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 108
HACHIMI-II: From Role-Play to Learner Behavior Modeling for Faithful Student Simulation
Simulated students let researchers test tutoring systems and teaching strategies before real learners are available, but only if the simulation reproduces where a particular learner succeeds and…Measuring and Reducing Unusable Replies of LLM Agents
People delegate multi-step work to LLM agents and read only the reply that the agent hands back.Beyond Distribution Matching: Selective Margin Preservation for Supervised Fine-Tuning
Supervised fine-tuning (SFT) changes logit margins among non-target tokens at teacher-forced prefixes.Interlock: From Local Correctness to Task Completion in Long-Horizon Agents
Large language model agents increasingly undertake long-horizon tasks in complex environments characterized by fragmented evidence, partially completed states, and dependencies across resources and…Function-Space Temporal Self-Distillation for Policy Optimization
Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in language models, but scalar outcomes provide coarse supervision over response trajectories.Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models
Multi-agent systems allow language models to solve tasks collaboratively by sharing complementary information.BANGLAPLAN: A Benchmark for Constraint-Based Planning and Decision-Making in Bangla
Large language models (LLMs) increasingly help users arrange appointments, plan journeys, and allocate limited resources.RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing
LLM routing dynamically selects and coordinates heterogeneous language models across diverse tasks.Beyond State Capacity: Why Retrieval Breaks in Mamba
Mamba models underperform Transformers on in-context retrieval.Articulation Upper Bounds for Language Models
Language captures only a subset of the perceptions, intuitions and intents that form meaning between speakers.Recognizing Dialogue Ambiguity via Candidate Set Visual Grounding
Interpreting an ambiguous utterance in real-world interactions often requires context beyond a single utterance.Mitigating Video Hallucinations via Attention-Guided Representation Perturbation
Video large language models (Video LLMs) often generate responses unsupported by the input video.MakSafe: A Spatiotemporal Semantic Framework for Formal Specification and Compliance Checking of Road Vehicle Safety Rules
Scenario-based validation is essential for automated road vehicles but cannot cover the full variability of openworld traffic.Does the Linguistic Register of Thinking Matter? Wenyan as a Compact Reasoning Register for Chinese LLMs
Visible reasoning traces of Chinese reasoning-oriented LLMs are typically written in modern vernacular Chinese, which may be verbose under limited decoding budgets.Beyond Reachability: A Relation-Semantic Reasoning Framework for Biomedical Multi-hop QA
Biomedical multi-hop reasoning over knowledge graphs requires identifying a semantically valid relation sequence that supports the answer.Qwen-MT-Lumen at WMT2026: Instruction-Specialized Translation via Quality-Aware Training and On-Policy Distillation
We present Lumen, The open-source model is available at, our submission to the WMT 2026 General Machine Translation Shared Task.PRISMATIC : Prescription Risk Inspection System for Multi-Agent Treatment Interaction in Clinical Decision-Making
Medical prescribing errors for multimorbid patients, who require complex drug regimens, are a major patient safety concern.Likelihood Is Not Authorship: Can We Reliably Measure Human Contribution in AI-Assisted Writing?
AI-text detection generally asks whether a machine wrote a text.More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning
Self-distillation in agentic reinforcement learning has produced a growing number of methods.JetSpec++: Foresight Parallel Drafting with Self Refinements
Speculative decoding's effectiveness is governed by two quantities: the acceptance rate of drafted tokens and the cost of producing them.