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 113
PRISM: Transfer and Limits of Activation Interventions in Tool-Calling Language Models
Recent literature shows that unsafe tool calls can often accompany textual refusals in language models.A Self-Improving Agent that Grows its Own DSL: Oracle-Free Operator Induction for Exact Question Answering
A self-improving agent has to decide which new skills to keep, and in practice it keeps whatever earns a high reward, convinces a judge model, or compresses its library, even when the skill is wrong.Gibbs-Gap Policy Optimization for Off-Policy RL with Verifiable Rewards
Reinforcement learning with verifiable rewards often trains language models on responses generated by a different, possibly stale behavior policy.Wolof-Adapted Industry-Ready Open-Weight Language Models
Wolof is spoken by 23M people, mostly in Senegal, but remains weakly supported by open-weight language models, while API models raise cost, governance, and sovereignty constraints for local…CoTranslator: Reverse to Forward Chain-of-Thought Translator for Reasoning Distillation
Reasoning distillation requires chain-of-thought (CoT) data with correct answers, but obtaining such data efficiently remains challenging.PEDBench: Can Speech Models Detect Phonetic Errors?
Phonetic error detection (PED) aims to identify phoneme-level substitutions, deletions, and insertions and is essential for educational and clinical speech assessment and intervention.Confidence-Calibrated Inference Expansion for Evaluator-Guided Test-Time Reasoning
Evaluator-guided reasoning presents a local control problem at every step: trust the current answer, return a fallback, or spend more inference.Evolving Together, Failing Apart: The Skill-Policy Co-evolution Trap in Self-Improving Agents
Skill-policy co-evolution, in which an agent's policy model and its skill bank improve each other during training, is a promising paradigm for self-improving agents.Probing Negation Understanding in Vision-Language Models With Object Attention
Negation is a fundamental aspect of language understanding and it is important vision-language models (VLMs) are able to process it effectively.Does Morphological Correctness Matter for Tokenization? A Scrambled Control Study in Tagalog
Typology-aware tokenizers are motivated by the claim that segmentation which respects morpheme boundaries preserves information that frequency-driven segmentation destroys.CogDrift-4D: Hierarchical Multimodal Modeling of Temporal Behavioral Decay for MCI Detection
Early detection of mild cognitive impairment remains a critical bottleneck in dementia care, demanding scalable tools capable of capturing subtle behavioral decay.Wrong Votes, Right Gradients: Why Majority-Vote Rewards Track Verifiable RL
Reinforcement learning with self-generated labels, such as majority vote over a model's own samples, often recovers most of the gain of training with verifiable rewards.Task-Centric Multimodal Learning for Cognitive Impairment Detection
Dementia affects millions of older adults worldwide, yet early detection remains difficult outside clinical settings.SkillNEO: Non-Elitist Evolutionary Optimization of Agent Skills
Agent skills turn procedural knowledge into reusable artifacts, allowing LLM agents to accumulate and refine expertise through experience.Prune the Summary, Not the History: Source-Judged Compaction for Long-Horizon Agents
Long-horizon LLM agents rely on context compaction: when the interaction history outgrows the context window, a compressor replaces it with a natural-language summary.LEV: Thinking Fast and Deep with Looped Decision Models
Decision models answer typed questions about an input with one probability per option, computed in a single forward pass without generating text.Same Context, Different Agents: A Behavioral Study of Semantic Layers, Orchestration and Compaction in Data Agents
Answering questions over heterogeneous data means combining evidence from files, databases, documents and the web.VELD-QA: A Large-Scale Dataset for Visual Evidence Grounding and Question Answering in Long Documents
Existing long-document QA benchmarks rarely combine large-scale human-authored questions with detailed visual evidence annotations, limiting diagnosis of evidence localization and interpretation…One Bias Score, Two Factors: How Mitigations Affect Option Bias in Multiple-Choice Evaluation
Reordering multiple-choice options can change a model's answer, an effect studied as selection bias (a preference for certain option letters) and as order sensitivity (changes in answers across…Can LLMs Anticipate Their Cruxes?
To use language models to help us make decisions we would like to understand the rationale behind the language model's outputs.