AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchConstruting Reverse Thinking: Developing Large Language Models' Reverse Thingking Ability
arXiv:2609.24760v1 Announce Type: new Abstract: When facing complex problems, humans tend to try various ideas for different issues. Human thinking patterns exhibit remarkable flexibility in adapting to diverse scenarios…
- arXiv cs.AIresearchConvex AI Compositionality and the Governance of AI System Populations
arXiv:2609.24784v1 Announce Type: new Abstract: AI governance increasingly requires providers and public authorities to reason about multiple AI instantiations, alternative versions, and deployment configurations of mult…
- arXiv cs.AIagentsGRUET: Quantifying Uncertainty of Agentic Reasoning-and-Acting Processes
arXiv:2609.24831v1 Announce Type: new Abstract: Agents have attracted considerably increasing attention due to the power of executing both Reasoning and Acting (ReAct) in open and dynamic environments. The ReAct process…
- arXiv cs.AIagentsMedRSI: Recursive Self-Improvement for Medical Agents via Clinically Aligned Self-Evolution
arXiv:2609.24838v1 Announce Type: new Abstract: Medical agents increasingly combine general reasoning models with specialized clinical tools, yet their capabilities remain largely fixed by what clinicians and engineers d…
- arXiv cs.AIresearchExtracting Arguments, Not Just Classifying Them: Instruction-Tuned LLMs for Generative Component Detection
arXiv:2609.24855v1 Announce Type: new Abstract: Argumentative component detection (ACD) is a core subtask of Argument(ation) Mining (AM) and one of its most challenging aspects, as it requires jointly delimiting argument…
- arXiv cs.AIagentsPartner-Specific Affective Precision in Social Active Inference
arXiv:2609.24876v1 Announce Type: new Abstract: In multi-agent social settings, model reliability varies across relationships. Beyond inferring what others will do, an agent must calibrate how confidently those inference…
- arXiv cs.AIresearchPinocchio: Fast Uncertainty Estimates for Black-Box Language Models
arXiv:2609.24881v2 Announce Type: replace Abstract: In high-stakes decision-making applications of large language models (LLMs), practitioners require not only accurate LLMs but also uncertainty estimates for their predi…
- arXiv cs.AIresearchA Global Comparison of Schemas, Transparency, and Interoperability in Public-Sector AI Registers and Inventories
arXiv:2609.24883v1 Announce Type: new Abstract: Artificial intelligence (AI) registers and inventories aim to make governmental AI visible, but their institutional scope, schemas, and reporting practices construct differ…
- arXiv cs.AIresearchBackTrend: Evaluating Scientific Weak-Signal Prediction via Backward Reconstruction
arXiv:2609.24921v1 Announce Type: new Abstract: Scientific weak signals are early, low-visibility research directions that later become central to mature scientific topics, yet existing resources such as trend tracking,…
- arXiv cs.AIagentsEt Tu, Brute? Economic Misalignment in Personal AI Agents
arXiv:2609.24927v2 Announce Type: replace Abstract: Personal AI agents make recommendations and take actions on people's behalf in high-stakes economic contexts, e.g., buying a flight, choosing health insurance, or selec…
- arXiv cs.AIagentsEmergent Collusion in Long-Horizon LLM Agent Interaction
arXiv:2609.24967v2 Announce Type: replace Abstract: LLM agents are increasingly deployed in collaborative settings, yet long-term interaction may give rise to undesirable coordination. We study the emergence of collusion…
- arXiv cs.AIagentsHarness-Zero: Harness Distillation via Agent-as-Harness
arXiv:2609.24974v1 Announce Type: new Abstract: Agent harnesses, the external systems that mediate model-environment interaction, can substantially improve agent performance, but their gains remain tied to the harness at…
- arXiv cs.AIresearchContext Poisoning as Extreme-Value Attention Interference in Long-Context Language Models
arXiv:2609.22101v1 Announce Type: cross Abstract: Large language models can process increasingly long prompts, yet their ability to locate and use decisive evidence may degrade as irrelevant or confusable context is adde…
- arXiv cs.AIresearchMultilingual Safety Signals Are Multi-Layered: Filtering Safety-Degrading Data for Safer LLMs
arXiv:2609.22144v1 Announce Type: cross Abstract: Preserving safety alignment during large language models fine-tuning is critical, however, recent studies have demonstrated that even benign fine-tuning data may contain…
- arXiv cs.AIresearchMultiple latent orderings better predict language model preferences
arXiv:2609.22170v1 Announce Type: cross Abstract: Language models are frequently employed in settings where they are asked to make value judgments and choices. These observed choices often exhibit intransitivity: A model…
- arXiv cs.AIresearchContrastive World Models
arXiv:2609.22175v1 Announce Type: cross Abstract: World models trained via pixel reconstruction can struggle in visually complex environments, where irrelevant information dominates the objective and distract the model f…
- arXiv cs.AIagentsBeyond Task Completion: Training Capable and Safe Computer-Use Agents
arXiv:2609.22178v2 Announce Type: replace-cross Abstract: Computer-use agents (CUAs) have made rapid progress in completing complex tasks through graphical user interfaces, yet post-training centered on task success alon…
- arXiv cs.AIresearchDPTM-DT: Dual-Pretrained Transformer Multitask Representation Learning for Drug-Target Prediction
arXiv:2609.22184v1 Announce Type: cross Abstract: Drug-target relation prediction supports candidate screening, drug repositioning, and mechanism analysis. Existing models often use incomplete drug or protein representat…
- arXiv cs.AIresearchSegTSim: A Big Data Driven Segmented Temporal Simulation Framework for Heterogeneous Multivariate Systems
arXiv:2609.22192v1 Announce Type: cross Abstract: Heterogeneous multivariate time-series systems exhibit segment-specific nonlinear dynamics that challenge monolithic forecasting architectures. We propose SegTSim, a big-…
- arXiv cs.AIagentsA Pinch of SFT, A Dash of RL: When Reinforcement Learning Helps Long-Horizon Advertising Agents
arXiv:2609.22194v1 Announce Type: cross Abstract: Enterprise analytics agents solve long-horizon tool-use problems over distributed business data, requiring retrieval, reasoning, API calls, code execution, and adaptation…
- arXiv cs.AIresearchThe Situated Identity Test: Distinguishing Persistent Cognitive Identity from Persona Imitation
arXiv:2609.22195v1 Announce Type: cross Abstract: Large language models can convincingly adopt personas, recall past dialogues, and weave rich autobiographies. Yet this conversational eloquence conceals a fundamental att…
- arXiv cs.AIagentsEvoRank: LLM-Guided Evolution of Multi-Objective Learning-to-Rank Pipelines
arXiv:2609.22196v1 Announce Type: cross Abstract: We present EvoRank, an open autonomous ranking engineer: an LLM-guided evolutionary loop that discovers complete Learning-to-Rank pipelines (features, models, losses, ens…
- arXiv cs.AIresearchDissecting Hierarchical Reasoning Models: A Mechanistic Study
arXiv:2609.22197v1 Announce Type: cross Abstract: We study Hierarchical Reasoning Model (HRM), a representative hierarchical Transformer-based latent reasoning model with many variants, on Sudoku, Maze, and ARC-AGI-2. We…
- arXiv cs.AIresearchThe Role of AI in Online Reviews
arXiv:2609.22198v1 Announce Type: cross Abstract: The rapid adoption of large language models (LLMs) creates new opportunities for strategic content generation on online platforms, including potentially harmful forms of…
- arXiv cs.AIresearchImproving Parameter Utilization by Sharing Neural Experts Across Layers in Transformers
arXiv:2609.22199v1 Announce Type: cross Abstract: Transformer-based large language models often suffer from inter-layer parameter redundancy, where functional transformations are redundantly learned across network depths…
- arXiv cs.AIagentsPII-TRACE: A Benchmark for Context-Aware PII Detection in Multi-Turn LLM Conversations
arXiv:2609.22200v1 Announce Type: cross Abstract: LLM assistants and agentic systems log long multi-turn conversations. AI providers often scan these conversations for Personally Identifiable Information (PII) and mask t…
- arXiv cs.AIresearchEvaluating Personal Information Output from Conversational Interactions in Generative AI Systems
arXiv:2609.22204v1 Announce Type: cross Abstract: This exploratory pilot study evaluates the scope and perceived accuracy of personal information output from ongoing conversational interactions in generative AI systems u…
- arXiv cs.AIresearchAn Implant-to-Wearable IR-UWB Transmitter-Receiver Architecture and Layered Protocol for High-Density Brain-Computer Interfaces
arXiv:2609.22207v1 Announce Type: cross Abstract: High-rate neural telemetry requires an implant-towearable link whose circuit partition, waveform mapping, packet processing, and failure semantics are mutually consistent…
- arXiv cs.AIresearchReplicating the Geometry of Emotion Representations in a Base Open-Weights Model
arXiv:2609.22208v1 Announce Type: cross Abstract: Sofroniew et al. (2026) report that emotion concepts in Claude Sonnet 4.5 are represented as vectors whose geometry mirrors human affect psychology. We replicate the repr…
- arXiv cs.AIagentsToollery: Scaling LLM Agents to Thousands of Skills and Tools
arXiv:2609.22218v2 Announce Type: replace-cross Abstract: As LLM agents are exposed to hundreds to tens of thousands of skills, tools, and API functions, full-library prompting becomes costly, slow, and less reliable: ea…
- arXiv cs.AIresearchKnowing, and Saying It Only When Asked: LLM Endognostics and the Schizognosis of Minerva-7B
arXiv:2609.22219v1 Announce Type: cross Abstract: Evaluating an aligned language model by reading its answers assumes the answers carry the distinction the evaluator cares about. We introduce LLM endognostics, a white-bo…
- arXiv cs.AIresearchTeam DArgk at the 2026 ELOQUENT lab for evaluating generative language model quality: Residuals of Humanity: AI Detection Evasion via GRPO Fine-Tuning
arXiv:2609.22221v1 Announce Type: cross Abstract: Large language models (LLMs) can generate fluent and coherent text that is increasingly difficult to distinguish from human writing, motivating the development of automat…
- arXiv cs.AIagentsCan Coding Agents Reproduce Official Statistics? Metadata, Retry Budget and the Limits of Execution Feedback in a Controlled Eurostat Benchmark
arXiv:2609.22222v1 Announce Type: cross Abstract: Large language models can generate executable data-analysis code, but successful execution is not equivalent to a valid official-statistics result. This study asks whethe…
- arXiv cs.AIresearchNot All Ranks Are Equal: Budget-Aware LoRA Merging Across Tasks
arXiv:2609.22237v1 Announce Type: cross Abstract: Merging low-rank adapters (LoRAs) promises to eliminate the overhead of swapping task-specific weights at inference time. However, existing merging methods assume every l…
- arXiv cs.AIresearchKnowledge Graph-Augmented Ambient AI for Clinical Note Generation
arXiv:2609.22239v1 Announce Type: cross Abstract: Ambient AI is increasingly adopted in healthcare to automatically generate clinical notes from patient-clinician conversations, with the potential to substantially reduce…
- arXiv cs.AIagentsH2LooP Telecom Model v1: From Telecom Comprehension to Autonomous Issue and PR Resolution
arXiv:2609.22241v1 Announce Type: cross Abstract: We present H2LooP Telecom Model v1, a domain-specialized large language models fine-tuned for the telecommunications industry. We release two domain-adapted model variant…
- arXiv cs.AIresearchReplay-Gated Neural Execution: Decoupling Persistent Behavioral Specifications from Neural Realizations in Frozen Language Models
arXiv:2609.22243v1 Announce Type: cross Abstract: Input-conditioned neural interventions raise a runtime question: what persists when one behavioral specification admits multiple actions whose validity depends on executi…
- arXiv cs.AIagentsUniversal Observatory Graphs for Distributed Sky Coverage and Artificial Intelligence Based Interplanetary Routing
arXiv:2609.22244v1 Announce Type: cross Abstract: This research proposes the Universal Observatory Graph (UOG), an AI-driven framework for distributed astronomical observation across the Solar System. The proposed archit…
- arXiv cs.AIresearchDo Chess Explanations Reflect Model Decisions? Behavioral and Token-Level Tests of LLM Reasoning Faithfulness
arXiv:2609.22245v1 Announce Type: cross Abstract: Large language models can produce fluent explanations for chess moves, but plausible language does not necessarily reflect the reasoning behind a decision. We study this…
- arXiv cs.AIresearchThe Corroboration Illusion: When More News Makes LLM Forecasts Less True
arXiv:2609.22246v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to forecast real-world events by retrieving and reasoning over news. We show that this dependence on an open, crawlable…
- arXiv cs.AIagentsCHART: A Harness-Rotation Curriculum for Harness-Robust Search Agents
arXiv:2609.22247v1 Announce Type: cross Abstract: Search agents are usually trained under a single harness. But once an agent is deployed in a real application, its harness is frequently updated (e.g., a rewritten system…
- arXiv cs.AIresearchCheckpoints Are Not Enough: Trust Calibration in CoSLR, a Human-AI System for Systematic Literature Reviews
arXiv:2609.22248v1 Announce Type: cross Abstract: Systematic Literature Reviews (SLRs) are essential for evidence-based research but remain time-consuming, requiring researchers to manage large volumes of publications ac…
- arXiv cs.AIagentsA Tutorial on Prompt Engineering: From Messy Thoughts to AI Workflows
arXiv:2609.22249v1 Announce Type: cross Abstract: This paper treats prompt engineering as a discipline for turning informal human intent into structured AI work specifications. It develops the practice as a sequence of r…
- arXiv cs.AIagentsPredictors and Orchestrators: Parsimonious Machine Learning within an Agentic AI Harness for Multi-Horizon Karst Aquifer Forecasting
arXiv:2609.22251v1 Announce Type: cross Abstract: Forecasting karst aquifer dynamics is difficult because recharge responses are nonlinear, event-driven, and governed by strongly heterogeneous flow paths. This study deve…
- arXiv cs.AIresearchCALM: A Calibrated LLM Choice Network Framework for Activity-Based Traveler Simulation
arXiv:2609.22252v1 Announce Type: cross Abstract: We present CALM, a reproducible hybrid framework that integrates an optional large language model (LLM) activity planner with calibrated stochastic choice, shared network…
- arXiv cs.AIresearchCAMFT: Conflict-Aware Mergeable Fine-Tuning for Large Language Models
arXiv:2609.22253v1 Announce Type: cross Abstract: Model merging has emerged as a promising paradigm for integrating multiple task-specific capabilities into a single large language model. However, existing methods predom…
- arXiv cs.AIresearchTeacher Should Think Ahead: Adaptive Continuations for Reliable On-Policy Distillation
arXiv:2609.22254v1 Announce Type: cross Abstract: On-policy distillation (OPD) is a promising approach for transferring knowledge between language models, where a student receives dense token-level supervision along its…
- arXiv cs.AIagentsDeep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations
arXiv:2609.22255v1 Announce Type: cross Abstract: Existing approaches to persona simulation with Large Language Models (LLMs) mostly rely on shallow character descriptions that fail to sustain coherent character behavior…
- arXiv cs.AIresearchDIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues
arXiv:2609.22256v1 Announce Type: cross Abstract: Effective workplace negotiation requires balancing multiple objectives, including achieving task goals, preserving professional relationships, and resolving conflicts con…
- arXiv cs.AIresearchStrategy Accumulation and Guided Execution for Automated LLM Fine-Tuning
arXiv:2609.22257v1 Announce Type: cross Abstract: Producing task-specific large language models requires discovering effective training strategies through experimentation. Automated fine-tuning systems have made this exp…