AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearch$\mathrm{R}{\scriptstyle\mathrm{EAL}}\mathrm{G}{\scriptstyle\mathrm{UARD}}$: Reliable, Efficient, and Auditable LLM Safeguards via Latent Reasoning
arXiv:2608.03838v2 Announce Type: replace Abstract: Reasoning-based large language model (LLM) safeguards improve safety classification accuracy by generating explicit rationales before making decisions. However, generat…
- arXiv cs.AIagentsContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?
arXiv:2608.03874v3 Announce Type: replace Abstract: Modern agent frameworks equip large language models with external skill libraries to solve complex tasks. However, it remains unclear whether these systems can effectiv…
- arXiv cs.AIagentsOctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling
arXiv:2608.05141v2 Announce Type: replace Abstract: Context lengths of language models (LMs) have dramatically increased, driven by the demands for in-context learning, self-improvement, and long-horizon agentic workflow…
- arXiv cs.AIagentsSkillEval: Decomposing Agent Skill Quality into Interpretable Signals
arXiv:2608.06891v2 Announce Type: replace Abstract: Agent skills provide reusable knowledge that helps agents solve specialized tasks. As their use expands, evaluating skill quality becomes increasingly important. Existi…
- arXiv cs.AIresearchIllusion of Alignment: Detecting Hidden Disagreement in Collaborative Dialogue
arXiv:2608.08210v2 Announce Type: replace Abstract: Collaborative dialogue can end with apparent agreement while participants still differ on goals, assumptions, or execution plans, creating an \textbf{illusion of alignm…
- arXiv cs.AIagentsReading is not Reasoning: Bridging the Agentic Policy Gap in Vision-Text Compression
arXiv:2608.08960v2 Announce Type: replace Abstract: Multi-step language-model agents repeatedly process growing interaction histories, leading to substantial context costs. Vision--text compression reduces these costs by…
- arXiv cs.AIagentsEmotion2Skill: Model-Internal Emotion Signals for Adaptive Skill Selection and Evolution
arXiv:2608.09248v3 Announce Type: replace Abstract: Skill-based LLM agents select reusable procedures from external libraries to solve complex tasks, yet their routing decisions rely primarily on task descriptions, verba…
- arXiv cs.AIagentsBench2Robust: Scenario-Controlled Recovery for Tool-Using Agents
arXiv:2608.11977v2 Announce Type: replace Abstract: Tool-using LLM agents are typically developed and post-trained in controlled environments with reliable tools, but deployment exposes them to tool failures, API and sch…
- arXiv cs.AIresearchAI Model Design and Physician Liability
arXiv:2608.13618v2 Announce Type: replace Abstract: Clinical algorithms can perform differently across patient groups, a concern that grows as these algorithms increasingly take the form of artificial intelligence (AI) m…
- arXiv cs.AIagentsSafeBranch: Branch-Pair Safety Alignment for Embodied Agents
arXiv:2608.19729v2 Announce Type: replace Abstract: Vision-language-model-based embodied agents can complete instructed tasks but often violate safety constraints in the process, a problem recently framed as interactive…
- arXiv cs.AIagentsReguSim: Evaluating LLM Agent Rule Grounding in Financial Compliance
arXiv:2608.19974v2 Announce Type: replace Abstract: LLM agents in financial markets may cite rules yet still submit orders that violate executable constraints or misread surveillance evidence. We introduce ReguSim, a con…
- arXiv cs.AIagentsAgentic neural architecture search for clinical prediction from electronic health records: Cross-hospital knowledge transfer and computational efficiency
arXiv:2608.21712v3 Announce Type: replace Abstract: Transformer architectures for clinical prediction from electronic health records (EHRs) often require costly manual tuning and may vary across hospitals and tasks. We i…
- arXiv cs.AIagentsParallelWorld: Test-Time Scaling for Agentic Embodied Reasoning
arXiv:2608.22971v2 Announce Type: replace Abstract: Embodied AI has emerged as a key paradigm for autonomous systems operating in complex physical environments. While end-to-end models have established strong local capab…
- arXiv cs.AIagentsWhen "Must" Becomes "Maybe": Erosion of Workflow Constraints in LLM Agent Handoffs
arXiv:2608.24569v2 Announce Type: replace Abstract: Large language model (LLM) agents build on one another's work through summaries, plans, and other intermediate artifacts. These records let a downstream agent continue…
- arXiv cs.AIresearchParason: Revealing Subtask and Trial Parallelism in LLM Reasoning
arXiv:2608.24658v2 Announce Type: replace Abstract: Scaling test-time reasoning has substantially improved the problem-solving ability of large language models (LLMs), but standard autoregressive decoding still executes…
- arXiv cs.AIagentsLoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering
arXiv:2608.28281v2 Announce Type: replace Abstract: Loop Engineering is emerging as a practice for organizing development work around coding agents. Instead of writing each prompt by hand, practitioners design loops that…
- arXiv cs.AIagentsRetailAgent: Structured Adverse Timing in Self-Conditioned Multimodal LLM Trading Agents
arXiv:2608.28399v2 Announce Type: replace Abstract: In financial markets, a sequential policy that reacts systematically to price movements may become predictable to other market participants. This paper studies whether…
- arXiv cs.AIagentsComposition without a Host: Carrying the Spatiotemporal-Composability Guarantee of Plugin-Based Agents across Processes
arXiv:2608.28553v4 Announce Type: replace Abstract: Plugin-based agents assemble capabilities at runtime, and the spatiotemporal-composability calculus proves a reversibility guarantee for this assembly. However, the gua…
- arXiv cs.AIresearchFractalNet-Based Heterogeneous Federated Learning for Orbital Edge Intelligence in Satellite Mega-Constellations: A Wildfire Case Study
arXiv:2609.00875v2 Announce Type: replace Abstract: Satellite mega-constellations are emerging as large-scale sensing, communication, and computation fabrics, yet their learning architectures remain largely inherited fro…
- arXiv cs.AIresearchEmoStance: Response-Side Affective-Orientation Control for Empathetic Response Generation via Emoji Weak Supervision
arXiv:2609.02133v2 Announce Type: replace Abstract: Empathetic response generation requires models to decide not only what to say, but also how to respond to the previous speaker's affective situation. We formulate this…
- arXiv cs.AIresearchSTAIR (STructure Aware Information Retriever): A novel dataset and LLM based retriever for document structure augmentation
arXiv:2609.03874v2 Announce Type: replace Abstract: Retrieval Augmented Generation (RAG) is a key component for generating accurate and hallucination free answers using Large Language Models (LLMs). LLMs are improving at…
- arXiv cs.AIresearchStyle Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts
arXiv:2609.08236v2 Announce Type: replace Abstract: Automatic safety judges -- for example Llama Guard, or GPT-4o given a grading prompt -- produce the numbers behind reported jailbreak success rates, defense evaluations…
- arXiv cs.AIagentsDo Agents Know When They Succeed? Calibrating Agent Confidence from Internal Representations
arXiv:2609.09448v2 Announce Type: replace Abstract: As agentic systems getting adopted rapidly in safety critical applications, it is vital to measure the confidence associated with the agentic actions. In comparison to…
- arXiv cs.AIagentsGeoSkill:Experience-Driven Hierarchical Skill Learning with Collaborative Revision forGeospatialAgents
arXiv:2609.13667v2 Announce Type: replace Abstract: Geospatial agents are increasingly expected to support recurring and evolving analytical tasks rather than execute isolated workflows. In such settings, effective agent…
- arXiv cs.AIagentsJaxAHT: A JAX-Based Library for Ad Hoc Teamwork
arXiv:2609.13716v2 Announce Type: replace Abstract: As autonomous agents are increasingly deployed, they must be able to coordinate with previously unseen agents, such as humans. This challenge has been formalized as Ad…
- arXiv cs.AIresearchNeuSE: Neural SE(3)-Equivariant Embedding for Long-Term Object-Based Simultaneous Localization and Mapping
arXiv:2303.07308v3 Announce Type: replace-cross Abstract: We present NeuSE, a novel Neural SE(3)-Equivariant Embedding for objects, and illustrate how it supports object-based Simultaneous Localization and Mapping (SLAM)…
- arXiv cs.AIresearchLLMRec: Benchmarking Large Language Models on Recommendation Task
arXiv:2308.12241v2 Announce Type: replace-cross Abstract: Recently, the fast development of Large Language Models (LLMs) such as ChatGPT has significantly advanced NLP tasks by enhancing the capabilities of conversationa…
- arXiv cs.AIresearchFast Diffusion-GAN Model for Generating Symbolic Music with Emotions
arXiv:2310.14040v2 Announce Type: replace-cross Abstract: Diffusion models have shown promising results for a wide range of generative tasks with continuous data, such as image and audio synthesis. However, little progre…
- arXiv cs.AIresearchOptimal Transport Aggregation for Distributed Mixture-of-Experts
arXiv:2312.09877v3 Announce Type: replace-cross Abstract: This paper considers the setting in which local Mixture-of-experts (MoE) models are fitted independently on distributed datasets and must be combined into a singl…
- arXiv cs.AIresearchFlowWise: Stateful Fast-Slow Model Serving for Streaming Traffic Intelligence
arXiv:2402.03694v3 Announce Type: replace-cross Abstract: Network traffic analysis in cloud and internet service provider (ISP) networks increasingly relies on machine learning (ML) models, as encryption and service cons…
- arXiv cs.AIresearchTeaching MLP More Graph Information: A Three-stage Multitask Knowledge Distillation Framework
arXiv:2403.01079v2 Announce Type: replace-cross Abstract: We study the challenging problem for inference tasks on large-scale graph datasets of Graph Neural Networks: huge time and memory consumption, and try to overcome…
- arXiv cs.AIresearchPrediction Is All MoE Needs: Expert Load Distribution Goes from Fluctuating to Stabilizing
arXiv:2404.16914v2 Announce Type: replace-cross Abstract: MoE facilitates the development of large models by making the computational complexity of the model no longer scale linearly with increasing parameters. The learn…
- arXiv cs.AIresearchGREAT: A Graph Edge Attention Network for the Electric Vehicle Routing Problem with Asymmetric Costs
arXiv:2408.16717v4 Announce Type: replace-cross Abstract: Due to the ongoing electrification of transportation systems, energy-based routing problems such as the Electric Vehicle Routing Problem (EVRP) are becoming incre…
- arXiv cs.AIresearchPolyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation
arXiv:2409.00696v4 Announce Type: replace-cross Abstract: Rating-based human evaluation has become an essential tool to accurately evaluate the impressive performance of large language models (LLMs). However, current rat…
- arXiv cs.AIresearchScale-specific auxiliary multi-task contrastive learning for deep liver vessel segmentation
arXiv:2409.12333v2 Announce Type: replace-cross Abstract: Extracting hepatic vessels from abdominal images is of high interest for clinicians since it allows to divide the liver into functionally-independent Couinaud seg…
- arXiv cs.AIresearchIs Complex Query Answering Really Complex?
arXiv:2410.12537v4 Announce Type: replace-cross Abstract: Complex query answering (CQA) on knowledge graphs (KGs) is gaining momentum as a challenging reasoning task. In this paper, we show that the current benchmarks fo…
- arXiv cs.AIresearchReMAP: Lossless Residual Neural Lifting for Scalable MAP Inference in Arbitrary-Order Markov Random Fields
arXiv:2411.18954v5 Announce Type: replace-cross Abstract: Maximum a posteriori inference in a finite Markov random field is generally NP-hard. We study an instance-wise optimizer that minimizes the exact multilinear ener…
- arXiv cs.AIresearchOpen Foundation Models in Healthcare: Challenges, Paradoxes, and Opportunities with GenAI Driven Personalized Prescription
arXiv:2502.04356v2 Announce Type: replace-cross Abstract: In response to the success of proprietary Large Language Models (LLMs), there is a growing interest in developing open, non-proprietary LLMs and AI foundation mod…
- arXiv cs.AIresearchRandomly Wrong Signals: Bayesian Auction Design with ML Predictions
arXiv:2502.08792v4 Announce Type: replace-cross Abstract: Machine learning can help sellers predict buyers' willingness to pay, but its predictions may be plausible and yet entirely unrelated to a buyer's value. We intro…
- arXiv cs.AIresearchNatural Language Generation from Visual Events: State-of-the-Art and Key Open Questions
arXiv:2502.13034v4 Announce Type: replace-cross Abstract: In recent years, a substantial body of work in visually grounded natural language processing has focused on real-life multimodal scenarios such as describing cont…
- arXiv cs.AIagentsVQEL: Enabling Self-Play in Emergent Language Games via Agent-Internal Vector Quantization
arXiv:2503.04940v3 Announce Type: replace-cross Abstract: Emergent Language (EL) focuses on the emergence of communication among artificial agents. Although symbolic communication channels more closely mirror the discret…
- arXiv cs.AIagentsA Generalist Hanabi Agent
arXiv:2503.14555v2 Announce Type: replace-cross Abstract: Traditional multi-agent reinforcement learning (MARL) systems can develop cooperative strategies through repeated interactions. However, these systems are unable…
- arXiv cs.AIresearchToxicity Is a Property of Communicative Events: A Contextual Stress Measurement Framework for NLP
arXiv:2503.16072v5 Announce Type: replace-cross Abstract: Toxicity detection has become core safety infrastructure for online moderation, dataset filtering, and deployed language-model systems. Yet most detectors still t…
- arXiv cs.AIresearchHorizon Scans can be accelerated using novel information retrieval and artificial intelligence tools
arXiv:2504.01627v2 Announce Type: replace-cross Abstract: Introduction: Horizon scanning in healthcare assesses early signals of innovation, crucial for timely adoption. Current horizon scanning faces challenges in effic…
- arXiv cs.AIresearchSAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs
arXiv:2504.08192v3 Announce Type: replace-cross Abstract: Machine unlearning is a promising approach to improve LLM safety by removing unwanted knowledge from the model. However, prevailing gradient-based unlearning meth…
- arXiv cs.AIresearchFPGA-Based Neural Network Accelerators for Space Applications: A Survey
arXiv:2504.16173v4 Announce Type: replace-cross Abstract: Space missions are becoming increasingly ambitious, necessitating high-performance onboard spacecraft computing systems. In response, field-programmable gate arra…
- arXiv cs.AIresearchA Comprehensive Review on RNA Subcellular Localization Prediction
arXiv:2504.17162v2 Announce Type: replace-cross Abstract: The subcellular localization of RNAs, including long non-coding RNAs (lncRNAs), messenger RNAs (mRNAs), microRNAs (miRNAs) and other smaller RNAs, plays a critica…
- arXiv cs.AIresearchGraph Neural Network-Based Reinforcement Learning for Controlling Biological Networks - the GATTACA Framework
arXiv:2505.02712v4 Announce Type: replace-cross Abstract: Cellular reprogramming, the artificial transformation of one cell type into another, has been attracting increasing research attention due to its therapeutic pote…
- arXiv cs.AIresearchTowards Understanding Deep Learning Model in Image Recognition via Coverage Test
arXiv:2505.08814v4 Announce Type: replace-cross Abstract: Deep neural networks (DNNs) play a crucial role in the field of artificial intelligence, and their security-related testing has been a prominent research focus. B…
- arXiv cs.AIagentsGenerative AI for Autonomous Driving: A Review
arXiv:2505.15863v2 Announce Type: replace-cross Abstract: Generative AI (GenAI) is rapidly advancing the field of Autonomous Driving (AD), extending beyond traditional applications in text, image, and video generation. W…