AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchCognition-Oriented Emotion Tracing from Causes to Consequences in Real-World Social Scenes
arXiv:2610.11410v2 Announce Type: replace Abstract: Affective computing has progressed from categorical emotion recognition to open-ended affective analysis with large multimodal models. Yet affective science describes e…
- arXiv cs.AIresearchWhy machines will still not rule the world
arXiv:2610.11424v1 Announce Type: new Abstract: In our book Why machines will never rule the world [13, 14] we argue that arti- ficial general intelligence is mathematically impossible. This is because the human beings a…
- arXiv cs.AIagentsTracing the Thoughts of a Coding Agent Playing ARC-AGI-3: Lessons for Continual Learning
arXiv:2610.11450v1 Announce Type: new Abstract: We study how a coding agent learns across a sequence of abstract reasoning tasks. The agent runs on a frozen foundation model inside a fixed harness and acts by writing and…
- arXiv cs.AIresearchSpikeSSL: A Universal Spike Inference Framework with Dynamics-Informed State-Space Layers
arXiv:2610.11456v1 Announce Type: new Abstract: Two-photon calcium imaging is a standard tool for recording large neural populations in vivo, yet inferring spikes accurately across the growing diversity of calcium indica…
- arXiv cs.AIagentsWho Verifies the Verifier? Co-Evolving Inspectable Graders with Self-Improving Agents
arXiv:2610.11464v1 Announce Type: new Abstract: We changed the agent: did it actually get better? Every self-improving agent loop answers this hundreds of times, and every answer comes from a verifier. On open-ended task…
- arXiv cs.AIresearchFrom Chain-of-Thought to Loops: Non-Autoregressive Latent Reasoning via Looped Transformers
arXiv:2610.11472v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning often improves language-model performance by giving models additional computation before answering. However, explicit CoT expresses this co…
- arXiv cs.AIagentsBridgeGuard: Explicit Safety Drift for Diffusion-based Autonomous Driving
arXiv:2610.11483v1 Announce Type: new Abstract: Diffusion-based driving planners capture diverse behaviors but can generate unsafe trajectories under distribution shift. We propose BridgeGuard, a safety-constrained diffu…
- arXiv cs.AIresearchFed-GRPO: Reward-Signal-Driven Federated Group Relative Policy Optimization
arXiv:2610.11502v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL), particularly through Group Relative Policy Optimizat…
- arXiv cs.AIagentsThe Operator Mismatch Problem: Deploying BEV Perception with Portable GPU Compute
arXiv:2610.11504v1 Announce Type: new Abstract: Modern autonomous driving systems rely on bird's-eye-view (BEV) perception models that fuse camera and LiDAR inputs to detect objects in 3D space. These models are accurate…
- arXiv cs.AIresearchAtomWorld-Mirror: Macro-Step World Modeling of Critical Evolution Backbones for Materials Dynamics
arXiv:2610.11527v2 Announce Type: replace Abstract: Atomistic simulation is a fundamental tool for studying long-term materials evolution, from diffusion and defect dynamics to interfacial reactions and fracture. Yet con…
- arXiv cs.AIresearchReTeach: Building a Self-Teacher through Multi-Round Reflection and Retry
arXiv:2610.11529v1 Announce Type: new Abstract: Self-distillation can improve reasoning without a separately trained, more capable teacher, but its effectiveness depends on how the self-teacher gains an advantage over th…
- arXiv cs.AIagentsSafe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds
arXiv:2610.11552v1 Announce Type: new Abstract: Large language model agents can invoke tools fluently, but enterprise workflows demand more than selecting the right tools: actions must strictly comply with organizational…
- arXiv cs.AIagentsWorkerville: Towards an Organizational Behavior Account of Agent Safety
arXiv:2610.11561v1 Announce Type: new Abstract: LLM-based agents now interact with their environments continuously, shaped by such organizational channels as user instructions, peer messages, and long-term memory. Existi…
- arXiv cs.AIresearchScaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals
arXiv:2610.11570v2 Announce Type: replace Abstract: In this paper, we argue that Looped Transformers need their own residual connections to prevent performance degradation as the number of iterations grows. We first intr…
- arXiv cs.AIagentsMemory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies
arXiv:2610.11573v1 Announce Type: new Abstract: The memory capabilities of Large Language Models (LLMs) have garnered increasing attention recently. Despite great success achieved, existing retrieval-based memory approac…
- arXiv cs.AIagentsError-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems
arXiv:2610.11600v1 Announce Type: new Abstract: LLM-based multi-agent systems (MASs) are increasingly used to solve complex tasks through coordinated reasoning, tool use, and interaction with external resources. However,…
- arXiv cs.AIagentsAgentEvolver: System-Wide Self-Evolution Through Task Execution
arXiv:2610.11613v1 Announce Type: new Abstract: An agent can complete a task without improving how it works. Turning task experience into reusable capability requires connecting the changed component to its evaluation an…
- arXiv cs.AIresearchWhere to Adapt Matters: Layer-Selective Fine-Tuning for Capability Retention
arXiv:2610.11620v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) enables large language models (LLMs) to adapt to specialized tasks, but often at the cost of degrading general capabilities acquired…
- arXiv cs.AIagentsEvidence-Traceable Dynamic Interviewer Architecture for Expertise-Adaptive Qualitative Interviews Using Local LLMs
arXiv:2610.11651v1 Announce Type: new Abstract: Automated interviewers and conversational agents are increasingly used in research, recruitment, customer service, and education. However, many existing systems rely on fix…
- arXiv cs.AIagentsHarness Evolution Hits a Ceiling: When Weight Training Should Begin
arXiv:2610.11655v1 Announce Type: new Abstract: Improving a long-horizon LLM agent means evolving the harness around a frozen model or training its weights. We let a self-evolving harness make the system stronger first,…
- arXiv cs.AIagentsLamarck's Driving School: Discovering Autonomous Driving Training Strategies through Evolutionary Competition
arXiv:2610.11662v1 Announce Type: new Abstract: Autonomous driving capabilities depend strongly on the distribution of scenarios encountered during training. Existing methods commonly construct or dynamically adapt train…
- arXiv cs.AIagentsConstrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games
arXiv:2610.11663v1 Announce Type: new Abstract: Deep reinforcement learning agents reach strong performance in real-time strategy games but can be brittle against opponents outside their training distribution. Separating…
- arXiv cs.AIresearchA 3D Characterization Framework for Intelligent Sequential Decision Making
arXiv:2610.11696v1 Announce Type: new Abstract: Puzzles are widely used to evaluate the reasoning capabilities of artificial intelligence (AI) systems for sequential decision making, yet approaches originating from diffe…
- arXiv cs.AIresearchIntervention anchors and scientific verification in synthetic vascular predictive representations
arXiv:2610.11704v1 Announce Type: new Abstract: Complete orthogonal predictive coordinates do not by themselves bind a latent direction to a named intervention. We present a mathematical and synthetic audit motivated by…
- arXiv cs.AIagentsDeltaReplay: Task-Relative Memory Reuse for Mobile GUI Agents
arXiv:2610.11707v1 Announce Type: new Abstract: Memory-augmented mobile GUI agents store successful execution trajectories and reuse them in later tasks, but a stored trajectory rarely matches a new task exactly. The new…
- arXiv cs.AIresearchInternalizer: Portable Context-to-Parameter Mapping for Very Large Language Models
arXiv:2610.11715v1 Announce Type: new Abstract: Hypernetworks that map a context directly to a LoRA adapter let a large language model carry that context in its weights, but prior work has demonstrated them only on base…
- arXiv cs.AIresearchMultiWorldBench: Do Independently Controlled Views Describe One Shared World?
arXiv:2610.11723v4 Announce Type: replace Abstract: Multiplayer world models must ensure that independently controlled views remain consistent with a single shared and persistent world. We introduce MultiWorldBench, a di…
- arXiv cs.AIagentsMemTrial: Learning When to Trust Memory in LLM Portfolio Agents
arXiv:2610.11732v2 Announce Type: replace Abstract: Large language model (LLM) agents for portfolio management learn from experience: they credit each experience in their memory with the outcome of the decisions that use…
- arXiv cs.AIresearchOnboard Marine Anomaly Detection on $\Phi$sat-2: From Simulation-Based Development to In-Orbit Demonstration
arXiv:2610.11735v1 Announce Type: new Abstract: Onboard Artificial Intelligence can improve responsiveness and bandwidth efficiency of Earth Observation systems by processing data directly on the satellite. This paper pr…
- arXiv cs.AIresearchScalable AI Uncertainty Quantification via Generalized Laplace Active Subspaces
arXiv:2610.11738v1 Announce Type: new Abstract: Reliable uncertainty quantification (UQ) is essential for deploying neural networks in scientific and high-stakes applications, but full Bayesian inference over the network…
- arXiv cs.AIresearchWhere Draft Trees Lose Target Mass: Exit-Guided Speculative Decoding
arXiv:2610.11750v1 Announce Type: new Abstract: Tree-based speculative decoding verifies multiple draft continuations in one target-model pass, but finite trees built from draft scores face a fundamental draft-target mis…
- arXiv cs.AIagentsWhat Output-Only Review Cannot Verify: Study Contracts for Research Agents
arXiv:2610.11754v1 Announce Type: new Abstract: Some defects in an AI-generated study can be identified from its artifacts; others require knowledge of what was approved before execution. We propose study contracts that…
- arXiv cs.AIagentsSafe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models
arXiv:2610.11773v3 Announce Type: replace Abstract: Guard models are increasingly used to safeguard LLM-based agents, primarily by identifying actions that agents are forbidden to perform. However, identifying forbidden…
- arXiv cs.AIresearchRouterInterp: Understanding Superposed Specialisation in Mixture of Experts Routing
arXiv:2610.11775v1 Announce Type: new Abstract: Sparse Mixture of Experts (MoE) models scale more efficiently than dense models by routing tokens to modular expert networks that are only active for processing a fraction…
- arXiv cs.AIagentsMemento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks
arXiv:2610.11794v1 Announce Type: new Abstract: Learning to act in unfamiliar environments requires agents to infer how the world works and revise that understanding as new evidence arrives. Yet limited observations can…
- arXiv cs.AIresearchProbability-Signature Dynamics: Unpacking Modular Addition Learning Within Two-Layer Networks
arXiv:2610.11833v1 Announce Type: new Abstract: Neural networks trained on modular addition tasks often develop Fourier-structured representations that support exact generalization. While prior work has identified these…
- arXiv cs.AIresearchLEVER: Adaptive Cost-Aware Proof Search Over AND/OR Graphs
arXiv:2610.11862v1 Announce Type: new Abstract: Mathematicians value proofs for more than correctness: among correct proofs, simplicity, purity and the computational cost of finding them vary widely. Yet LLM-powered theo…
- arXiv cs.AIresearchHow Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices
arXiv:2610.11877v1 Announce Type: new Abstract: Automated research systems support literature synthesis, ideation, experiments, writing, and peer review, but their evaluation is dispersed across tasks, benchmarks, and st…
- arXiv cs.AIresearchMindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation
arXiv:2610.11966v1 Announce Type: new Abstract: Research idea innovation is a fundamental engine of scientific progress, yet it remains difficult to generate and evaluate in a scalable and controllable way. This challeng…
- arXiv cs.AIresearchMetaOPD: Meta-Learned Token Weighting for On-Policy Distillation
arXiv:2610.11989v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own generated responses using token-level teacher supervision. However, uniform weighting overlooks differences in toke…
- arXiv cs.AIresearchAn Interpretable Approach to PDE Solution Discovery via Structural Experience Distillation
arXiv:2610.12003v1 Announce Type: new Abstract: PDE solution discovery aims to identify explicit symbolic expressions for unknown physical fields from observations under known physical constraints. Existing methods, howe…
- arXiv cs.AIresearchComplexity of Grounded Semantics and Preferred Semantics in Finitary Argumentation Frameworks
arXiv:2610.12008v1 Announce Type: new Abstract: Abstract argumentation frameworks (AFs) introduced by Dung provide a formal foundation for non-monotonic reasoning in artificial intelligence. While decision problems for g…
- arXiv cs.AIresearchPulseBound: Future-Beat State Forecasting Under an Explicit Information Boundary
arXiv:2610.12010v2 Announce Type: replace Abstract: Predictive representation learning from photoplethysmography (PPG) can violate causal information access even with causal attention, as normalization, nonlocal transfor…
- arXiv cs.AIresearchInterviewPlayground: A Validated Simulation Environment for Evaluating AI Interviewers
arXiv:2610.12023v2 Announce Type: replace Abstract: Increasingly, AI interviewers are being developed to elicit open-ended responses in applications like market research, public polling, preference elicitation, and socia…
- arXiv cs.AIresearchStructure Tax: How Structured Output affects LLMs Performance
arXiv:2610.12056v1 Announce Type: new Abstract: Deploying large language models in production often requires constraining outputs to structured formats such as JSON or XML, and prior work treats the resulting accuracy lo…
- arXiv cs.AIagentsWhen Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation
arXiv:2610.12061v1 Announce Type: new Abstract: Large language model (LLM)-based agents have demonstrated strong capabilities on complex tasks. They typically perform reasoning before each action throughout an interactio…
- arXiv cs.AIresearchIs Memorization Context-Sensitive? Prefix-Based Extraction Beyond Isolated Prefixes
arXiv:2610.12085v1 Announce Type: new Abstract: Large language models (LLMs) can expose memorized training sequences under prefix-based extraction: given a prefix from a training example, the model may assign high probab…
- arXiv cs.AIagentsEvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program Evolution
arXiv:2610.12086v1 Announce Type: new Abstract: LLM-based program evolution relies on evaluation feedback to guide the iterative search for high-performing programs. However, evaluation is often computationally expensive…
- arXiv cs.AIresearchRecompose and Refine Latent Reasoning Flows for Vision-Language-Action Models
arXiv:2610.12090v1 Announce Type: new Abstract: Latent reasoning enables vision-language-action (VLA) models to transform multimodal observations into task-relevant internal states before generating continuous robot acti…
- arXiv cs.AIresearchUniversal Textual Teaching for LLMs
arXiv:2610.12114v1 Announce Type: new Abstract: Knowledge distillation (KD) transfers knowledge from stronger Teacher models to weaker Student models, but most methods require training the Student parameters, thereby bin…