AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchCross-Modal Emotion Understanding: A Transformer-GAT Approach for Dialogue Emotion Recognition
arXiv:2609.29556v2 Announce Type: replace Abstract: Multimodal emotion recognition is a key research area in affective computing, with applications in sentiment analysis, intelligent customer service, and human-computer…
- arXiv cs.AIresearchIs Reasoning Always Useful? Rethinking Reasoning Utility in Universal Multimodal Embeddings
arXiv:2609.29560v1 Announce Type: new Abstract: Reasoning-enhanced universal multimodal embeddings (UME) improve heterogeneous retrieval, but plausible rationales do not necessarily produce discriminative rankings. We st…
- arXiv cs.AIagentsPartHackBench: Certified Equal-Progress Stress Tests for Partial-Credit Tool-Agent Evaluation
arXiv:2609.29578v1 Announce Type: new Abstract: Long-horizon tool agents often make useful progress without reaching terminal success, motivating partial-credit evaluation. Yet evaluators may reward milestones that were…
- arXiv cs.AIresearchSequential knowledge editing breaks a model's ability to tell good evidence from bad, without costing it accuracy
arXiv:2609.29587v1 Announce Type: new Abstract: Knowledge editing is evaluated on whether the edited fact changed, whether paraphrases follow, and whether unrelated answers stayed put. A model can pass all three and stil…
- arXiv cs.AIresearchPEEL: Physics-Enabled Evidential Learning for Identifiable Uncertainty in CT Imaging
arXiv:2609.29599v1 Announce Type: new Abstract: Normal-inverse-gamma (NIG) regression is not uniquely identifiable from its marginal Student-t likelihood: the likelihood determines three combinations of four NIG paramete…
- arXiv cs.AIresearchiCoder-27B: Recursive AI-Led Development of Frontier Industrial Coding Model
arXiv:2609.29626v1 Announce Type: new Abstract: Recursive AI, the prospect of AI taking an increasingly complete role in building and improving AI, is a crown jewel of AI for AI. Although recursive self-development has b…
- arXiv cs.AIagentsIngest-Time Fact Compilation for Cost-Efficient and Reliable Question Answering over Revised Corpora
arXiv:2609.29661v1 Announce Type: new Abstract: Most agentic question answering (QA) systems do an important part of their semantic work at the worst possible time: every time someone asks a question. When a corpus conta…
- arXiv cs.AIresearchTo Think or Not to Think: Allocating Reasoning Where It Helps
arXiv:2609.29664v1 Announce Type: new Abstract: Reinforcement learning (RL) has proven effective in enhancing the reasoning performance of large language models (LLMs), particularly in complex mathematical and programmin…
- arXiv cs.AIresearchFair Like Us? Auditing LLM Alignment in Resource Allocation
arXiv:2609.29692v1 Announce Type: new Abstract: Fair allocation of scarce, indivisible resources is an important challenge in many societal problems. While there are several formal theories of fairness, no single definit…
- arXiv cs.AIresearchA General Framework for Budgeted Threshold Incentives on Request
arXiv:2609.29724v1 Announce Type: new Abstract: On-demand delivery platforms pay riders through incentive activities whose tiers are set from recent completions of riders with a similar history. Operators request such pl…
- arXiv cs.AIresearchThe Gold in Bias: Maturing the AI Design Process through Verification
arXiv:2609.29730v1 Announce Type: new Abstract: Bias in AI systems is typically framed as a flaw to be minimized, yet it also serves as a critical indicator of underlying weaknesses in data, modeling assumptions, and sys…
- arXiv cs.AIresearchC3M: Cross-Session Multimodal Memory Maintenance for Long-Horizon Tasks
arXiv:2609.29735v1 Announce Type: new Abstract: Long-horizon tasks require preserving and later recovering cross-session evidence under a bounded, query-blind memory budget. Existing compression can discard fine-grained…
- arXiv cs.AIresearchAI-based detection of worsening heart failure from low-resolution telemonitoring data
arXiv:2609.29742v1 Announce Type: new Abstract: Objective: Heart failure (HF) presents a healthcare challenge due to its high comorbidity burden, aging patient population and frequent hospitalizations. Remote monitoring…
- arXiv cs.AIagentsBreaking the Environment Wall: A Unified Framework for Preparing and Evolving Agent-Native Environments
arXiv:2609.29773v2 Announce Type: replace Abstract: Many real-world tasks (e.g., office workflows, scientific experimentation) require LLM agents to interact repeatedly with their environments for context-dependent opera…
- arXiv cs.AIresearchHallucination Neurons and Where to Find Them: An Investigation into the existence of Hallucination Neurons
arXiv:2609.29781v1 Announce Type: new Abstract: Interpretable machine learning for Large Language Models (LLMs) increasingly relies on sparse probing methods that identify small sets of neurons claimed to detect and caus…
- arXiv cs.AIresearchLearning to Ideate for Scientific Impact
arXiv:2609.29802v1 Announce Type: new Abstract: Scientific ideation is increasingly mediated by large language models, but current ideation systems are usually trained and evaluated on immediately judgeable proxies such…
- arXiv cs.AIresearchDecoding Imagined Speech: A Strictly Subject-Independent Approach Using EEG
arXiv:2609.29820v1 Announce Type: new Abstract: Imagined speech decoding from electroencephalography (EEG) has gained increasing attention as a potential communication pathway for individuals with severe motor impairment…
- arXiv cs.AIagentsPUBG Ally: A Conversational Embodied Agent as an AI Teammate
arXiv:2609.29837v2 Announce Type: replace Abstract: We introduce PUBG Ally, an embodied agent for PUBG: BATTLEGROUNDS that can reason, act autonomously, and play alongside players as a voice-enabled teammate. Building su…
- arXiv cs.AIresearchA Risk-Adaptive and Evidence-Constrained Framework for Generative AI Feedback in Programming Education
arXiv:2609.29874v1 Announce Type: new Abstract: Generative artificial intelligence can turn learning analytics into personalized support, but feedback systems must decide when to intervene, which evidence to use, and how…
- arXiv cs.AIagentsWhen Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression
arXiv:2609.29875v1 Announce Type: new Abstract: Long horizon language model agents continually accumulate reasoning history, increasing context length and inference cost even after earlier decisions have been executed an…
- arXiv cs.AIresearchOntology-Mediated Neurosymbolic Constraint Acquisition from Multiple Stakeholders
arXiv:2609.29876v1 Announce Type: new Abstract: Neurosymbolic research typically assumes a pre-existing symbolic specification, leaving the upstream challenge of acquiring and formalizing requirements and constraints lar…
- arXiv cs.AIagentsQwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents
arXiv:2609.29892v1 Announce Type: new Abstract: The rapid progression of large language models is extending AI from passive content generation into the active workflows of engineering and scientific discovery. This shift…
- arXiv cs.AIagentsWho Holds the Pen? Let Specifications, Not Agents, Sign Off
arXiv:2609.29921v1 Announce Type: new Abstract: Large language model agents increasingly combine generation, decision-making, execution, and self-evaluation within a single agentic loop. Although they operate under exter…
- arXiv cs.AIresearchNeuro-symbolic AI for Industrial Configuration
arXiv:2609.29947v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown impressive performance on a wide range of generative tasks. Yet their probabilistic nature makes them, in isolation, fundamentally u…
- arXiv cs.AIresearchENDOPROMPT: Victim-Side Pseudo-References for Utility Degradation
arXiv:2609.29948v1 Announce Type: new Abstract: Prompt injection can degrade benign task performance without eliciting harmful content. Yet many attack objectives depend on task labels or predefined target responses. We…
- arXiv cs.AIresearchAugur: A Synthetic Decision Lab for Rehearsing Reactions to Product and Policy Changes
arXiv:2609.29952v1 Announce Type: new Abstract: Before a product or policy change ships, the question that matters is how people will react to it. Augur rehearses that reaction offline: it builds a typed knowledge graph…
- arXiv cs.AIagentsAdvancing Model Research in AgentX: Long-Horizon Autonomy for Industrial Recommender Systems
arXiv:2609.30001v1 Announce Type: new Abstract: Sustaining industrial recommendation research requires using the results of one experiment to decide what to investigate next. We present AgentX-Model, the next generation…
- arXiv cs.AIagentsSynthetic Hospital: An Open, Verifiable, Physician-Validated Longitudinal EHR Benchmark
arXiv:2609.30027v2 Announce Type: replace Abstract: Frontier language models are rarely used in clinical workflows because the realistic, longitudinal benchmarks needed to develop them are scarce. Real electronic health…
- arXiv cs.AIagentsHow does Adversarial Influence Scale in Multi-Agent Systems?
arXiv:2609.30028v2 Announce Type: replace Abstract: Multi-agent deliberation can improve performance, but what happens when some agents do not act in good faith? In practice, an agent may be deceptive and work to subvert…
- arXiv cs.AIresearchStyle, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Models
arXiv:2609.30048v1 Announce Type: new Abstract: If a language model can recognize code it wrote, it may favor that code as a judge, and instances of one model monitoring each other could collude. We test this zero-shot o…
- arXiv cs.AIresearchNNV3: Expanding Neural Network Verification to New Architectures and Domains
arXiv:2609.30050v1 Announce Type: new Abstract: We present NNV3, the latest version of the Neural Network Verification (NNV) tool, a MATLAB framework for formal verification of deep learning models and learning-enabled c…
- arXiv cs.AIresearchSciWalker: Synthesizing Scientific Coding Problems with Operator Graphs and Execution Feedback
arXiv:2609.30054v1 Announce Type: new Abstract: Improving the scientific coding capabilities of large language models (LLMs) requires high-quality training data. However, such data remain scarce because manually authorin…
- arXiv cs.AIresearchSelf-Play Pretraining with Zero Data
arXiv:2609.30063v1 Announce Type: new Abstract: Advances in language modeling have been driven by scaling pretraining on ever more data. Yet, the training data is still largely curated on the model's behalf. A more gener…
- arXiv cs.AIagentsPrivDrift: Auditing User-Secret Leakage Under Topic Drift in Active LLM Conversations
arXiv:2609.30094v2 Announce Type: replace Abstract: Large language models increasingly operate as persistent assistants in user-facing, shared-session, and tool-augmented settings. When users disclose sensitive informati…
- arXiv cs.AIagentsHEXIS: Compiling Agent Skills into Extended Finite State Machines
arXiv:2609.30123v2 Announce Type: replace Abstract: Agent skills provide instructions and reusable knowledge, yet agents have to frequently infer which action to take next. This skill's execution paradigm combines task r…
- arXiv cs.AIagentsScreen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scale
arXiv:2609.30137v1 Announce Type: new Abstract: Customer experience (CX) agents use tools and large language models to address customer requests and guide conversational interactions with an organization's products. Impr…
- arXiv cs.AIresearchEnigmaForge: The Question Is Hidden in the Story
arXiv:2609.30144v1 Announce Type: new Abstract: Most benchmarks hand the model a question. EnigmaForge hands it a stack of old documents and no question at all. Buried in the letters, receipts, and logbook margins is a s…
- arXiv cs.AIagentsGRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI
arXiv:2609.30147v1 Announce Type: new Abstract: Large Language Models (LLMs) typically exhibit a performance profile where reliability degrades as task complexity increases. We address the challenge of generating high-qu…
- arXiv cs.AIresearchSearch-Aware Reinforcement Learning for Multi-Component Query Understanding in Roblox Game Search
arXiv:2609.30177v2 Announce Type: replace Abstract: Query understanding (QU) in production search systems has typically relied on separate models for each subtask, such as search intent classification, attribute extracti…
- arXiv cs.AIagentsJev-Mobile: Jev as an Executor for Mobile GUI Agents
arXiv:2609.30186v1 Announce Type: new Abstract: Vision-language models (VLMs) have become a common foundation for autonomous mobile GUI agents, but most existing systems rely on the VLM for both planning and action groun…
- arXiv cs.AIresearchSAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance
arXiv:2609.30192v1 Announce Type: new Abstract: Long-horizon reasoning remains a central challenge for large language models (LLMs) under sparse-reward regimes. We argue that this brittleness arises from two biases induc…
- arXiv cs.AIresearchExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds
arXiv:2609.30199v2 Announce Type: replace Abstract: Scientific discovery begins where known problems end. There, AI systems must engage in exploration: framing hypotheses, designing experiments, and iterating on the resu…
- arXiv cs.AIagentsA Living Benchmark for Information Retrieval from Electronic Health Records
arXiv:2609.30205v2 Announce Type: replace Abstract: Large language model (LLM)-based clinical assistants are increasingly being integrated into electronic health record (EHR) systems, transforming how clinicians retrieve…
- arXiv cs.AIresearchAD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control
arXiv:2609.30264v2 Announce Type: replace Abstract: Latent world models are typically trained to predict factual transitions, whereas model predictive control (MPC) must compare alternative actions from the same state. A…
- arXiv cs.AIresearchCaliPPer: quantifying, predicting and improving AI model performance for binding prediction
arXiv:2606.07258v1 Announce Type: cross Abstract: Binding prediction models accelerate therapeutic antibody and TCR discovery, but their performance on new datasets is unpredictable, often leading to low discovery rates.…
- arXiv cs.AIresearchHybrid Variational Quantum-Classical Framework with Adaptive Weighting and Efficiency Assessment
arXiv:2609.28491v1 Announce Type: cross Abstract: Hybrid quantum-classical neural networks have emerged as a promising approach for leveraging quantum computing in machine learning while mitigating current hardware limit…
- arXiv cs.AIresearchAI in Science: Early Insights
arXiv:2609.28504v2 Announce Type: replace-cross Abstract: Scientific progress is a key driver of economic growth and prosperity. There is great excitement - but also concerns - about the impacts of AI on science, but so…
- arXiv cs.AIagentsCertified Task-Conditioned Active Observability
arXiv:2609.28520v1 Announce Type: cross Abstract: Before acting upon an unobservable physical system, an autonomous agent must determine which latent distinctions govern downstream tasks, how many active interventions ar…
- arXiv cs.AIresearchCrossScale-GLIO: Topology-Preserving Vision-Language Alignment of MRI and Whole-Slide Histopathology for Diffuse Glioma
arXiv:2609.28524v1 Announce Type: cross Abstract: Magnetic resonance imaging and histopathology observe the same glioma at radically different scales. We present CrossScale-GLIO, a visual multimodal framework that repres…
- arXiv cs.AIresearchSMILESGNN: Interpretable Clinical Toxicity Prediction via SMILES-Graph Cross-Attention Fusion
arXiv:2609.28553v1 Announce Type: cross Abstract: Drug toxicity prediction is critical for reducing late-stage attrition in drug discovery, yet remains challenging due to severe class imbalance, scaffold-based generaliza…