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 109
Learning Perception to Action Rules through Reinforcement Learning for Theory-of-Mind Reasoning
In Theory-of-Mind (ToM) reasoning, large language models may correctly infer the agent's mental state but fail to use that inference when predicting or judging the agent's subsequent actions.Evolve Together, Fall into Place: How Social Scaffolding Shapes Self-Evolving Multi-Agent Systems
Recent work lets LLM agents evolve their own harness, up to the team itself.Delta Tokenizer: Reference-Identical Tokenization of Session Deltas and Segment-Parallelism for Long Prompts on Multicore CPUs
An agent that drives an LLM sends the model the same conversation again and again, and each turn adds only a little text at the end.Model vs. User: Whose Values Prevail? Inference-Time Value Alignment in Multi-Turn Conversations
Human values shape how we expect language models to behave.MAPLE: A Multi-Axis Parametric Knowledge Extraction Lens for LLM Evaluation
LLMs absorb vast knowledge from training data, yet their inherently probabilistic nature offers no guarantee that this knowledge will surface in their outputs.EGCForest: Structured Agent Memory Organization for Enterprise Group Chats
Enterprise group chats record project progress, decisions, task ownership, and other organizational information valuable to enterprise agents.OpenTWBench (Open Taiwan Benchmark): Taiwan-Domain Knowledge Evaluation for Large Language Models, and How the Measurement Apparatus Shapes the Score
We present OpenTWBench, an open evaluation suite for Taiwan-domain knowledge in large language models, built around two benchmarks. tw-exam-bench contains 255,854 four-option questions across 148…SEA-HELM Audio: Evaluating Multilingual ASR-LLM Pipeline Performance Across SEA-HELM Subsets
We introduce SEA-HELM Audio, a Southeast Asian (SEA) multilingual evaluation framework that extends the text-based SEA-HELM benchmark to assess performance degradation in cascaded automatic speech…Rationale Distribution Distillation via Flow Matching for Distributional Continuous Latent Reasoning
Sampling multiple chain-of-thought rationales from a language model can uncover correct solutions missed by a single attempt.RCCM: Diagnosing Gains and Harms in Reasoning-Prompt Transfer
A reasoning prompt can improve one deployment and degrade another.Frustratingly Easy Majority Voting Using Length Conditioning
Majority Voting (MV) is a simple and widely used strategy which improves the reasoning accuracy of Large Language Models (LLMs) by allocating additional inference-time computation.Beyond Benchmark Accuracy: A Diagnostic Test for LLM Chemical Prediction
LLMs have achieved strong performance on chemical prediction benchmarks.Not All Criteria Matter: Importance-Aware Criteria Weighting for Rubric-Based LLM Evaluation
Rubric-based evaluation assesses the responses of large language models (LLMs) by aggregating the verification results of explicit criteria, yet not all criteria matter equally.MolHop: Scaffold-Hopping Molecular Design with Agentic Reinforcement Learning
Molecular design is often formulated as an optimization problem over existing molecular spaces.MemDuet: Learning Dual-Process Memory for Long-Context Reasoning
Reasoning over infinitely long documents is becoming a reality with recurrent memory agents.To Reason but Not to Stop: Understanding and Recovering Pruned Large Reasoning Models
Weight pruning can degrade the accuracy of large reasoning models (LRMs), yet it remains unclear whether it damages reasoning itself.Does Machine Translation Retain Media Bias?
Within the most recent two decades, machine translation (MT) has been advanced from a research area to a mature, deployed technology for prose text and most language pairs.AtomSearch: Evidence-Grounded Tree Search for Agent Skill Optimization
Agent skills adapt frozen models through editable external instructions.Choosing the Number of Attention Heads from Intrinsic Dimension: A Small-Scale Study
The number of attention heads in a transformer is usually set by convention or grid search.SoK: Grading Open-Text Legal Answers, from Law School Exams to Trustworthy Rubric Judges
Law students are examined through open-text answers: case solutions, essays and memos that apply the law to a set of facts.