arXiv cs.AI

Artificial Intelligence daily digest.

52 past editions, oldest first by date. Atom feed → · all categories

01 — Past editions

most recent first

2026-07-19 Pretraining Data Can Be Poisoned through Computational Propaganda 59 papers · No. 58
2026-07-18 Pretraining Data Can Be Poisoned through Computational Propaganda 59 papers · No. 57
2026-07-17 Pretraining Data Can Be Poisoned through Computational Propaganda 59 papers · No. 56
2026-07-16 Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models 32 papers · No. 55
2026-07-15 Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning... 46 papers · No. 54
2026-07-14 Playful AI in Professional Email: A Field Experiment on Tone and Recipient Engagement 39 papers · No. 53
2026-07-13 ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI 32 papers · No. 52
2026-07-12 Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and... 42 papers · No. 51
2026-07-11 Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and... 42 papers · No. 50
2026-07-10 Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and... 42 papers · No. 49
2026-07-09 Institutional Red-Teaming: Deployment Rules, Not Just Models, Causally Shape... 27 papers · No. 48
2026-07-08 Rethinking Indic AI from a Lens of Cultural Heritage Preservation 44 papers · No. 47
2026-07-07 LLM-as-a-Verifier: A General-Purpose Verification Framework 30 papers · No. 46
2026-07-06 Distributed Attacks in Persistent-State AI Control 53 papers · No. 45
2026-07-05 Distributed Attacks in Persistent-State AI Control 53 papers · No. 44
2026-07-04 Distributed Attacks in Persistent-State AI Control 53 papers · No. 43
2026-07-03 Distributed Attacks in Persistent-State AI Control 53 papers · No. 42
2026-07-02 AutoMem: Automated Learning of Memory as a Cognitive Skill 20 papers · No. 41
2026-07-01 AxDafny: Agentic Verified Code Generation in Dafny 49 papers · No. 40
2026-06-30 Self-Evolving World Models for LLM Agent Planning 41 papers · No. 39
2026-06-29 Agent-Native Immune System: Architecture, Taxonomy, and Engineering 19 papers · No. 38
2026-06-28 Language-Based Digital Twins for Elderly Cognitive Assistance 51 papers · No. 37
2026-06-27 Language-Based Digital Twins for Elderly Cognitive Assistance 51 papers · No. 36
2026-06-26 Language-Based Digital Twins for Elderly Cognitive Assistance 51 papers · No. 35
2026-06-25 The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and... 25 papers · No. 34
2026-06-24 OpenThoughts-Agent: Data Recipes for Agentic Models 66 papers · No. 33
2026-06-23 PsyBridge: A Hybrid Intelligent Framework for Multi-Dimensional Mental... 38 papers · No. 32
2026-06-22 Toward Calibrated Mixture-of-Experts Under Distribution Shift 41 papers · No. 31
2026-06-21 Toward Calibrated Mixture-of-Experts Under Distribution Shift 41 papers · No. 30
2026-06-20 Toward Calibrated Mixture-of-Experts Under Distribution Shift 41 papers · No. 29
2026-06-19 Toward Calibrated Mixture-of-Experts Under Distribution Shift 41 papers · No. 28
2026-06-18 Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation 24 papers · No. 27
2026-06-17 EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot... 46 papers · No. 26
2026-06-16 Bayesian Inference and Decision Audits for Public Archives of Frontier AI Evaluations 37 papers · No. 25
2026-06-15 Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows 26 papers · No. 24
2026-06-14 Automated reproducibility assessments in the social and behavioral sciences... 54 papers · No. 23
2026-06-13 Automated reproducibility assessments in the social and behavioral sciences... 54 papers · No. 22
2026-06-12 Automated reproducibility assessments in the social and behavioral sciences... 54 papers · No. 21
2026-06-11 Nonslop: A Gamified Experiment in Human-AI Collaborative Writing 24 papers · No. 20
2026-06-10 The Role of Feedback Alignment in Self-Distillation 36 papers · No. 19
2026-06-09 Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting 46 papers · No. 18
2026-06-08 How AI Agents Reshape Knowledge Work: Autonomy, Efficiency, and Scope 21 papers · No. 17
2026-06-07 MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm... 52 papers · No. 16
2026-06-06 MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm... 52 papers · No. 15
2026-06-05 MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm... 52 papers · No. 14
2026-06-02 ClinEnv: An Interactive Multi-Stage Long Horizon EHR Environment for Agents 48 papers · No. 13
2026-05-30 Physics Is All You Need? A Case Study in Physicist-Supervised AI Development... 48 papers · No. 12
2026-05-28 Calibrating Conservatism for Scalable Oversight 66 papers · No. 11
2026-05-27 MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management,... 43 papers · No. 10
2026-05-25 SkillOpt: Executive Strategy for Self-Evolving Agent Skills 45 papers · No. 9
2026-05-23 MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems 68 papers · No. 8
2026-05-22 MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems 68 papers · No. 7

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.