AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchLess Uniform Discrete Diffusion is More Powerful and Scalable
arXiv:2609.35817v1 Announce Type: cross Abstract: Although uniform diffusion language models (UDLMs) represent a promising diffusion paradigm, scaling them remains challenging. We identify the core obstacle as an over-un…
- arXiv cs.AIagents$\tau$-Multilingual: Benchmarking Voice Agents Across Languages
arXiv:2609.35820v1 Announce Type: cross Abstract: English-only benchmarks expose only a narrow slice of voice-agent behavior. We introduce $\tau$-Multilingual, extending $\tau$-Voice to Spanish, Brazilian Portuguese, Hin…
- arXiv cs.AIresearchWhen Should LLMs Trust Their Own Revisions? A Risk-Aware Study of Intrinsic Self-Correction
arXiv:2609.35832v1 Announce Type: cross Abstract: Intrinsic self-correction asks a language model to revise its own answer without receiving new external evidence. A second pass can recover mistakes, but it can also over…
- arXiv cs.AIresearchEstimation of Room Impulse Responses from Handclaps
arXiv:2609.35839v1 Announce Type: cross Abstract: Handclaps provide an equipment-free excitation for room acoustics, but their unknown and variable source waveform makes room impulse response (RIR) estimation challenging…
- arXiv cs.AIresearchBeyond Rule-Based Mutation Testing: Test-Aware Mutant Generation Using Large Language Models
arXiv:2609.35841v1 Announce Type: cross Abstract: Mutation testing evaluates test-suite adequacy by injecting synthetic faults into program code. However, traditional rule-based tools often generate large numbers of triv…
- arXiv cs.AIresearchPosition: Let's Strengthen Verifiability If We Can't Enforce Reproducibility
arXiv:2609.35854v1 Announce Type: cross Abstract: In the field of Machine Learning, many papers contain empirical results supporting claimed statements or illustrating the performance of a proposed method. However, most…
- arXiv cs.AIresearchMara Chain: Rethinking Failure as a Stepping Stone for AI System Auto-Evolution
arXiv:2609.35855v1 Announce Type: cross Abstract: Optimizing deployed AI systems increasingly amounts to editing prompts, skills, harnesses, and code rather than model weights. Existing approaches commonly optimize these…
- arXiv cs.AIresearchBeyond Keywords: Leveraging Generative LLMs and Label Aggregation to Classify Economic Policy Uncertainty in News Articles
arXiv:2609.35856v1 Announce Type: cross Abstract: This research describes the adaptation of Large Language Models (LLMs) for economic monitoring in the public sector to automatically determine whether an article discusse…
- arXiv cs.AIresearchThe Detectability Gap: Hidden Heterogeneity in Hallucination Detection Across Language Models
arXiv:2609.35860v1 Announce Type: cross Abstract: Sampling based consistency is widely used for hallucination detection, yet aggregate performance can conceal systematic differences in which errors are detectable. This w…
- arXiv cs.AIresearchPACT: Pairwise-Anchored Calibrated Tuning for Single-Token Typed Decisions
arXiv:2609.35865v1 Announce Type: cross Abstract: Single-token typed-decision models answer a schema question by reading the logits of a few one-letter answer codes at a single position: they are fast and return a probab…
- arXiv cs.AIresearchCruxBench: A Benchmark of Information Discovery
arXiv:2609.35879v1 Announce Type: cross Abstract: Benchmarks for large language models (LLMs) typically evaluate the accuracy of answers against fixed reference labels. But a central step in many complex real-world tasks…
- arXiv cs.AIagentsAgentic Commerce Bench: Measuring Fraud Detection for Agents That Spend Money
arXiv:2609.35886v1 Announce Type: cross Abstract: AI agents now hold spend authority and settle payments without per-action human confirmation. The resulting loss is often not a security failure: a counterparty with the…
- arXiv cs.AIagentsSINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents
arXiv:2609.35889v1 Announce Type: cross Abstract: Tool-using language-model agents select and execute third-party artifacts. Different implementations can return the requested output while producing hidden execution effe…
- arXiv cs.AIagentsReconstructing Implicit Scientific Knowledge: Evaluating LLM Agents through End-to-End Reproduction of Astronomy
arXiv:2609.35900v1 Announce Type: cross Abstract: The integration of large language models (LLMs) into scientific workflows is accelerating, yet their ability to reconstruct the reasoning underlying published research re…
- arXiv cs.AIresearchSimilarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning
arXiv:2609.35908v1 Announce Type: cross Abstract: Semantic caches reduce LLM serving costs by reusing previously generated answers for semantically similar queries. However, retrieval is based solely on embedding similar…
- arXiv cs.AIagentsCheap to Hypothesize, Costly to Verify: The Defense Surface of Agentic Vulnerability Discovery
arXiv:2609.35909v4 Announce Type: replace-cross Abstract: Autonomous LLM agents turn vulnerability discovery into a repository-scale search: they generate many vulnerability hypotheses but can verify only a subset under…
- arXiv cs.AIagentsLearn Now, Use Next, Trust Later: Prequential Test-Time Learning for LLM Agents
arXiv:2609.35911v1 Announce Type: cross Abstract: Adapting large language model agents during deployment requires not only retaining past experience, but also turning new observations into timely guidance. Many test-time…
- arXiv cs.AIagentsMMSkillRisk: Can Agents Stay Safe When Multimodal Skills Become Traps?
arXiv:2609.35912v1 Announce Type: cross Abstract: Agent skills are shareable packages of procedural instructions, tools, and examples. Multimodal skills additionally include visual references that agents retrieve and ins…
- arXiv cs.AIresearchUNBIND: UNlearning By INference-time Directional Steering for Code LLMs
arXiv:2609.35913v1 Announce Type: cross Abstract: Code large language models acquire programming capabilities from large code corpora, but can also memorize implementations that later require removal. Code unlearning is…
- arXiv cs.AIagentsEvaluating Name-Only Directory Routing for One-Shot Code Search
arXiv:2609.35918v1 Announce Type: cross Abstract: Finding the right files is an early challenge for coding agents. We test whether a language model can follow directory and file names to find annotated code files missed…
- arXiv cs.AIagentsAlmost Human, Except When It Matters: VoxParity and the Decisions a Voice Should Change
arXiv:2609.35922v1 Announce Type: cross Abstract: A voice agent can handle almost every call on the words alone and still fail the few its sector's rules were written for. Emergency-call standards, fraud guidance, radio…
- arXiv cs.AIresearchNormative Loss Landscape Navigation: A Trajectory-Based Approach to Mitigating Forgetting in Incremental Learning
arXiv:2609.35926v1 Announce Type: cross Abstract: Continual learning models suffer from catastrophic forgetting when trained sequentially on non-stationary data distributions. Previously, this has been addressed through…
- arXiv cs.AIagentsPrompted Identity Degrades Cooperation in Multi-Agent LLM Systems
arXiv:2609.35928v1 Announce Type: cross Abstract: Multi-agent LLM systems increasingly mix models from several providers, yet exposing each agent's underlying model identity to its peers significantly impairs cooperation…
- arXiv cs.AIagentsSame Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection
arXiv:2609.35932v1 Announce Type: cross Abstract: Prompt injection against LLM agents becomes much stronger when the injected instruction is wrapped in the model's own chat template. A forged template marker such as can…
- arXiv cs.AIresearchGraph neural networks for sampling-invariant embeddings of organized signal sets
arXiv:2609.35934v1 Announce Type: cross Abstract: Sensor networks and radars can deliver signals as organized sets, e.g. ordered signals, signals describing range cells within a grid or signals perceived as graph nodes.…
- arXiv cs.AIagentsEmbodied Semantic Communication for Collective Autonomous Agents: A Tutorial on Representation, Wireless Delivery, and Closed-Loop Coordination
arXiv:2609.35936v1 Announce Type: cross Abstract: As autonomous systems and embodied intelligence enter the dynamic physical world, multi-agent collaboration calls for a paradigm shift in communication design. However, e…
- arXiv cs.AIagentsPrivacySkills: How Privacy Guidance Shapes Source Selection in LLM Agents
arXiv:2609.35937v1 Announce Type: cross Abstract: While prior work has documented privacy failures in LLM agents, it remains unclear how the presentation of privacy guidance influences their choice of information sources…
- arXiv cs.AIresearchIntrinsic Associative Memory on Riemannian Manifolds: Curvature, Capacity, and Emergent Modes
arXiv:2609.35948v1 Announce Type: cross Abstract: Geometry does more than constrain an associative memory: curvature determines what it remembers and which states it creates. We develop intrinsic dense associative memori…
- arXiv cs.AIresearchHEAR: Real Voices, Real Bias: A Large-Scale Human-Recorded, Demographically Diverse Benchmark for Audio Language Models
arXiv:2609.35952v1 Announce Type: cross Abstract: We introduce HEAR (Human-recorded Evaluation of Audio-LLM bias by Real speakers), a large-scale, ecologically valid benchmark comprising 87k real human audio samples from…
- arXiv cs.AIresearchROSS: Relearning from Self-Generated Rollouts through Selective Supervision
arXiv:2609.35954v2 Announce Type: replace-cross Abstract: Large language model post-training generates self-generated rollouts through reinforcement learning and on-policy distillation, yet this experience is often treat…
- arXiv cs.AIagentsSolver Agent: an Agentic AI Framework for Theoretical Physics Computations Applied to F-theory Uplifts of O3-planes and S-folds
arXiv:2609.35958v1 Announce Type: cross Abstract: We introduce Solver Agent, an AI framework based on large language models for calculations and proofs in mathematics and theoretical physics. The solution process is trac…
- arXiv cs.AIagentsSystematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method
arXiv:2609.35965v2 Announce Type: replace-cross Abstract: Vision-and-Language Navigation (VLN) has largely focused on a single agent following a single instruction, yet many real-world applications require teams of robot…
- arXiv cs.AIresearchCausal and Interpretable Structures in LLM Compositional Tasks
arXiv:2609.35970v1 Announce Type: cross Abstract: Large language models are able to solve tasks whose answers depend on not only individual input tokens, but also on relations among them. How is such relational informati…
- arXiv cs.AIresearchInfrared Subtraction with Artificial Intelligence
arXiv:2609.36007v3 Announce Type: replace-cross Abstract: We present AI-developed local infrared subtraction, building on projection to Born and EFT matching. The framework separates an integrable radiation term from a f…
- arXiv cs.AIresearchTORQUE: Optimizing What (not) to Quantize Before and After Rotation
arXiv:2609.36032v1 Announce Type: cross Abstract: Uniform random rotations are an effective preprocessing step for quantization: they make normalized coordinate distributions approximately Gaussian, enabling the use of c…
- arXiv cs.AIresearchNeural networks for spectral optimization
arXiv:2609.36047v1 Announce Type: cross Abstract: Given a functional dependent on the spectrum of a differential operator, we address the problem of finding a domain which optimizes this functional. PDE solvers might be…
- arXiv cs.AIresearchImproving scalable oversight with co-trained monitors
arXiv:2609.36049v1 Announce Type: cross Abstract: Worker-monitor setups are a promising approach to AI oversight, but training workers against fixed monitors can incentivize monitor evasion. We study whether this failure…
- arXiv cs.AIresearchWhat if automating AI R&D triggers an intelligence explosion?
arXiv:2609.36054v2 Announce Type: replace-cross Abstract: In contrast to even a year ago, AI systems now write most of the code inside the companies that build them. As more of the AI research and development (R&D) pipel…
- arXiv cs.AIagentsMnemon: Raw Records, Fast Judgments, Slow Thoughts
arXiv:2609.36059v1 Announce Type: cross Abstract: Long-term memory lets an LLM assistant use a history it can no longer reread, and most memory systems build it by rewriting conversations into facts, graphs or typed memo…
- arXiv cs.AIresearchUnderstanding Decision-Making Mechanisms in Neural Routing Solvers
arXiv:2609.36063v1 Announce Type: cross Abstract: Neural Combinatorial Optimization (NCO) has achieved strong empirical success, yet the internal mechanisms driving model decisions remain largely unexplored. In this pape…
- arXiv cs.AIresearchFLOORA: A Human-Aligned Domain-Specific Language Model for Architectural Design
arXiv:2609.36064v1 Announce Type: cross Abstract: Foundation models are powerful generators, but many engineering domains require structured representations that general-purpose systems handle poorly. We introduce FLOORA…
- arXiv cs.AIagentsAerialDojo-200K: A Large-Scale Benchmark Suite for Open-World Aerial Object-Goal Search
arXiv:2609.36066v1 Announce Type: cross Abstract: Open-world aerial object-goal search is a foundational yet challenging task, requiring aerial agents to autonomously explore large-scale, unstructured three-dimensional e…
- arXiv cs.AIresearchThe Uneven Decline of Collective Knowledge Production: Evidence from Stack Overflow After Generative AI
arXiv:2609.36069v1 Announce Type: cross Abstract: Generative AI (Gen AI) is reshaping how individuals learn and work, but its consequences for collective knowledge, the shared body of knowledge that online communities pr…
- arXiv cs.AIresearchMeasuring trainable degrees of freedom in materials graph neural networks: a random-subspace intrinsic dimension analysis
arXiv:2609.36084v1 Announce Type: cross Abstract: Final predictive accuracy is the standard basis for comparing graph neural networks (GNNs) in materials-property prediction, but it does not show how strongly performance…
- arXiv cs.AIagentsPADM\'E: Preference Alignment Data Synthesis for Meta-Evaluation of LM Agent Evaluators
arXiv:2609.36086v1 Announce Type: cross Abstract: Language models are frequently employed to evaluate other language models. An LM evaluator scoring agentic behaviors across multiple criteria is valuable, provided that i…
- arXiv cs.AIresearchPHASE: A Physiology-Guided Hierarchical Foundation Model for Intracranial EEG
arXiv:2609.36087v2 Announce Type: replace-cross Abstract: Clinicians and neuroscientists have long analyzed intracranial electroencephalography (iEEG) through directly measurable physiological characteristics, which carr…
- arXiv cs.AIresearchOne Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models
arXiv:2609.36101v1 Announce Type: cross Abstract: Contrastive vision-language models learn shared embedding spaces by aligning matched image-text pairs, yet their representations remain separated by a modality gap. Prior…
- arXiv cs.AIresearchLoopICL: Looping a single transformer block to solve tabular tasks
arXiv:2609.36108v1 Announce Type: cross Abstract: Tabular foundation models using in-context learning have recently surpassed gradient-boosted trees on predictive tabular tasks. However, recent mechanistic insights sugge…
- arXiv cs.AIresearchThinQuant: Scalable Rotation Learning for Weight and Activation Quantization of LLMs
arXiv:2609.36120v1 Announce Type: cross Abstract: Learned rotations play an important role in enabling low-bit weight and activation quantization of large language models by smoothing outliers in the activation distribut…
- arXiv cs.AIresearchRender Before Reading: Visual Rendering as a Prompt Injection Defense
arXiv:2609.36121v1 Announce Type: cross Abstract: Large language models are vulnerable to prompt injection attacks, where third-party adversarial content can hijack the model's behavior. In this paper, we study the role…