AI & Machine Learning · Computer Science & AI
Artificial Intelligence
The newest papers in Artificial Intelligence 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 11 October 2026 to 5 November 2026: 4,993 arXiv preprints and 7 OpenAlex records.
Get the few papers worth your time in Artificial Intelligence every morning.
Follow Artificial Intelligence 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 3
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?The Popular Get More Popular: Auditing Brand Bias in Generative Search
The shift from traditional to generative search has fundamentally transformed online product discovery.Beneath the Surface: What We Overlook When We Talk About Agent Evolution
Agent harness evolution enables recursive self-improvement (RSI) without updating model weights.Redacting Personal Data: A Speed and Accuracy Comparison of Regex, Presidio and Hybrid Designs
Many enterprise projects now pass free text to large language models (LLMs), and that text often contains personally identifiable information (PII) such as names, phone numbers, email addresses…Measuring the Marginal Value of Verifier-Based RL Beyond Supervised Fine-Tuning
Reinforcement learning from verifiable rewards (RLVR) is usually evaluated as an alternative to supervised fine-tuning (SFT), or as a stage that follows it, with the implicit assumption that the RL…Beyond Instruction Override: Benchmarking Indirect Prompt Injection with Task-Tampering Attacks
Indirect prompt-injection (IPI) benchmarks predominantly test planted instructions that redirect a tool-using agent toward an attacker-chosen task.Neural Image Compression with Internal-External Prior Fusion and Alignment
Existing context models for learned image com- pression rely primarily on internal priors from the current image, overlooking common patterns and typical textures shared across natural images.WaSP: Wasserstein Data Synthesis Pipeline for Solver-Free Operator Learning
Neural operators offer fast surrogates for solving PDEs, but training them typically requires expensive input-solution pairs.UniGADD: Universal Generator-Agnostic Deepfake Detector
In this paper, we introduce Universal Generator-Agnostic Deepfake Detector (UniGADD), a novel method that employs supervised learning to achieve high accuracy on known deepfake generators, while…What the Middleman Delivers: Answer Behavior, Tool Permissions, and Billed Usage in LLM API Relays
Third-party application programming interface (API) relays offer access to large language models (LLMs), often at lower prices.GraspBench: Execution-Aware Cross-Robot Evaluation of 6-DoF Grasp Generation in MuJoCo
Modern 6-DoF grasp generators are often evaluated using grasp scores, dataset-level metrics, or single-robot demonstrations, yet proposal quality alone does not determine whether a grasp is…Don't Prompt Your Agents. Equip Them: Skillware as a Modular Standard for Sovereign, Auditable, and Deterministic Capability Execution for Logical Systems
Current autonomous logical systems rely on a fragile assumption: that language models should dynamically write code, guess API payloads, and memorize operational constraints through prompt…PharmAgents2: Towards Autonomous End-to-End Drug Discovery
Drug discovery requires continuous scientific decision-making across a vast research space.Energy-Aware Open-Vocabulary Detection Scheduling for Low-Power Robotic Autonomy
Open-vocabulary object detection (OVD) lets robots search for run-time object queries, but fixed-rate inference spends embedded compute on low-value frames during idle motion, map revisits, or…Who Should Know What? Empirical Information Design for Multi-Agent LLM Economies
The performance of multi-agent LLM systems depends not only on the capabilities of the underlying models but also on information-sharing policies, which govern what information each agent observes…Randomized Parallel Complexity of Weakly Convex Optimization
We study the minimum number of query rounds needed to find approximate stationary points of nonsmooth weakly convex functions, measured by the gradient of the Moreau envelope.ReferClaw: Disambiguating User Intent for Egocentric Assistance
Users of egocentric AI assistants often ask short, ambiguous questions whose intended referents cannot be uniquely resolved from video and dialogue history.MCPHallu: Benchmarking Reasoning, Execution, and Memory Hallucinations in MCP Agents
Large language model agents are increasingly deployed through the Model Context Protocol (MCP), which allows them to discover and invoke tools across multiple servers at runtime.Equivariant Deep Learning in Direct-Product Space for Electronic-Structure Hamiltonian Prediction
Most existing equivariant architectures for Hamiltonian prediction propagate features in direct-sum spaces of irreducible spherical tensors, whereas the target Hamiltonian is naturally an operator…InfMasking: A Unified Variational Framework for Synergistic Multimodal Learning
Multimodal models are expected to exploit synergistic information, that is, information available only when multiple modalities are observed together.