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 18 September 2026 to 6 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 224
On the Behavioral Traits of LLM Agents
Users increasingly describe different AI agents as distinct colleagues to work with.CLAIRE: A Schema-Grounded Hybrid Workflow for Healthcare Administrative Form Completion
Healthcare administrative staff transfer structured information from electronic health records, referrals, claims systems, provider rosters, and work queues into dynamic forms.Understanding and Exploiting Anisotropy in Post-Training
LLM post-training combines supervised fine-tuning (SFT), a mode-covering forward-KL objective, with reinforcement learning (RL), a mode-seeking reverse-KL objective.Re-derivability Decides What a Staged Agent Pipeline Recovers After an Upstream Fault
One variable sets what an upstream fault costs a staged pipeline of language-model agents: re-derivability, how much of what a stage needs it can rebuild from the original problem.Decision-Sufficient State Representations: Measuring and Reducing Write-Time Regret
Long tasks produce more history than an LLM agent can hold in its context, and more than it uses reliably even when the history fits.Mind the Spike: Mechanisms and Brittleness of Visual Massive Activations in Large Vision-Language Models
Large vision-language models (LVLMs) inherit massive activations from their text-only bases: spikes where a few fixed hidden channels receive values thousands of times above the typical magnitude.Overwhelmed by Choice: Studying LLM Decision Making at Scale
Multiple-choice and candidate-selection evaluations are widely used to assess LLM reasoning and decision-making, yet most benchmarks contain relatively small candidate sets.OpenTumorBoard: A Real-World Benchmark of Multidisciplinary Tumor Board Discussion Trajectories
Multidisciplinary tumor boards integrate multimodal clinical observations and longitudinal patient histories through specialist discussions, yet benchmarks rarely capture these real-world…USAI-Quant: A Quantitative Reasoning Benchmark for Vision-Language Models in Built Environments
Large vision-language models (VLMs) have emerged as a powerful paradigm for urban and spatial AI.The Decomposition Tax: LLM Pipelines Lose Up to 40 Accuracy Points at Their Own Interfaces
A four-stage LLM pipeline gives up as much as 40.5 accuracy points at its own interfaces (gemma-3-12B on MATH-500, Holm-corrected p = 1.66e-19; the largest tax in the primary family).ARSM: Auto-Regressive State Machine for Agentic Reasoning Compression
While Large Language Model (LLM)-based agents demonstrate strong capabilities in long-horizon tasks by interleaving reasoning with external environment interactions, the continuous accumulation of…Are You Sure You're Sure? Two Confounds in a Sycophancy Benchmark
Sycophancy is a language model's tendency to cave when a user pushes back, abandoning a correct answer for the user's.Multimodal LLMs Outperform Pathology Foundation Models in Cross-Domain Histological Similarity
State-of-the-art pathology foundation models, trained on millions of histology tiles, can fail to preserve tissue similarity when comparisons cross slide or institution boundaries.Linger and Lose: Knowledge Collapse in Low-Bit Language Models
Training language models with ternary weights is commonly judged by loss and downstream accuracy, which record only a modest cost relative to full precision.Logical subspace in LLMs
Recent work has identified a human brain network specialized for abstract formal reasoning (Kean et al., 2025).Planner-as-Router: Joint Plan-Time Model Routing for Cost-Efficient Multi-Agent Workflows
Running large language model (LLM) agents in production gets expensive fast.Theory of Scene: Breaking the Symmetry Trap in Multi-Agent LLM Coordination
Multi-agent systems built on large language models (LLMs) are largely homogeneous, as their agents behave alike even across distinct LLMs.The Key Handoff: Retrieval in Hybrid Language Models
A two-hop question makes a language model retrieve twice: once to produce a bridge entity, and once to retrieve with it.DynamicDx: Evaluating Evidence Acquisition in Video-Based Diagnosis
Diagnosing a patient from video requires more than recognizing the sign: a vision-language model must turn what it sees into hypotheses, questions and tests.TCMQA: A 38K-Question Traditional Chinese Medicine Benchmark with a Licensed-Practitioner Reference
Medical benchmarks for language models are built almost entirely on Western biomedicine.