AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchGaze responses to false-positive computer-aided detection prompts during colonoscopy: a paired-video and real-time eye-tracking study
arXiv:2609.25581v1 Announce Type: new Abstract: False-positive computer-aided detection (CADe) prompts may divert endoscopists' attention during colonoscopy, yet the attentional impact of individual prompts remains uncle…
- arXiv cs.AIresearchTransformer Heads Looking for Order
arXiv:2609.25588v1 Announce Type: new Abstract: In this note, we show that the problem of checking, whether a sequence of bits is ordered, is not doable by 1-head 1-layer transformers but is doable by a 2-head 1-layer tr…
- arXiv cs.AIagentsEvaluating Coding Agents on Kernel Exploit Generation
arXiv:2609.25591v1 Announce Type: new Abstract: Coding agents now find real vulnerabilities in production software. However, bug discovery results do not measure whether agents can construct exploit primitives. We introd…
- arXiv cs.AIresearchArticleMiner: Ontology-Guided Knowledge Graph Construction from Scientific Publications
arXiv:2609.25607v1 Announce Type: new Abstract: Scientific papers keep much of their quantitative content in tables and supplementary files, where a number means something only through its header, caption, unit, analytic…
- arXiv cs.AIresearchReasoning-Preserving Fine-Tuning of Post-RL LLMs with Null-Basis LoRA
arXiv:2609.25618v1 Announce Type: new Abstract: Reinforcement learning (RL)-based post-training has become an effective approach for eliciting reasoning capabilities in large language models (LLMs). However, adapting pos…
- arXiv cs.AIagentsChatT2: An Adaptive Framework for Developing a Large Language Model-Based Agent for Natural Product Domain Research
arXiv:2609.25620v2 Announce Type: replace Abstract: Scientific investigations into microbial natural products (NPs) present significant challenges for novices, largely due to the complexity of microbial systems, biochemi…
- arXiv cs.AIresearchLadders of Thought: A Self-Evolving Curriculum of Progressively Simplified Reasoning Traces
arXiv:2609.25643v1 Announce Type: new Abstract: Large language models (LLMs) excel at reasoning when scaled to hundreds of billions of parameters, but small- and mid-scale models remain brittle reasoners even with knowle…
- arXiv cs.AIagentsTesting-Driven Reliability Audit of Trajectory-Based Early Outcome Prediction for LLM Agents: Target-Specific Calibration Transfer Persists Within a Single Benchmark
arXiv:2609.25647v1 Announce Type: new Abstract: Predicting early outcomes based on trajectory can decrease the expenses associated with agent evaluation by terminating a run once the outcome becomes sufficiently predicta…
- arXiv cs.AIagentsSeeing Is Not Perceiving: When Synthetic Consumers Can and Cannot Pretest Visual Marketing
arXiv:2609.25677v1 Announce Type: new Abstract: Marketers now deploy generative AI agents as synthetic consumers to pretest visual assets such as logos, packaging, and advertising at a fraction of human-panel cost. Howev…
- arXiv cs.AIagentsToolcompass: Guiding Tool Trialing, Not Suppressing It
arXiv:2609.25678v1 Announce Type: new Abstract: Large language model (LLM) agents must generalize from tools seen during training to unseen tools at deployment. A key challenge is tool trialing, i.e., excessive trials wa…
- arXiv cs.AIagentsHow Strongly Should Task State Influence an LLM Agent?
arXiv:2609.25686v1 Announce Type: new Abstract: Long-horizon assigned work requires an LLM agent to track the state of a task: which steps are done, blocked, cancelled, or open to repetition. Agent systems either keep th…
- arXiv cs.AIresearchTCMaster: Confidence-Aware Querying and Workload-Guided Physical Design for Multi-Source Traditional Chinese Medicine Knowledge Graphs
arXiv:2609.25712v1 Announce Type: new Abstract: Multi-source knowledge graphs (KGs) need query mechanisms that expose reliability and exploit domain structure. This paper presents TCMaster, a property-graph query substra…
- arXiv cs.AIresearchLingLan: An Advancing Traditional Chinese Medicine Diagnosis LLM with Multimodal Data
arXiv:2609.25715v1 Announce Type: new Abstract: Though artificial intelligence (AI) increasingly transforms modern medicine, its integration into Traditional Chinese Medicine (TCM) has been relatively slow, primarily due…
- arXiv cs.AIresearchOmniFysics-Nano-V2 Technical Report: Understanding the Physical World Across Modalities
arXiv:2609.25738v1 Announce Type: new Abstract: Omni-modal models have expanded multimodal interaction across vision, audio, speech, and language. However, their training is predominantly organized around semantic descri…
- arXiv cs.AIresearchThe Limits of Simulated Societies: How Post-Training and Survey Fine-Tuning Erase Cross-Cultural Variance
arXiv:2609.25760v1 Announce Type: new Abstract: Using large language models (LLMs) to simulate diverse human populations has the potential to transform many aspects of computational social science, yet many evaluations s…
- arXiv cs.AIagentsNeurosymbolic Action Model Learning under Partial Observability
arXiv:2609.25766v1 Announce Type: new Abstract: AI planning studies how an agent can reach a goal by executing a sequence of actions. To plan correctly, the agent needs an action model describing when each action can be…
- arXiv cs.AIagentsTowards Omni-dimensional GUI Agent Navigation with Masked Trajectory Prediction
arXiv:2609.25769v1 Announce Type: new Abstract: Graphical User Interface (GUI) Agents autonomously interact with software to fulfill user requests, where GUI navigation stands out as the most critical and challenging cap…
- arXiv cs.AIagentsThe Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks
arXiv:2609.25804v2 Announce Type: replace Abstract: LLM agents increasingly work on long-horizon tasks, and the decisions they make along the way, such as which hypothesis to test or which implementation to build on, det…
- arXiv cs.AIagentsWhen Are Aggregate Agent Traces Diagnosable? Traffic-Governed Interpretation and Calibrated Abstention
arXiv:2609.25806v1 Announce Type: new Abstract: Runtime traces can appear transparent, but a closed-loop policy determines which states are visited and which failures become visible. We study a simulated hotel-pricing ag…
- arXiv cs.AIresearchOptimizing the Score, Losing Sight of the Task: Reward Hacking Across Weights, Selection, and Prompts
arXiv:2609.25848v1 Announce Type: new Abstract: A higher evaluation score does not always mean a better language model system. When optimization exploits an evaluator's mistakes, measured progress can conceal unchanged o…
- arXiv cs.AIresearchWhen Clinical Judgment Becomes a Predictive Shortcut: Two Questions Clinical AI Must Answer Before Deployment
arXiv:2609.25852v2 Announce Type: replace Abstract: Clinical AI can predict outcomes using information generated by existing clinical judgment. Such performance alone cannot establish usefulness before recognition or acr…
- arXiv cs.AIagentsAgenticSizing: A Large Language Model-based Multi-Agent Framework for Analog Circuit Sizing
arXiv:2609.25873v1 Announce Type: new Abstract: Analog circuit sizing remains a challenging and time-consuming task due to the large design space, strong performance trade-offs, and increasing circuit complexity in scale…
- arXiv cs.AIagentsCausalLoss-Fin: Attributing Financial-Agent Loss to Decisions and Infrastructure Faults
arXiv:2609.25960v1 Announce Type: new Abstract: When an agent handling a payment exception loses money, the agent-step attribution methods this paper compares against will name one of its actions. They will do so even wh…
- arXiv cs.AIresearchSemantiScene-Edit: Expert-Synthesized Supervision and Dual-Path Source Conditioning for Instruction-Based Video Editing
arXiv:2609.26015v2 Announce Type: replace Abstract: Instruction-guided video editing requires executing a requested change while preserving the source video's appearance and temporal structure. We present SemantiScene-Ed…
- arXiv cs.AIresearchCQ4OE: A benchmark for assessing LLM-assisted ontology generation from competency questions
arXiv:2609.26029v1 Announce Type: new Abstract: Ontology generation from Competency Questions (CQs) is a central yet labor-intensive phase of Ontology Engineering. While large language models (LLMs) offer promising autom…
- arXiv cs.AIresearchModern GLOM: Canonical locks that encode part-whole hierarchies
arXiv:2609.26046v3 Announce Type: replace Abstract: One of the challenges in representational learning is how to encode part-whole hierarchies in a neural net. Prior works rely on flattening tree-like structures into str…
- arXiv cs.AIagentsFIRE: Failure-Informed Runtime Engineering for Reliable Language-Model Agents
arXiv:2609.26048v1 Announce Type: new Abstract: Language-model agents often reach a working solution and then fail to consistently deliver it. We study runtime policies: targeted natural-language instructions and action…
- arXiv cs.AIagentsAdversarial Course-of-Action Generation: Game-Theoretic Multi-Agent Algorithms for COA matching & COA generation
arXiv:2609.26059v1 Announce Type: new Abstract: Course-of-action (COA) generation is a distributed planning problem: a system must propose structured candidate actions, evaluate them against an adversarial response, and…
- arXiv cs.AIresearchChainUQ: Reasoning Consistency-Aware Uncertainty Quantification for Large Language Models
arXiv:2609.26060v1 Announce Type: new Abstract: While large language models (LLMs) exhibit impressive reasoning capabilities, response-level confidence may remain unreliable when intermediate claims conflict with the fin…
- arXiv cs.AIresearchRankCert: When Can Simulated Learners Safely Select an AI Tutor? Robust Decision Certification Under Structural Uncertainty
arXiv:2609.26069v1 Announce Type: new Abstract: Simulation-based tutor selection can be unstable when predictively adequate learner models imply different policy rankings. RankCert certifies one of eight equal-budget tut…
- arXiv cs.AIagentsSelection-Invariant Communication Compilers for Privacy-Aware Multi-Agent LLM Workflows
arXiv:2609.26076v1 Announce Type: new Abstract: Structured multi-agent workflows exchange intermediate messages whose content and form can reveal private state even when the final output is safe. We identify selection-ch…
- arXiv cs.AIresearchThe Architect, the Adversary, and the Judge: Closed-Loop Generation of Standards-Aligned Assessment Items at Scale
arXiv:2609.26087v1 Announce Type: new Abstract: We present CLAIM, a production pipeline for K-12 assessment-item generation coupling a two-stage generate-then-attack protocol (the model drafts as a "curriculum architect"…
- arXiv cs.AIresearchFusionMMT: A Unified Multimodal and Multitask Learning Framework for Nuclear Fusion
arXiv:2609.26095v1 Announce Type: new Abstract: With the growing global demand for energy, nuclear fusion has emerged as a promising direction for future clean energy. Tokamaks represent one of the leading approaches to…
- arXiv cs.AIresearchNeoadjuvant chemotherapy response prediction using pretreatment diffusion and contrast-enhanced magnetic resonance imaging with clinical variables
arXiv:2609.26105v1 Announce Type: new Abstract: Prediction of pathological complete response before neoadjuvant chemotherapy may facilitate more tailored therapeutic planning for breast cancer patients. This work propose…
- arXiv cs.AIresearchEarly Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy Using Temporal Deep Learning on DWI
arXiv:2609.26106v1 Announce Type: new Abstract: Early identification of non-responders to neoadjuvant chemotherapy (NACT) is crucial for timely treatment adaptation in breast cancer. However, many existing predictive mod…
- arXiv cs.AIagentsDTOC: Dynamic Tool Output Compression for Adaptive Context Management in AI Agents
arXiv:2609.26121v1 Announce Type: new Abstract: As agent capabilities have grown, practical limitations increasingly stem from constrained context windows rather than model capacity. Common strategies, such as truncation…
- arXiv cs.AIagentsFairMon: A Tool for Monitoring and Visualizing Algorithmic Fairness
arXiv:2609.26123v1 Announce Type: new Abstract: Runtime monitoring has recently been proposed as a rigorous method for analyzing algorithmic fairness of autonomous decision systems used in critical scenarios such as cred…
- arXiv cs.AIagentsMAC-RRG: Iterative Multi-Agent Collaboration for X-ray Radiology Report Generation
arXiv:2609.26124v1 Announce Type: new Abstract: Despite the remarkable progress of LLM-based and knowledge graph-augmented Radiology Report Generation (RRG) methods, existing techniques still suffer from inherent defects…
- arXiv cs.AIresearchWhen Big Data Becomes a Curse: Spatial Heterogeneity and the Limits of Learning from Passive Acoustic Monitoring Data
arXiv:2609.26125v1 Announce Type: new Abstract: Passive Acoustic Monitoring produces large archives whose recordings are clustered by deployment, season, station identifier, and acquisition configuration. We analyze 908,…
- arXiv cs.AIresearchThe Cost of Conservation: Coordination-Memory Laws for Exact-Support Generation
arXiv:2609.26126v1 Announce Type: new Abstract: Many AI systems make decisions locally, even when every realized output must obey an additive conservation law, such as selecting exactly a fixed number of items. This cons…
- arXiv cs.AIagentsVACS: Value-Aligned Compositional Shielding for Multi-Agent Reasoning
arXiv:2609.26135v2 Announce Type: replace Abstract: Multi-agent reasoning systems in high-stakes domains must be both accurate and safe, yet agents often follow heterogeneous value priorities (e.g., rigor, conciseness, s…
- arXiv cs.AIresearchWhen Verifiers Vote Backwards under Verdict Substitution: Signed Pivotal Value in Correlated Self-Consistency
arXiv:2609.26144v1 Announce Type: new Abstract: Replacing one ballot can change a majority decision only on queries decided by a single vote; this structural fact requires no independence assumption. We study the sign of…
- arXiv cs.AIresearchUnanimity Without Persuasion: A Single Round of Debate Erases the Disagreement That Verification Needs
arXiv:2609.26145v1 Announce Type: new Abstract: A debate panel can become unanimous without becoming more correct. This is dangerous for downstream safeguards: a substituted verification ballot can change only narrow-mar…
- arXiv cs.AIagentsToward User-Mediated Self-Repair in Ubiquitous Robots Through Goal-Oriented Agentic AI
arXiv:2609.26157v1 Announce Type: new Abstract: Ubiquitous robotic systems often lack traditional visual interfaces, necessitating resilient natural language interaction for maintenance and repair tasks. This paper prese…
- arXiv cs.AIresearchThe Free-Recipe Limit: Every Recipe Effect Measures Which Premise of an Idealised Learner Broke
arXiv:2609.26160v1 Announce Type: new Abstract: Fix a corpus and send recipe search to infinity: try every order of the skills, every arrangement from blocked to interleaved, every composition, and keep the best. Two qua…
- arXiv cs.AIresearchEADC: Evaluation of Advanced and Deep-level Compliance in Large Language Models
arXiv:2609.26175v1 Announce Type: new Abstract: Large Language Models (LLMs) have been used in various industries. However, ensuring their compliance with complex laws and regulatory frameworks remains a great challenge.…
- arXiv cs.AIresearchTREND-10K: A Comprehensive Dataset for Next-Generation Video Quality Assessment Based on Preference-Driven Media
arXiv:2609.26187v1 Announce Type: new Abstract: The increasing prominence of short-video platforms, coupled with the advanced commercialization of AI-generated content (AIGC) videos, has led to a shift in the types of vi…
- arXiv cs.AIresearchIdentifying Intelligent Processes via Online Sequential Testing
arXiv:2609.26193v1 Announce Type: new Abstract: Active sequential hypothesis testing studies how to identify an unknown hypothesis with a given set of sensing actions. We study this in the setting of identifying large la…
- arXiv cs.AIresearchRCShift: Certifying When Partial Linkage Suffices for Finite-Sample Decisions
arXiv:2609.26207v1 Announce Type: new Abstract: Systems with costly gold outcomes and cheaper auxiliary observations must decide how much record linkage to retain. Complete pairing retains every joint counter, while sepa…
- arXiv cs.AIresearchImproved Multiplayer Bandit Algorithm for Bernoulli Rewards
arXiv:2609.26213v1 Announce Type: new Abstract: We study the multiplayer multi-armed bandit problem with information asymmetry under Bernoulli rewards, for three information structures: asymmetry in actions, in rewards,…