AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchClosing the Loop: Practical Training Recipes for Looped Language Models
arXiv:2610.00673v1 Announce Type: cross Abstract: Looped language models increase effective depth by repeatedly applying a shared block of layers, but existing large-scale recipes require multi-stage training over trilli…
- arXiv cs.AIresearchLabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery
arXiv:2610.00675v1 Announce Type: cross Abstract: Evolutionary approaches to LLM-driven discovery often generate new programs from a small set of selected ancestors. This keeps contexts manageable but can omit useful evi…
- arXiv cs.AIresearchLearning Transferable Skills using Goal-Conditioned Bisimulation
arXiv:2610.00676v1 Announce Type: cross Abstract: Unsupervised skill discovery has emerged as a promising approach for leveraging reward-free datasets to pretrain general-purpose policies. However, current skill discover…
- arXiv cs.AIresearchHow Divergence Becomes Decision Flips in Compressed Language Models
arXiv:2610.00694v1 Announce Type: cross Abstract: Compression reports summarize how far a compressed language model moved from the dense one, usually by a KL divergence; a deployment that relies on the dense model's outp…
- arXiv cs.AIresearchInitialization Improves LLM-Driven Discovery
arXiv:2610.00707v1 Announce Type: cross Abstract: Large Language Models (LLMs) have been used for novel discovery of algorithms, theorems, drugs, and other tasks through the use of harnesses that prompt an LLM to iterati…
- arXiv cs.AIresearchSequential Functional Structured Tucker Compression for Large Language Model Attentions
arXiv:2610.00717v1 Announce Type: cross Abstract: Post-training compression of LLM attention is often formulated as independent matrix approximation, ignoring both the shared structure among attention projections and the…
- arXiv cs.AIresearchOuter Diversity of Condorcet Domains
arXiv:2610.00720v1 Announce Type: cross Abstract: A Condorcet domain is a set of rankings over a given candidate set, such that every election that consists only of (an odd number of) votes from the domain has a transiti…
- arXiv cs.AIresearchBenchmarking Generative Models for Near-Surface Data Assimilation on Real Station Observations
arXiv:2610.00728v2 Announce Type: replace-cross Abstract: Weather reanalysis products rely on computationally intensive numerical weather predictions followed by data assimilation that corrects the forecast toward observ…
- arXiv cs.AIresearchPersonalized Image Generation with Reasoning and Reflection
arXiv:2610.00737v1 Announce Type: cross Abstract: Personalized image generation has remained narrowly focused on conditional synthesis from curated visual exemplars, rather than capturing who a user is. In practice, howe…
- arXiv cs.AIresearchIncreasing Width Allows Greedy Layer-wise Training to Rival End-to-End Backpropagation in Self-Supervised Learning
arXiv:2610.00753v1 Announce Type: cross Abstract: End-to-end backpropagation has been the dominant mode of training in deep learning, allowing for the coordination of parameter updates across layers of a neural network.…
- arXiv cs.AIresearchPre-training interventions, ex post facto: Grafting model beliefs across checkpoints
arXiv:2610.00767v1 Announce Type: cross Abstract: Pre-training interventions are critical to alignment research, since beliefs formed during pre-training shape how a model generalizes from later training. One recently po…
- arXiv cs.AIresearchVideo Generation Models: A Survey of Post-Training and Alignment
arXiv:2610.00812v1 Announce Type: cross Abstract: Video generation has rapidly progressed from short, low-quality clips to high-resolution, long-duration sequences with complex spatiotemporal dynamics. Despite strong gen…
- arXiv cs.AIresearchTraining-Aware Target Coverage for Synthetic Data Selection
arXiv:2610.00814v1 Announce Type: cross Abstract: Synthetic data are increasingly used to scale LLM training, yet more synthetic data do not necessarily produce better models. Useful synthetic data must add information r…
- arXiv cs.AIresearchTabJoinBench: A Benchmark for Joinable Table Discovery
arXiv:2610.00817v1 Announce Type: cross Abstract: Join discovery aims to identify tables from large data repositories that can augment a query table with complementary information, enabling downstream tasks such as data…
- arXiv cs.AIresearchOn-the-fly Weight Generation: A Hypernetwork Proof of Concept on ARC-1D
arXiv:2610.00820v1 Announce Type: cross Abstract: General-purpose models can adapt to many tasks from context, while specialised models can execute individual functions with less capacity. Yet obtaining such specialists…
- arXiv cs.AIresearchVerbalized and Internal Probabilities Are Coupled in Large Language Models
arXiv:2610.00827v1 Announce Type: cross Abstract: Large language models carry an internal notion of uncertainty in their sampling distribution, i.e., the probabilities they place on generating one answer rather than anot…
- arXiv cs.AIagentsSHARPO: Segment-Level Credit Assignment for Agentic Reinforcement Learning
arXiv:2610.00838v2 Announce Type: replace-cross Abstract: Agentic reinforcement learning (RL) trains a large language model (LLM) to act over long, multi-step interactions. However, a single localized error can cause tas…
- arXiv cs.AIresearchContextual trajectory and incremental contextual displacement: Towards using LLMs to understand dynamic, utterance-specific meaning construction
arXiv:2610.00840v1 Announce Type: cross Abstract: Transformer-based large language models (LLMs) such as RoBERTa represent text using contextual word embeddings (CWEs), which alter the embeddings associated with each tok…
- arXiv cs.AIresearchGeometric Similarity in VLM Low-Level Vision Representations
arXiv:2610.00848v1 Announce Type: cross Abstract: Vision-language models (VLMs) have emerged as powerful candidates for universal vision backbones, with representative architectures including autoregressive (AR) models a…
- arXiv cs.AIresearchDon't Waste the Noise: Importance-Guided Perturbation Allocation under Joint Global and Local Constraints
arXiv:2610.00861v1 Announce Type: cross Abstract: Adversarial optimization under a shared $\ell_1$ budget requires deciding not only how much perturbation to use, but also where that limited budget should be spent. This…
- arXiv cs.AIresearchKinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models
arXiv:2610.00864v1 Announce Type: cross Abstract: In this paper, we study how to achieve one-step action generation in Robotic Foundation Models (RFMs), aiming to overcome the high inference latency of multi-step flow ma…
- arXiv cs.AIresearchRethinking Data Augmentation under Covariate Shift: Invariant-Guided Diffusion and Prototype Reweighting
arXiv:2610.00873v1 Announce Type: cross Abstract: In many industrial applications, 1) tabular data is scarce and imbalanced and thus requires synthetic expansion; 2) input distributions drift between training and deploym…
- arXiv cs.AIagentsFORALL-LEAN-AGENT for Auditable Reasoning in Formal Mathematics and Software Verification
arXiv:2610.00885v1 Announce Type: cross Abstract: Coding agents increasingly automate Lean proof development, but successful compilation alone does not establish that a candidate proves the intended statement under accep…
- arXiv cs.AIresearchMatch the Distribution, Not the Compute: Post-Training Multi-Token Prediction Heads
arXiv:2610.00888v1 Announce Type: cross Abstract: Multi-token prediction (MTP) improves the throughput of autoregressive generation by enabling the language model to draft multiple next tokens per forward pass, while a v…
- arXiv cs.AIagentsCross-Benchmark Transfer from RL on Agentic Coding Tasks
arXiv:2610.00890v1 Announce Type: cross Abstract: Coding agents often fail in the last mile: they build most of a feature but drop a requirement, test only the cases their implementation already handles, break behavior t…
- arXiv cs.AIresearchTOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models
arXiv:2610.00899v1 Announce Type: cross Abstract: Autoregressive Vision-Language-Action models often represent continuous robot actions as discrete token sequences, enabling action prediction with standard next-token obj…
- arXiv cs.AIagentsMean field games as a tool for AI safety: a worked example from the July 2026 Hugging Face incident
arXiv:2610.00902v1 Announce Type: cross Abstract: One way to make AI systems safe is to shape what the system is: its objective and dispositions. We take a complementary route: treat the agents' characteristics as partly…
- arXiv cs.AIresearchScrew Attention: Rigid-Body Algebra Inside a Transformer
arXiv:2610.00904v3 Announce Type: replace-cross Abstract: Learned manipulation policies rediscover from data the spatial relations that rigid-body mechanics supplies in closed form, which leaves them fragile to geometric…
- arXiv cs.AIagentsUnderstanding Issues, Causes and Solutions in Open-Source LLM-based Multi-Agent Systems
arXiv:2610.00905v1 Announce Type: cross Abstract: With the advancement of LLM-based multi-agent systems (MAS), an increasing number of opensource projects are adopting multi-agent architectures as the foundation of their…
- arXiv cs.AIresearchThe Geometry of Contextual Relations: Language Models Address Facts by Order of Mention
arXiv:2610.00910v1 Announce Type: cross Abstract: Human reasoning depends on how objects are related within propositions. \textit{How do relations organize the language representations of contextual contents?} We give an…
- arXiv cs.AIresearchReHoPER: Receding-Horizon Planning for Enhanced Reasoning
arXiv:2610.00940v1 Announce Type: cross Abstract: We propose ReHoPER, an inference-only, zero-shot method that improves large language models' reasoning by generating and answering intermediate questions along multiple p…
- arXiv cs.AIagentsGUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution
arXiv:2610.00948v1 Announce Type: cross Abstract: The executable harness surrounding a GUI model determines how observations are assembled, actions are executed, and verification, recovery, and termination are controlled…
- arXiv cs.AIresearchA Matched-Budget Audit Framework for Recaptioned Image-Text Supervision Distributions
arXiv:2610.00952v1 Announce Type: cross Abstract: Recaptioned image-text corpora are now standard for text-to-image (T2I) training, with vision--language model (VLM) captioners replacing sparse alt-text by dense descript…
- arXiv cs.AIresearchTwo Clocks in Diffusion MLLMs: When Answers Stabilize Before Rationales Unfold
arXiv:2610.00953v1 Announce Type: cross Abstract: An answer candidate in a masked diffusion MLLM can stabilize while its rationale is still unfolding. We distinguish retrospective stabilization of the logged candidate fr…
- arXiv cs.AIresearchStructure-agnostic Causal Representation Learning
arXiv:2610.00968v1 Announce Type: cross Abstract: Causal representation learning aims to discover robust features by exploiting the causal structure underlying data generation. Existing methods require specifying the cau…
- arXiv cs.AIresearchA Citation-Grounded Benchmark for Trustworthy Earnings Call Transcript Analysis with Large Language Models
arXiv:2610.00969v1 Announce Type: cross Abstract: Large language models (LLMs) have been increasingly used for financial document analysis, including earnings call transcripts (ECTs). Beyond generating standalone claims,…
- arXiv cs.AIresearchRelationVGGT: Visual Geometry Transformers for 3D Spatial Relation Segmentation
arXiv:2610.00970v2 Announce Type: replace-cross Abstract: Recent advances in 3D reconstruction have progressed from per-scene optimization to feed-forward inference, and semantic scene understanding has followed suit --…
- arXiv cs.AIresearchGeneralist Representation, Specialist Detection: TS-Router for Time-Series Anomaly Detection
arXiv:2610.00978v1 Announce Type: cross Abstract: Time-series anomaly detection (TSAD) is difficult to generalize across datasets because heterogeneous temporal dynamics imply different notions of normality and favor dif…
- arXiv cs.AIagentsCan AI Scientists Coordinate at Runtime?
arXiv:2610.00980v1 Announce Type: cross Abstract: Multi-agent AI scientists have shown improving performance across a diverse range of tasks. Yet a common approach is design-time agentic orchestration, which typically re…
- arXiv cs.AIresearchDivide-and-Remember: Recursive Action-Relevant Memory for Long-Horizon VLA Policies
arXiv:2610.00982v1 Announce Type: cross Abstract: Vision-language-action (VLA) models struggle on history-dependent manipulation tasks, where the current observation alone does not determine the action, and the policy ne…
- arXiv cs.AIresearchThe Devil Is in the Reconstruction Loss Scale: Rethinking Optimization in LLM Quantization
arXiv:2610.00983v1 Announce Type: cross Abstract: Post-training quantization (PTQ) methods typically use sequential quantization that partitions a pre-trained LLM into a series of units (e.g., transformer blocks), with o…
- arXiv cs.AIresearchDistilling Directional Verification
arXiv:2610.00997v1 Announce Type: cross Abstract: Knowledge distillation aims to transfer the factual knowledge of large language models to smaller models for efficient deployment. Yet a teacher may recall a relation in…
- arXiv cs.AIagentsGroundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents
arXiv:2610.01023v1 Announce Type: cross Abstract: Coding agents can return plausible patches that omit required behavior. These failures are hard to review because long traces and confident summaries often hide what was…
- arXiv cs.AIagentsIt Takes Workflows to Evolve Better Workflows
arXiv:2610.01026v1 Announce Type: cross Abstract: Tackling complex real-world tasks can exceed the capabilities of a single large language model (LLM), motivating the use of multi-agent workflows that coordinate speciali…
- arXiv cs.AIresearchOptimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise
arXiv:2610.01028v1 Announce Type: cross Abstract: Machine learning models often suffer performance degradation under subpopulation shift, particularly when spurious correlations cause models to rely on shortcut features…
- arXiv cs.AIresearchPosterior sampling by source-space MCMC via prior-based few-step transport maps
arXiv:2610.01034v1 Announce Type: cross Abstract: Bayesian inference increasingly uses informative but implicit priors represented only by samples, such as historical ensembles, simulator outputs, and pretrained generati…
- arXiv cs.AIresearchCapturing In-Context Learning Dynamics with Task Operators
arXiv:2610.01054v1 Announce Type: cross Abstract: In-context learning (ICL) enables language models to perform new tasks from demonstrations without weight updates. However, every ICL inference requires processing the fu…
- arXiv cs.AIresearchMOMAT: Mixture of Multiple Atlases for Low-Power Jailbreak Defense of Quantized LLMs
arXiv:2610.01058v1 Announce Type: cross Abstract: Quantized large language models are increasingly deployed on edge devices for their low latency and energy efficiency. However, model quantization weakens alignment safeg…
- arXiv cs.AIresearchJoinGR: Learning to Traverse Join Graphs for Table Retrieval
arXiv:2610.01064v1 Announce Type: cross Abstract: Retrieving the right tables is a prerequisite for Text-to-SQL over realistic databases. Dense table retrievers rank schema elements independently, but this ignores a key…
- arXiv cs.AIresearchJev-IDS: System One Models for Network Intrusion Detection
arXiv:2610.01079v1 Announce Type: cross Abstract: Machine-learning Network Intrusion Detection Systems (IDS) depend on substantial labeled datasets and task-specific training, whereas Large Language Models (LLMs) detecti…