AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchOSFP4: Joint Optimization of Diagonal Smoothing and Block Scales for NVFP4 Quantization
arXiv:2610.08231v1 Announce Type: new Abstract: NVFP4 is an attractive datatype for large language model (LLM) inference, offering compact storage and native tensor-core acceleration. However, preserving accuracy using N…
- arXiv cs.AIresearchSensor-Language-Action Models
arXiv:2610.08244v1 Announce Type: new Abstract: Sensors are useful not only for understanding the world but also for deciding what to do next. Existing sensor models however largely stop at perception: they recognize sta…
- arXiv cs.AIresearchLeanPlan: Optimal Planning with LLM-Generated Heuristics and Admissibility Proofs
arXiv:2610.08246v1 Announce Type: new Abstract: Frontier large language models (LLMs) can generate heuristic functions that guide search to achieve state-of-the-art performance in satisficing planning, where any plan is…
- arXiv cs.AIagentsMASC: A Multi-Agent Self-Calibration Framework with Latent Construct Alignment for Consistent Client Role-Playing in Psychological Counseling
arXiv:2610.08250v1 Announce Type: new Abstract: Large language models are increasingly used to simulate clients for counselor training and psychological counseling research, but reliable simulation requires clients to re…
- arXiv cs.AIresearchzkLLMPoT: Efficient Zero Knowledge Proof of Training for Large Language Models
arXiv:2610.08258v2 Announce Type: replace Abstract: Auditing the claimed outcomes of large language model (LLM) training is challenging when model weights and training data are private, while cryptographically proving th…
- arXiv cs.AIresearchCoDe-LoRA: Mitigating the Orthogonality Dilemma in Continual Learning of LLMs via Knowledge Consolidation and Decoupling
arXiv:2610.08312v1 Announce Type: new Abstract: Continual learning (CL) is essential for Large Language Models (LLMs) to sequentially adapt to evolving tasks. To mitigate catastrophic forgetting, recent advances implemen…
- arXiv cs.AIresearchThe Standardization Trap: Certifying Joint Label Processing in Tabular Foundation Models
arXiv:2610.08314v1 Announce Type: new Abstract: Linear regression and kernel smoothing offer tractable explanations of in-context learning: in both, the features determine the weight assigned to each context label. Howev…
- arXiv cs.AIagentsSCOPE: Certified Theorem Proving with a Language Model as the Policy Planner
arXiv:2610.08319v2 Announce Type: replace Abstract: In proof assistants such as Lean, a generated proof must pass machine compilation checks, so evaluation needs no human scoring. Direct generation fails on multi-step nu…
- arXiv cs.AIagentsMedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation
arXiv:2610.08327v3 Announce Type: replace Abstract: Large language models (LLMs) have shown promise in medical question answering and clinical reasoning, yet their improvement remains constrained by static parametric kno…
- arXiv cs.AIresearchAn AI-Assisted Formalization of the Poincar\'e Conjecture
arXiv:2610.08329v1 Announce Type: new Abstract: We present an AI-assisted Lean 4 formalization of the Poincar\'e conjecture. The project began with limited reusable formal infrastructure for the geometric analysis behind…
- arXiv cs.AIresearchMoF: Preference-Aware Mixture Modeling for Black-Box LLM Personalization
arXiv:2610.08330v1 Announce Type: new Abstract: Proprietary Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet aligning their outputs with diverse user preferences re…
- arXiv cs.AIresearchExplainable Failure Prediction and Prevention in Maritime
arXiv:2610.08363v1 Announce Type: new Abstract: Maritime systems operate in highly dynamic environments where unexpected equipment failures can compromise safety, reliability, and operational efficiency. Recent advances…
- arXiv cs.AIagentsTransect: Retaining Observability for Long-Horizon LLM Agent Evaluations
arXiv:2610.08364v2 Announce Type: replace Abstract: Frontier AI evaluations increasingly use open-ended, agentic, long-horizon tasks whose transcripts can span hundreds of pages of outputs and actions from complex multi-…
- arXiv cs.AIagentsEMHO: EMbodied Agent Harness Optimization via Experience Traces
arXiv:2610.08432v1 Announce Type: new Abstract: Improving embodied agents often focuses on optimizing the underlying model through training, while the surrounding agent harness that controls planning, context, and tool u…
- arXiv cs.AIresearchAssemState: Manual and Physical-State-Guided Reasoning for Zero-shot Furniture Assembly
arXiv:2610.08446v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have made significant progress in visual understanding, but precise 3D spatial reasoning integrated with physical environment remai…
- arXiv cs.AIresearchCylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation
arXiv:2610.08510v1 Announce Type: new Abstract: Paired translation between quasiperiodic physiological waveforms (i.e., recovering a target oscillatory signal from the source) is central to the interpretation of cardiova…
- arXiv cs.AIagentsHow Much Evidence Should a Coding Agent's Self-Correction Carry? Adaptive Dirichlet Evidence for Self-Distillation
arXiv:2610.08514v1 Announce Type: new Abstract: Execution feedback lets coding agents revise programs and learn from their own corrections. A correction's learning weight should reflect both the transitions supported by…
- arXiv cs.AIresearchToward Alignment Scaling Laws: A Framework and First Preregistered Measurements
arXiv:2610.08540v1 Announce Type: new Abstract: Whether alignment gets easier or harder as models grow is often argued from isolated findings, as if alignment were one property. We treat it as a family of measurable scal…
- arXiv cs.AIresearchAnyBottle: A Recipe to Only Keep the Concepts You Really Need
arXiv:2610.08552v1 Announce Type: new Abstract: Concept bottleneck models (CBMs) make predictions inspectable and intervenable by routing them through human-interpretable concepts, but originally required concept annotat…
- arXiv cs.AIresearchAdaptive Power Sampling for LLM Reasoning
arXiv:2610.08563v1 Announce Type: new Abstract: Sequence-level power sampling has recently emerged as a training-free approach to reasoning by sampling from a sharpened output distribution of a base large language model…
- arXiv cs.AIagentsMINDSET: Energy-based Schema Evolution for Long Conversational Agent Memory
arXiv:2610.08586v1 Announce Type: new Abstract: Long conversational agents have become essential in our daily lives. They must remember what was said long back in order to help us efficiently complete a task without need…
- arXiv cs.AIagentsRecursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness
arXiv:2610.08621v2 Announce Type: replace Abstract: Recent game design agents have made substantial progress in generating playable games. However, program correctness does not ensure an enjoyable experience for players.…
- arXiv cs.AIresearchParallel Predictive World Models for Accurate and Efficient Long-Horizon Planning
arXiv:2610.08627v1 Announce Type: new Abstract: Long-horizon world-model planning typically relies on autoregressive rollouts, where predicted states are repeatedly fed back into the model. This preserves temporal struct…
- arXiv cs.AIagentsSquidAgent: Parallelize Wisely, Coordinate Efficiently
arXiv:2610.08647v1 Announce Type: new Abstract: LLM-based agents solve complex multi-step tasks, but sequential execution incurs substantial latency. In principle, parallelizing work across multiple agents should yield n…
- arXiv cs.AIagentsParanoiaEval: Benchmarking Unnecessary Defensive Work in Agentic Coding
arXiv:2610.08662v3 Announce Type: replace Abstract: As coding agents increasingly undertake real-world work autonomously, judging whether their risk treatments are warranted has become important. Existing work evaluates…
- arXiv cs.AIagentsCoupled but Late: Turn-Taking Between Full-Duplex Speech Models in Unscripted Dialogue
arXiv:2610.08683v1 Announce Type: new Abstract: Full-duplex speech models are trained to converse with a person, but they are increasingly made to converse with each other, in self-play data generation, agent societies,…
- arXiv cs.AIagentsScienceClaw: Benchmarking Continual Self-Evolution of AI-for-Science Agents Across the Natural and Social Sciences
arXiv:2610.08691v1 Announce Type: new Abstract: Large language model agents are accelerating scientific automation, yet verified executions rarely become persistent program-level improvements, and existing evaluations do…
- arXiv cs.AIagentsnanoMuse: An Open-Source Personal Agent for Every Device You Own
arXiv:2610.08699v1 Announce Type: new Abstract: Assistants from 2011 answered and waited, and agents from 2023 did a task and stopped. In September 2026 Meta's Muse showed an agent for one person, with accounts, devices,…
- arXiv cs.AIagentsWorldSolver: Can LLM Agents Simulate the Physical Dynamics via Solver Generation?
arXiv:2610.08720v1 Announce Type: new Abstract: LLM-based agents are increasingly advancing scientific and engineering problem solving, with physics simulation emerging as a challenging yet practical testbed for reproduc…
- arXiv cs.AIagentsDoes an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus
arXiv:2610.08722v1 Announce Type: new Abstract: Many long-horizon agents compact their context on a global rule, usually a token budget, blind to what the agent was doing. We ask whether the agent's recent behaviour pred…
- arXiv cs.AIresearchVeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning
arXiv:2610.08761v1 Announce Type: new Abstract: Self-improving policies continually expose new failure patterns, changing what their judges must be able to verify. However, current fixed judges constrain both optimizatio…
- arXiv cs.AIagentsAgent in a Bottle: Can LLM Agents Turn Their Capabilities Into Cheap, Scalable Artifacts?
arXiv:2610.08775v1 Announce Type: new Abstract: Large language models (LLMs) can solve many narrow tasks, but querying them separately for millions of related instances can be prohibitively expensive. Can LLM agents auto…
- arXiv cs.AIresearchSherpa: Teaching LLMs to Teach Adaptively
arXiv:2610.08778v1 Announce Type: new Abstract: Large language models (LLMs) have become increasingly capable problem solvers, but being able to solve a problem is not the same as being able to teach it. Existing approac…
- arXiv cs.AIresearchOncoNoteBERT: A Foundation Representation Model for Natural Language Processing of Real-World Outpatient Oncology Notes
arXiv:2610.03829v1 Announce Type: cross Abstract: Real-world outpatient oncology notes contain specialised terminology, tumour staging expressions, treatment names, toxicity descriptions, and institution-specific de-iden…
- arXiv cs.AIresearchHow Much Do LLM-as-a-Judge Design Choices Matter? A Systematic Comparison of Prompt Designs, Rating Scales, and Models
arXiv:2610.05094v1 Announce Type: cross Abstract: Researchers increasingly use Large Language Models as judges (LLM-as-a-judge) to evaluate model outputs. Yet there are no standards for how to design these judges. Typica…
- arXiv cs.AIresearchWhen Can World Models Recover Physical Laws?
arXiv:2610.06877v1 Announce Type: cross Abstract: Accurate prediction does not establish that a world model has recovered a physical law: distinct dynamics can generate identical records under the same observation protoc…
- arXiv cs.AIresearchNeutrosophic Ensemble Classification for Uncertainty-Aware Bearing Fault Detection: Evidence from Laboratory and Variable-Speed Industrial Benchmarks
arXiv:2610.06880v1 Announce Type: cross Abstract: Machine learning classifiers for bearing fault detection produce scalar confidence scores that conflate confident errors with genuinely ambiguous predictions, and the con…
- arXiv cs.AIresearchComparative review of hybrid forecasting models for short-term prediction of building thermal load
arXiv:2610.06881v2 Announce Type: replace-cross Abstract: In this paper, a comparative review of different hybrid models for short-term forecasting of building thermal demand is carried out. Particularly, the assessment…
- arXiv cs.AIresearchLearning When to Refine: Long-Horizon Reinforcement Learning for Budgeted Neural-Operator PDE Solvers
arXiv:2610.06883v1 Announce Type: cross Abstract: Neural operators provide fast surrogates for time-dependent PDEs, but autoregressive deployment creates a refinement-allocation problem: prediction errors vary over space…
- arXiv cs.AIresearchDynamical low-rank equilibrium computation for stochastic games between advanced persistent threats and moving target defense
arXiv:2610.06885v2 Announce Type: replace-cross Abstract: Moving target defense (MTD) against advanced persistent threats (APTs) in industrial control systems (ICS) has well-established game-theoretic formulations, but t…
- arXiv cs.AIresearchZero-Shot Visualization: Exploring Text Corpora with User-Prompted Axes
arXiv:2610.06889v1 Announce Type: cross Abstract: We study the application of large language models (LLMs) to the visual exploration of textual corpora. We introduce zero-shot visualization (ZSV), a task in which users s…
- arXiv cs.AIresearchAxiom Satisfiability of Linear Rewards in Alignment
arXiv:2610.06892v1 Announce Type: cross Abstract: Learning from human preference data is the dominant route to aligning language models with human values. In linear social choice, where rewards are linear in a fixed feat…
- arXiv cs.AIresearchComponent and Dimension Sparsity in Transformer Refusal Mechanisms
arXiv:2610.06903v1 Announce Type: cross Abstract: Activation steering manipulates large language model behavior by intervening on internal activations, but the mechanistic basis of these interventions remains poorly unde…
- arXiv cs.AIresearchAttSVD:Prompt-Adaptive Low-Rank KV Cache Compression via Attention-Guided SVD
arXiv:2610.06927v1 Announce Type: cross Abstract: The key-value (KV) cache of autoregressive transformers grows linearly with context length and dominates memory at long context. Most training-free remedies evict low-imp…
- arXiv cs.AIresearchLearning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering
arXiv:2610.06950v2 Announce Type: replace-cross Abstract: Injecting skills into a frozen language model currently costs a million parameters and a reinforcement-learning pipeline. We introduce DecSteer, a System-1 decisi…
- arXiv cs.AIagentsVerdicts Without Annotated Evidence: Rejection Sampling or Label-Only Post-Training for Evidence Recovery?
arXiv:2610.06962v1 Announce Type: cross Abstract: In many review workflows the verdict is the only thing retained. The passages behind it are not marked, because that annotation costs far more than recording the decision…
- arXiv cs.AIagentsAPEX: Active Protection at Execution Boundaries for LLM Agents
arXiv:2610.06966v2 Announce Type: replace-cross Abstract: Indirect prompt injection (IPI) hides adversarial instructions in content that large language model (LLM) agents read at runtime. As agents compose heterogeneous…
- arXiv cs.AIresearchVisual-Invariance-Augmented Feature Optimal Alignment for Transferable Adversarial Attacks against Closed-Source MLLMs
arXiv:2610.06977v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples, especially in black-box settings where only open-source surrogate models…
- arXiv cs.AIresearchCrystalJev: calibrated foundation-model probabilities decide what to compute next in materials discovery
arXiv:2610.06985v2 Announce Type: replace-cross Abstract: Atomistic foundation models screen hypothetical crystals by thresholding predicted energies, an output that states neither how likely a candidate is to be stable…
- arXiv cs.AIresearchDART-ES: Difficulty-Aware Reweighting and Targeted Replay for Fine-Tuning LLMs with Evolution Strategies
arXiv:2610.06993v1 Announce Type: cross Abstract: Evolution Strategies (ES) enable memory efficient full parameter fine-tuning of large language models (LLMs) using only forward computation. However, standard ES uniforml…