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
HyFlash: A Prefix-Memory Prior for On-Device Speculative Decoding
Parallel block drafting accelerates speculative decoding by predicting multiple future positions in a single backbone pass, but on-device deployment constrains both drafter capacity and context…Encoding and Propagation of Grammatical Number in Large Language Models
Sparse autoencoders (SAEs) have become an increasingly popular means of translating Large Language Model (LLM) hidden state vectors into a human-comprehensible list of features or symbols.EnvOpt: Automated Optimization for Agent Environments
An LLM agent's cost and success depend on its model, its harness, and its environment.Latency-Aware Adaptive Best-of-$N$
Test-time compute (TTC) improves language model responses by spending additional computation at inference time, and the right amount of compute depends on the prompt.The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks
How can an agent handle a real-world task end to end?FINCOSMOS: An Open-World Evaluation Paradigm for Agents in Finance
Language agents increasingly work for users on the open Web, and finance is where trusting them is hardest.Recursive Self-Improvement for Long-Horizon Role-Playing Dialogue
Long-horizon role-playing dialogue requires consistent character identity, reliable memory, and context-sensitive interaction.Localization Does Not Imply Steerability: A Mechanistic Study of Sign Errors in LLM Mathematics
When large language models do multi-step mathematics, a characteristic failure recurs: the model writes one wrong sign token mid-computation -- a cofactor sign, the minus of a recursive…MEvince: Knowledge-Constrained LLM Reasoning for Technique Identification from Malware Reports
Mapping behavioral intelligence in malware analysis reports to ATT&CK techniques supports threat analysis and defense, but reliable identification remains challenging.ReviewMap: Mapping Evaluative Acts and Automation Boundaries in Peer-Review Comments
Peer-review comments check what a paper does and judge why it matters, but no existing scheme distinguishes these two evaluative acts.Enhancing Repository-Level Code Completion with Reinforcement Learning in Real-World Scenarios
The rapid development of large language models (LLMs) for code, which closely aligns with the practical needs of real-world software development, has sparked growing attention in repository-level…SPARE: Fast Linear Attention Decoding with Compact Recurrent States
Linear attention reduces the quadratic sequence-length complexity of softmax attention by maintaining fixed-size recurrent states.The Memory Trap: Language Agents Overgeneralize from Benign Interactions
Language agents increasingly use persistent memory to record user preferences and procedures across sessions.SKIM: Pruning Large Language Model Agents via Selective Knowledge Informed Masking
Large Language Model (LLM) agents are increasingly deployed under structured generation, where grammar constraints enforce output format at inference time.Stress Testing Chain-of-Thought Monitoring Against Covert Misalignment
As LLM agents advance rapidly in autonomy, the risk of hidden objectives that bypass safety constraints becomes increasingly plausible.Fine-Tuning a Transducer for Impaired Speech: Where the Gains Appear and What They Mean for Evaluation
Speech recognition still works poorly for many people whose speech is affected by conditions such as ALS, Parkinson's disease, cerebral palsy, Down syndrome or stroke.The Gating Mechanism of KV Cache Eviction
KV cache eviction must decide which entries carry information that the rest of the cache can no longer supply.Embedding-Space Fingerprinting of LoRA Fine-Tunes: Recovering the Training-Data Domain from the Model Artifact Alone
When a base language model is fine-tuned with Low-Rank Adaptation (LoRA), how much of the training data domain leaks into the resulting artifact?English Calibration Erodes Lithuanian in Expert-Pruned Mixture-of-Experts Language Models
Expert pruning compresses Mixture-of-Experts (MoE) language models by removing the experts that a calibration set marks as unimportant.Continued Training of Continuous Language Flows with Token Identity Squared Supervision
Diffusion and flow models have recently been extended to language modeling, generating text through continuous denoising in token embedding spaces.