AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchAtomSteer: Test-Time Constraint Steering for Atomistic Generative Models
arXiv:2610.38517v1 Announce Type: cross Abstract: Diffusion and flow matching models offer scalable approaches to generating crystalline materials, molecular conformers, and protein-ligand complexes. However, satisfying…
- arXiv cs.AIagentsPersona Learning from Feedback for Personalized AI Assistants
arXiv:2610.38561v1 Announce Type: cross Abstract: Personalizing AI assistants requires adapting their behavior to users' preferences and task contexts. Existing work elicits assistant personas through persona prompting o…
- arXiv cs.AIresearchDo Audio LLMs HEAR Pain? Tracing Acoustic Evidence from Speech to Language Reasoning
arXiv:2610.38570v1 Announce Type: cross Abstract: Large audio language models (LALMs) can process speech directly, but it remains unclear how well they use the non-lexical acoustic information that speech carries. We stu…
- arXiv cs.AIresearchEpisodic looking - using reinforcement learning to bias perception enhances few-shot and continual learning with protection from forgetting
arXiv:2610.38577v1 Announce Type: cross Abstract: There is a fundamental contradiction between the desire for models that can generalize, and models that can continuously adapt to recent input with changing statistics. T…
- arXiv cs.AIagentsThe Artificial Personality Model: Theory, Implementation, Measurement and Experimental Validation in Conversational Agents
arXiv:2610.38608v1 Announce Type: cross Abstract: Artificial personality shapes user experience (UX) in human-machine interaction, yet coherent theoretical frameworks and validated measurement instruments remain limited.…
- arXiv cs.AIagentsHow Deterministic SAST and AI Security Agents Divide the Work: Coverage, Harness Policy and Cost in Snyk VulnBench 2.0
arXiv:2610.38617v1 Announce Type: cross Abstract: We ask what AI coding agents and AI security harnesses find that deterministic static application security testing (SAST) does not, and what they miss that SAST catches.…
- arXiv cs.AIresearchOn-Policy Self-Distillation with Teacher Evolution
arXiv:2610.38637v1 Announce Type: cross Abstract: On-Policy Self-Distillation (OPSD), which aligns a student model's token-level distribution with that of its self-teacher prompted by privileged context, has emerged as a…
- arXiv cs.AIresearchEnhanced image forensics through partial C2PA-based provenance information
arXiv:2610.38639v1 Announce Type: cross Abstract: Cryptographically verifiable C2PA-based Content Credentials (CCs) can be attached to freshly acquired or generated digital images but also to already existing ones with n…
- arXiv cs.AIresearchWhen AI performs, what remains? An integrative review of generative AI and cognitive capital in individuals and organizations
arXiv:2610.38647v1 Announce Type: cross Abstract: Generative artificial intelligence is rapidly entering knowledge work, and its short-term productivity benefits are increasingly documented. Less is known about what happ…
- arXiv cs.AIresearchInformation-Theoretic Reliability--Safety Bounds and Finite-Alignment Dynamics in AI Knowledge Distillation
arXiv:2610.38651v1 Announce Type: cross Abstract: The reliability and safety of artificial intelligence (AI), together with their transfer and evolution through knowledge distillation, have attracted growing attention. W…
- arXiv cs.AIresearchExplore Where It Matters: Targeted Exploration for Efficient Rover Adaptation
arXiv:2610.38657v1 Announce Type: cross Abstract: Future planetary rovers will traverse steep, deformable terrain where slip, sinkage, and terrain deformation can threaten mobility. Although simulation can capture some w…
- arXiv cs.AIresearchGeometry Matters in Packed 3D Attention
arXiv:2610.38694v1 Announce Type: cross Abstract: Packing a 3D volume into a token sequence is not merely long-sequence modeling. Once the volume is packed, sequence order no longer encodes the geometry of the sample---s…
- arXiv cs.AIresearchSatOps-Decision: Low-Latency Discriminative Decisions for Onboard Satellite Communication Operations
arXiv:2610.38697v1 Announce Type: cross Abstract: We propose SatOps-Decision, a method for low-latency decisions in satellite communication operations. To the best of our knowledge, it is the first application of Jev-sty…
- arXiv cs.AIresearchLatent Decision Flow Rewards for Clinical Guideline Reasoning
arXiv:2610.38709v1 Announce Type: cross Abstract: Clinical practice guidelines encode evidence-based recommendations as conditional decision flows, which makes them a natural source of process supervision for training re…
- arXiv cs.AIresearchLearning Scientific Trajectories to Predict Future Biomedical Discoveries
arXiv:2610.38719v1 Announce Type: cross Abstract: AI co-scientists have expanded the use of large language models for generating scientific hypotheses and guiding experimental investigation. Here we investigate whether t…
- arXiv cs.AIresearchinkGround: Benchmarking Fine-grained Visual Grounding Capabilities of Vision-Language Models for Cursive Handwriting in the Wild
arXiv:2610.38720v1 Announce Type: cross Abstract: Human handwriting is produced as an ordered sequence of pen movements, but an offline image keeps only the final ink. Handwriting trajectory recovery aims to restore the…
- arXiv cs.AIagentsAtomTree: A Hierarchical Framework for State-Aware Embodied Instruction Following with LLMs
arXiv:2610.38744v1 Announce Type: cross Abstract: Embodied instruction following in interactive environments requires agents to interpret natural language commands and complete long-horizon tasks. Existing planners eithe…
- arXiv cs.AIresearchCopyLoop: Fast Looped Transformer Decoding via Context Copying and Shallow Screening
arXiv:2610.38822v1 Announce Type: cross Abstract: Looped Transformers increase computational capacity through the repeated application of shared blocks, but their recurrent depth makes conventional full-depth decoding ex…
- arXiv cs.AIresearchEvaluating Visual Realism of AI-Generated Videos with Eye Tracking
arXiv:2610.38825v1 Announce Type: cross Abstract: Human evaluation of AI-generated videos has so far relied on explicit human feedback, such as judgments or ratings. While these signals capture the conclusions viewers re…
- arXiv cs.AIresearchDiscovering Jailbreaks via Curriculum of Models
arXiv:2610.38833v1 Announce Type: cross Abstract: Automated jailbreak discovery aims to find prompts that elicit prohibited behaviors from safety-trained language models, helping developers identify vulnerabilities befor…
- arXiv cs.AIagentsAutonomous Quantum Measurement with Agentic AI
arXiv:2610.38850v1 Announce Type: cross Abstract: Quantum materials exhibit diverse electronic and functional phenomena, but their characterization requires extensive experimental expertise, iterative decision-making and…
- arXiv cs.AIresearchFlipJev: Fast Black-Box Red Teaming Finds Universal Adversarial Suffixes for Typed Decision Models
arXiv:2610.38895v1 Announce Type: cross Abstract: Typed decision models are an emerging class of language models that make decisions instead of generating free-text responses. They answer in a single fast and cheap query…
- arXiv cs.AIresearchInterventional Training Reduces Causal Bypass in In-Context Introspection
arXiv:2610.38911v1 Announce Type: cross Abstract: Introspection, the ability of a system to access and reason about its internal signals, is crucial for language model (LM) self-consistency and scalable interpretability.…
- arXiv cs.AIresearchLev-3B: A Data Recipe for Compact Probabilistic Log Decision Models
arXiv:2610.38915v1 Announce Type: cross Abstract: Many log-analysis tasks involve choosing among known options, such as detecting anomalous sessions or identifying attack techniques, and benefit from calibrated probabili…
- arXiv cs.AIresearchTrussTutor-Bench: Benchmarking large language models on solution accuracy, sycophancy, and error detection in statics
arXiv:2610.38917v1 Announce Type: cross Abstract: Large language models (LLMs) have rapidly become a default source of help for students in science and engineering courses. In foundational engineering mechanics courses s…
- arXiv cs.AIagentsMAS-Loop: Beyond One-Shot Orchestration towards Self-Evolving Multi-Agent Systems
arXiv:2610.38946v1 Announce Type: cross Abstract: Training-time multi-agent system (MAS) design seeks to learn reusable orchestration policies, yet prevailing approaches remain largely one-shot: an Orchestrator generates…
- arXiv cs.AIresearchTableTune: Measured, Self-Correcting Draft-Length Tables for Dynamic Speculative Decoding
arXiv:2610.38968v1 Announce Type: cross Abstract: Speculative decoding speeds up large language model (LLM) serving only while the GPU has spare compute, so the best draft length, the number of tokens a small drafter gue…
- arXiv cs.AIresearchWhy Speculative Decoding Works Better Than Predicted on Sparse MoE Models
arXiv:2610.38981v1 Announce Type: cross Abstract: Speculative decoding (SD) accelerates autoregressive inference by leveraging the memory bound nature of decoding, verifying multiple draft tokens in a single forward pass…
- arXiv cs.AIresearchBenchmarking Graph Neural Networks for AC Power Flow: The Role of Inductive Biases and Physical Constraints
arXiv:2610.38985v1 Announce Type: cross Abstract: Fast and accurate models for AC power flow (ACPF) are increasingly important as modern electrical grids require more frequent system analyses. Graph neural networks (GNNs…
- arXiv cs.AIresearchRethinking GFlowNet Training: Negative Reinforce Dynamics
arXiv:2610.38994v1 Announce Type: cross Abstract: Generative Flow Networks (GFlowNets) are models that learn to sample discrete objects proportional to a target reward. They are trained by minimizing balance errors over…
- arXiv cs.AIresearchAssessing feature scorer results on high-dimensional datasets with t-SNE
arXiv:2610.39009v1 Announce Type: cross Abstract: While vast literature on high-dimensional data visualization is available, there are not many works regarding the visualization of feature scorers and their results. Feat…
- arXiv cs.AIresearchImplicit Reasoning in Transformers: Bridging the Compositionality Gap in GPT-2-like Models
arXiv:2610.39016v1 Announce Type: cross Abstract: Compositional generalization remains a persistent limitation of transformer language models: even when a model learns to combine known facts correctly in-distribution (ID…
- arXiv cs.AIresearchDistilling the Shape of Uncertainty: What On-Policy Distillation Learns and How to Predict It
arXiv:2610.39020v1 Announce Type: cross Abstract: On-policy distillation (OPD) is increasingly adopted in the post-training of large language models. However, a stronger teacher may fail to improve the student. Prior wor…
- arXiv cs.AIresearchRepresentation Complexity Along Learning Trajectories: Trading Width for Precision and Time
arXiv:2610.39027v1 Announce Type: cross Abstract: What computational role does overparameterisation play during learning? Information-plane analyses suggest that neural networks can traverse representations substantially…
- arXiv cs.AIresearchReinforcement Learning for the Game of Balatro: A Fast Simulator and Two-Policy Training Approach
arXiv:2610.39049v1 Announce Type: cross Abstract: Balatro, a 2024 roguelike deckbuilder, presents three difficulties that have historically derailed reinforcement learning methods: a 3,000-action state-dependent action s…
- arXiv cs.AIresearchWhen Does Closed-Loop Curriculum Adaptation Help GRPO? An Analysis on Countdown
arXiv:2610.39056v1 Announce Type: cross Abstract: Reinforcement fine-tuning has become an effective post-training paradigm for improving the reasoning ability of large language models, but it remains sample-inefficient w…
- arXiv cs.AIagentsHERA: Assessing an Autonomous Agent for Quantum Device Measurement
arXiv:2610.39074v1 Announce Type: cross Abstract: Large language model agents have begun to carry out laboratory measurements, but their scientific conclusions are useful only if they hold up under scrutiny. Demonstratin…
- arXiv cs.AIresearchTactus: Tactile & Pose Sensing Glove for Natural Dexterity Data Collection
arXiv:2610.39076v1 Announce Type: cross Abstract: Collecting naturalistic human manipulation demonstrations with accurate contact force and hand pose is essential for robot dexterous manipulation policy and foundational…
- arXiv cs.AIresearchGenerating Critic-Guided Synthetic Experience in Latent World Models
arXiv:2610.39100v1 Announce Type: cross Abstract: Learning from offline datasets is limited in scalability, as collecting new experience is often costly or unsafe in the real world. World models offer an alternative way…
- arXiv cs.AIagentsPCM: A Proof-Carrying Message Protocol for Verifiable Multi-Agent Communication
arXiv:2610.39109v1 Announce Type: cross Abstract: When one AI agent tells another that "the tests passed" or "a person approved this refund", the receiver has only the sender's word. A2A and MCP authenticate the channel,…
- arXiv cs.AIresearchFrom Local Recovery to Unified Generation: Discovering Triple Set in Knowledge Graphs via Observation-Anchored Latent Diffusion
arXiv:2610.39114v1 Announce Type: cross Abstract: Triple set prediction (TSP) is to recover missing relational triples in a knowledge graph by predicting the triple set instead of isolated links. Existing approaches pred…
- arXiv cs.AIagentsAppreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt Injection
arXiv:2610.39122v1 Announce Type: cross Abstract: Self-evolving personal agents act for users and learn from user feedback. However, if an agent obeys an instruction that an untrusted third party hides in content, the th…
- arXiv cs.AIagentsClean Sheets and Checkpoints: Evidence Complexity for Certifying Sequential Agent Risk
arXiv:2610.39124v1 Announce Type: cross Abstract: Dangerous-capability evaluations often test an AI agent from prepared states at ordered milestones. A clean sheet records no successes. What it certifies about a campaign…
- arXiv cs.AIagentsREALM: Identifying Minimal Task Assets for LLM Agents
arXiv:2610.39155v1 Announce Type: cross Abstract: Large language model (LLM) agents often receive access to more files, accounts, and services than a task requires. Prompt injection turns this excess access into an oppor…
- arXiv cs.AIresearchPRISM: Personalized Item Representations in User History
arXiv:2610.39175v1 Announce Type: cross Abstract: Sequential recommenders typically construct history inputs from item identifiers or content features using an embedding map shared across users. The same item therefore y…
- arXiv cs.AIagentsEmbodiExp: Compositional Experience Transfer for Embodied Agents
arXiv:2610.39180v1 Announce Type: cross Abstract: Experience can help embodied agents turn high-level plans into grounded actions, but transferring it across tasks remains challenging: previously effective strategies may…
- arXiv cs.AIresearchWhere Position Matters: Profiling-Guided Layer-Wise RoPE Allocation in Transformers
arXiv:2610.39223v1 Announce Type: cross Abstract: Rotary Position Embedding (RoPE) typically uses uniform coverage across Transformer layers despite heterogeneous positional requirements. Phase-off interventions reveal n…
- arXiv cs.AIresearchDeCoRL: Decomposed Consistency Reinforcement Learning for Multi-Image Composition
arXiv:2610.39265v1 Announce Type: cross Abstract: Multi-image composition (MICo) is a critical yet challenging capability for large-scale image editing models, where consistency degrades rapidly as the number of referenc…
- arXiv cs.AIresearchWorldFlow: Joint Video and 3D Motion Prediction via Large-Scale Pretraining
arXiv:2610.39278v1 Announce Type: cross Abstract: Predicting future physical states stands as a central challenge in embodied intelligence. Existing video world models leave 3D dynamics implicit, action-based formulation…
- arXiv cs.AIresearchThere Is No Free Lunch in RLVR: Every pass@1 Gain Has a pass@k Price
arXiv:2610.39295v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) makes a language model solve more problems on the first try and fewer when given many tries: it raises pass@1 while…