are fixed at release.Contextual Correction of Parallel Drafts for Speculative Decoding
Speculative decoding accelerates large language model inference by using a lightweight drafter to propose multiple tokens that are subsequently verified in parallel by the target model.CLUE: A Contrastive Learning Framework for Unsupervised Event Type Induction and Annotation
Event ontology is the foundational framework for defining events in a dataset.One Model to Loop Them All: Elastic Latent Recurrence for Language Models
A latent recurrent language model applies a shared block of layers repeatedly, so one checkpoint can trade inference compute for accuracy by changing the loop count.SpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the Spire
Agentic large language models now tackle complex tasks, yet strategic reasoning over long horizons is under-studied: most agentic benchmarks are short and episodic, and performance on long tasks is…Reflective Prompt Optimization of a Deep-Research Agent: A Topic-Disjoint, Multi-Seed Protocol for Measuring Transferable Gains and Prompt-Level Overfitting
Prompt optimization is an attractive alternative to reinforcement learning for adapting language-model agents, since it is cheap and produces human-readable artifacts.Self-Preservation in Language Models
Continual learning (CL) seeks to adapt pretrained models while preserving prior capabilities.Knowing Is Not Telling: Identity Ossification in LLM Representations of Trans-border Communities
Ethnic and cultural identities rarely align with political borders, a tension made sharper by migration and long-standing cross-border ties.GeopoliticalQA: Benchmarking Retrieval and Generation over Intelligence Reports
Geopolitical and strategic intelligence reports constitute a rich source of expert knowledge and have increasing value in the current political climate, but their heterogeneity and analytical…Cancerous Backdoor Attack: Gradual Activation via Invisible Tokens and A Stage Controller
Backdoor Attacks on Large Language Models (LLMs) typically follow a trigger-response pattern, where satisfying a trigger condition activates a single terminal behavior.perturber: A Stateless Service for Semantics-Preserving Text Perturbations
Large language model (LLM) evaluations on clean benchmarks overstate model robustness: real inputs arrive perturbed, and these meaning-preserving variants routinely move model answers.