AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchCommonsense-Grounded Path Planning from Abstract Instructions
arXiv:2609.22813v1 Announce Type: cross Abstract: We present \emph{commonsense ranked search} (CoRS), a novel path planner that turns an abstract instruction into a route that follows commonsense. While existing methods…
- arXiv cs.AIagentsThe Price of Safety: Benign-Case Utility and Token Overhead of Memory-Poisoning Defenses in LLM Agents
arXiv:2609.22818v2 Announce Type: replace-cross Abstract: Memory-poisoning defenses for LLM agents are typically evaluated by how well they stop attacks, even though almost all traffic they encounter is benign. We measur…
- arXiv cs.AIresearchSatOV: Restoring Spatial Priors for Training-Free Open-Vocabulary Segmentation in Remote Sensing Imagery
arXiv:2609.22834v1 Announce Type: cross Abstract: Open-vocabulary semantic segmentation (OVS) of remote sensing imagery is a challenging pixel-level task requiring strong generalization and adaptation to the spatial char…
- arXiv cs.AIresearchSame Outcome, Different Readout: What Does a Steerable Valence Direction in LLMs Represent?
arXiv:2609.22850v4 Announce Type: replace-cross Abstract: Claims about what an internal direction in an LLM represents need evidential constraints beyond an observer's prior beliefs about the system. Decodability and suc…
- arXiv cs.AIresearchDiscrete vs. Continuous: A Comprehensive Study of Unified Audio Understanding in LALMs
arXiv:2609.22851v2 Announce Type: replace-cross Abstract: Large Audio Language Models (LALMs) utilize either continuous features or discrete tokens, yet the optimal representation paradigm for general audio understanding…
- arXiv cs.AIagentsPlanning-Aligned Pretraining of BEV Representations with Sparse Action-Conditioned Targets for End-to-End Autonomous Driving
arXiv:2609.22868v1 Announce Type: cross Abstract: End-to-end driving requires planning-relevant bird's-eye-view (BEV) representations, but existing pretraining approaches often rely on task annotations or dense scene rec…
- arXiv cs.AIresearchThe Moral Check: Strategic AI Governance for the Pacing Problem
arXiv:2609.22869v1 Announce Type: cross Abstract: Technology cannot steer itself. Strategy provides that steering, establishing the rule that purpose and judgment must precede compute capital. As the frontier artificial…
- arXiv cs.AIagentsTowards Full Pipeline FP8 Reinforcement Learning for LLMs
arXiv:2609.22870v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a key technique for improving the reasoning and agentic abilities of large language models (LLMs). Although FP8 quantization can ac…
- arXiv cs.AIresearchPer-Query Gating of LLM Rerankers for Multi-Hop Retrieval
arXiv:2609.22880v1 Announce Type: cross Abstract: LLM rerankers add of the order of \$0.2-0.3 per 1,000 queries and about a second of tail latency on top of a graph-augmented dense pipeline such as HippoRAG2, and on thre…
- arXiv cs.AIagentsThe Law of Stop: Interruptibility, Injunctions, and the Governance of Agentic AI
arXiv:2609.22882v2 Announce Type: replace-cross Abstract: On June 12, 2026, the U.S. government ordered Anthropic to bar foreign nationals from two of its most capable models. Unable to sort users by nationality, it with…
- arXiv cs.AIresearchBlock-Sparse Attention with Semantic-Geometric Decoupled Routing
arXiv:2609.22884v1 Announce Type: cross Abstract: Long-context inference has become a defining capability of large language models, but exact dense attention remains costly due to its quadratic scaling with sequence leng…
- arXiv cs.AIresearchMerge++: Universal Merge Refinement Through Data-Free Checkpoint Inversion
arXiv:2609.22886v1 Announce Type: cross Abstract: Model merging consolidates fine-tuned experts into one multi-task model without retraining. All existing data-free methods approach this problem entirely in weight space.…
- arXiv cs.AIresearchAre Coreset Selection Methods Worth Their Cost?
arXiv:2609.22894v2 Announce Type: replace-cross Abstract: Coreset selection picks a representative subset of the labeled training set to make training cheaper. However, it is usually evaluated by downstream accuracy at a…
- arXiv cs.AIresearchAVTR-1: Open Stack for Real-Time Interactive Avatars
arXiv:2609.22913v1 Announce Type: cross Abstract: Talking-head and dyadic models now achieve real-time inference, yet fast motion generation alone does not produce an interactive conversation. A live system must synchron…
- arXiv cs.AIagentsAn Iterative LangGraph Agent for Text-to-SQL: Natural Language Access to the Chicago Crime Database
arXiv:2609.22917v2 Announce Type: replace-cross Abstract: Non-technical stakeholders frequently cannot write the SQL needed to extract insights from operational databases. We built and evaluated a Text-to-SQL agent that…
- arXiv cs.AIresearchMeasuring Behavioural Signatures of Large Language Models through Psychometric Profiling
arXiv:2609.22934v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly mediate human decisions and communication, yet their behavioural regularities remain difficult to characterize systematically. W…
- arXiv cs.AIagentsAn Evolutionary Agentic Approach for Open-ended Image Quality Perception
arXiv:2609.22942v1 Announce Type: cross Abstract: Generative models are rapidly expanding image quality assessment (IQA) beyond traditional fidelity factors to emerging dimensions such as physical plausibility and text-r…
- arXiv cs.AIagentsNostrAgent: A Decentralized Identity and Delegation Architecture for Sovereign Agentic Systems
arXiv:2609.22944v1 Announce Type: cross Abstract: Autonomous AI agents increasingly act across organizational boundaries on behalf of human operators: they invoke third-party services, delegate subtasks to other agents,…
- arXiv cs.AIresearchRewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling
arXiv:2609.22947v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) is vital for optimizing video generation models, with a robust reward model (RM) serving as the cornerstone. However, existing video r…
- arXiv cs.AIagentsBeyond Single-Model Injection: A Threat Model and Defense Architecture for Prompt Injection in Multi-Agent Systems
arXiv:2609.22949v1 Announce Type: cross Abstract: Existing prompt injection research focuses on single-model chatbot scenarios, where an attacker manipulates one LLM through crafted input. Multi-agent systems amplify thi…
- arXiv cs.AIagentsWhen Agentic Trust Crosses Organizational Boundaries: Structural Externalization and a Reference Model for Trust Evidence
arXiv:2609.22961v1 Announce Type: cross Abstract: Agentic systems increasingly invoke tools, services, data, and other agents across organizational boundaries, yet a relying party cannot assess a delegated action solely…
- arXiv cs.AIagentsGeneral Collaborative Intelligence: Architecting Cognition for Resilient Multi-Agent Ecosystems
arXiv:2609.22967v1 Announce Type: cross Abstract: Multi-agent unmanned systems are moving from isolated, ego-centric sensing toward collaborative intelligence, in which distributed agents exchange compact features to ove…
- arXiv cs.AIagentsAutomatic multimodal UX improvement recommendations from LLM agent user simulations
arXiv:2609.22971v1 Announce Type: cross Abstract: Evaluating user experience (UX) on live websites through user testing is expensive, subjective, and difficult to scale. LLM agents offer a promising route to automating U…
- arXiv cs.AIresearchA Horizon-slicing Approach to Minimum Obstacle Displacement Planning for Robot Navigation
arXiv:2609.22974v1 Announce Type: cross Abstract: In this paper, we investigate the Minimum Obstacle Displacement Planning problem from a robot motion planning perspective. The problem involves determining a feasible pat…
- arXiv cs.AIresearchDual-Locking Learned AI Models: A PIN-Based Sparse QIM Watermarking and Adaptive Index Permutation Approach
arXiv:2609.22981v1 Announce Type: cross Abstract: We present a dual-locking method for securing trained neural networks that combines key-driven index permutation with PIN-based watermarking based on Sparse Quantization…
- arXiv cs.AIresearchInterpretable Multi-Hypersphere Deep Anomaly Detection for Open-set Supervised Anomaly Detection
arXiv:2609.23008v1 Announce Type: cross Abstract: Multi-class open-set anomaly detection requires a model to characterize the normal acceptance domain formed by multiple heterogeneous subdistributions using only class-la…
- arXiv cs.AIresearchWatching Quantum Models Think: Hilbert-Space Interpretability in Quantum Transformer Blocks
arXiv:2609.23016v1 Announce Type: cross Abstract: Deep learning models are powerful but opaque. As quantum machine learning matures, the field faces a defining choice: build quantum models that are equally opaque, or exp…
- arXiv cs.AIagentsAuditing Political Alignment in LLM Assistants: Engagement, Stance, and User Identity
arXiv:2609.23039v1 Announce Type: cross Abstract: LLM-based AI systems answer political questions for hundreds of millions of people. Current audits measure what they say to an average user, but their behavior is dynamic…
- arXiv cs.AIresearchFrom Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness
arXiv:2609.23065v3 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) can sound plausible yet be unfaithful to the model's underlying reasoning. Most prior work probes CoT faithfulness through input--output be…
- arXiv cs.AIresearchMolSC: Leveraging Substituent Contributions to Enhance Fine-grained Molecular Understanding in LLMs
arXiv:2609.23073v1 Announce Type: cross Abstract: Recent advances in natural language processing have led to molecular Large Language Models (LLMs) with strong performance across diverse chemistry tasks. However, they st…
- arXiv cs.AIresearchNeural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone
arXiv:2609.23087v1 Announce Type: cross Abstract: Modern Transformer design and compression both reduce to allocating capacity under a budget. The standard scalars for these decisions, #Params and #FLOPs, capture size an…
- arXiv cs.AIagentsDiagGen: Agentic Generation of Deformable Assets with Sim-based Diagnostics for Robotic Simulation
arXiv:2609.23103v1 Announce Type: cross Abstract: While simulation-ready deformable assets are essential for in-silico robotic manipulation tasks, existing generation frameworks typically assess physical plausibility aft…
- arXiv cs.AIresearchWhitening Inverts the Hierarchy: What the Norm of a Whitened Embedding Measures
arXiv:2609.23117v1 Announce Type: cross Abstract: Whitening a foundation-model embedding and using its squared norm as a training-free likelihood surrogate is motivated by the observation that whitened coordinates often…
- arXiv cs.AIagentsMM-ContextFold: Context Folding for Multimodal Agentic Retrieval
arXiv:2609.23121v2 Announce Type: replace-cross Abstract: Multimodal Agentic Retrieval (MAR) requires agents to solve complex information-seeking tasks by iteratively invoking external tools. Typical frameworks such as R…
- arXiv cs.AIresearchQwenVLConnector: A Fast, Unified Medical VLM Chatbot for Fine-Grained Clinical Perception and Text Generation
arXiv:2609.23139v1 Announce Type: cross Abstract: Most medical vision-language models (VLMs) excel at open-ended report generation and VQA but provide limited support for structured, fine-grained clinical perception with…
- arXiv cs.AIresearchBearings: Self-Supervised Soundfield Embeddings from First-Order Ambisonics
arXiv:2609.23152v1 Announce Type: cross Abstract: Recently proposed self-supervised audio encoders learn powerful general-purpose representations of sound scenes, yet they are spatially blind. To supply the missing spati…
- arXiv cs.AIresearchEquiSELD: Efficient training of equivariant sound event localization and detection networks
arXiv:2609.23156v1 Announce Type: cross Abstract: First-order Ambisonics (FOA) signals exhibit exact O(3) symmetry: The rotation or reflection of the FOA signal modifies the direction of arrival of the sound sources, whi…
- arXiv cs.AIresearchGrapeSplat: Geometry-Grounded Reconstruction via Amalgamated Pose-Free Encoding for Feed-Forward 3D Gaussian Splatting
arXiv:2609.23182v1 Announce Type: cross Abstract: Feed-forward 3D Gaussian Splatting now reconstructs renderable scenes from unposed, uncalibrated images. Yet, most models supervise only photometric consistency and predi…
- arXiv cs.AIagentsLLMs as Linguistic Chameleons: Decoupling Semantics and Structure for Privacy-Preserving Communication
arXiv:2609.23193v1 Announce Type: cross Abstract: As Large Language Model (LLM) APIs become increasingly integrated into privacy-sensitive workflows, ensuring inference-time privacy without compromising task utility rema…
- arXiv cs.AIagentsTriggers and Diagnostics for LLM-Based Interpretability Failures in Active Inference Agents
arXiv:2609.23215v1 Announce Type: cross Abstract: LLM explainers are increasingly attached to autonomous agents as runtime oversight, with operators reading a generated account of the agent's beliefs and actions rather t…
- arXiv cs.AIresearchWhy Ghost Outputs Teach: A Kernel-Based Understanding of Subliminal Learning
arXiv:2609.23260v1 Announce Type: cross Abstract: Subliminal Learning (SL) is a recently identified phenomenon in which a student model acquires downstream task capabilities by matching seemingly unrelated auxiliary outp…
- arXiv cs.AIresearchKnowing When to Trust Images: Reliability-Aware Multi-modal Entity Alignment
arXiv:2609.23267v1 Announce Type: cross Abstract: The visual modality, i.e., images, plays a key role in multi-modal entity alignment (MMEA). Existing approaches often directly fuse the image with other modalities to ali…
- arXiv cs.AIagentsSemantic Candidate-Job Matching: A Comparative Evaluation of Dense Embedding Models in Hybrid Retrieval
arXiv:2609.23307v1 Announce Type: cross Abstract: This paper presents a comparative evaluation of dense embedding models for semantic candidate-job matching in high-volume staffing workflows. Incoming job descriptions ar…
- arXiv cs.AIresearchValueDiff: Value-Geometric KV Cache Eviction for Sink-Suppressed LLMs
arXiv:2609.23314v2 Announce Type: replace-cross Abstract: Modern LLMs with QK-normalization, gated attention, learned attention sinks, or logit softcapping exhibit weaker persistent attention sinks, on which existing KV…
- arXiv cs.AIagentsGraph Memory for LLM Agents: At What Cost? A Comparative Evaluation of Query, Ingest, and Update Performance Across Graph Database Engines
arXiv:2609.23315v1 Announce Type: cross Abstract: Graph databases are frequently positioned as categorically necessary for connected-data workloads, yet the systems dimension along which they actually differ - query plan…
- arXiv cs.AIresearchCo-occurrence Patterns of LoRA Adapters in Production Diffusion Model Inference Services
arXiv:2609.23321v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) has become a key technology for serving large-scale personalized large language models and diffusion models in the cloud. However, the co-occur…
- arXiv cs.AIresearchA Patient World Model for Early Forecasting of Digital Health Campaign Outcomes: Capabilities and Limits
arXiv:2609.23333v1 Announce Type: cross Abstract: Digital direct-to-consumer (DTC) health campaigns are usually measured after the fact. In-flight forecasting commonly relies on a separate classifier for every cutoff and…
- arXiv cs.AIagentsHuman-guided physics-constrained AI agents construct an auditable model of soil-plug evolution
arXiv:2609.23360v1 Announce Type: cross Abstract: Engineering predictions require physical mechanisms to be translated consistently into equations, discretization, code, and validation, yet errors can propagate despite l…
- arXiv cs.AIresearchDiscovering Physical Representation Languages
arXiv:2609.23381v1 Announce Type: cross Abstract: Before a machine can discover a physical law, it must discover what its measurements are: which observations live on cells, which are intensive or extensive, which sector…
- arXiv cs.AIresearchBayesian Filtering in Physical Systems via Test-time Trained Flow Matching
arXiv:2609.23383v1 Announce Type: cross Abstract: Bayesian filtering provides a principled framework for online state estimation under uncertainty, yet its application to systems with high-dimensional states and complica…