AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchEliteTable: Self-Improving Program Search for Executable Control Policies
arXiv:2610.12536v1 Announce Type: new Abstract: EliteTable is a self-improving program-search algorithm guided by large language models (LLMs) that uses a fixed-capacity table of high-scoring solutions to guide new propo…
- arXiv cs.AIresearchMagicBeanStalk: Escaping the RLVR Zero Advantage Trap with Recursive Data Synthesis
arXiv:2610.12659v1 Announce Type: new Abstract: Data-centric scaling of RLVR has focused on collecting or generating verifiable training problems. However, corpus size alone does not determine whether the dataset provide…
- arXiv cs.AIresearchFaithful and Complete LLM-Assisted Automated Construction of Hierarchical Hardware Knowledge Graphs
arXiv:2610.12762v1 Announce Type: new Abstract: Hardware datasheets contain engineering specifications essential for component selection, system integration, and hardware compatibility verification. However, manual inspe…
- arXiv cs.AIresearchRepresentation Alignment from a Few Paired Data via Distilled Optimal Transport
arXiv:2610.12781v1 Announce Type: new Abstract: Aligning two independently pretrained unimodal encoders typically demands millions of paired examples. In this paper, we study the regime where only $N \sim 100$--$500$ pai…
- arXiv cs.AIresearchNeural networks are more modular than single neurons suggest
arXiv:2610.12842v2 Announce Type: replace Abstract: Neural networks routinely develop representations in which individual neurons contribute to multiple distinct functions, leading to the widespread view that such networ…
- arXiv cs.AIresearchTowards Defining, Measuring, and Leveraging Creativity in AI Applications
arXiv:2610.12845v1 Announce Type: new Abstract: Despite extensive research, computational creativity still lacks a conceptually grounded, practically relevant, and empirically applicable formal definition across contexts…
- arXiv cs.AIresearchMitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization
arXiv:2610.12855v1 Announce Type: new Abstract: On-Policy Self-distillation is a self-improvement paradigm that enables large language models (LLMs) to improve their capabilities by leveraging the same model as both teac…
- arXiv cs.AIresearchCollaborative Theory of Mind: Learning to Self-Revise by Anticipating User Responses
arXiv:2610.12872v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong individual task performance, yet still struggle to collaborate with users over extended, multi-turn interactions, for exampl…
- arXiv cs.AIresearchOne-Step Text Generation by Seq-Drifting
arXiv:2610.12879v1 Announce Type: new Abstract: Diffusion language models generate tokens in parallel, but still require multiple sampling steps to produce high-quality text. In this paper, we investigate whether a model…
- arXiv cs.AIresearchMind the Spatial Gap: A Benchmark for Geospatial Reasoning and Constrained Spatial Editing
arXiv:2610.12881v1 Announce Type: new Abstract: Understanding and manipulating spatial relations is fundamental to AI systems that reason about physical environments and construct grounded world models. However, existing…
- arXiv cs.AIresearchOGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models
arXiv:2610.12914v1 Announce Type: new Abstract: Vision-language-action (VLA) models have shown strong promise in robotic manipulation, yet their post-training still predominantly relies on trajectory-level supervised imi…
- arXiv cs.AIresearchDeFiRank: Federated Pairwise Ranking for Governance in Decentralized Financial Networks
arXiv:2610.12916v1 Announce Type: new Abstract: Existing governance approaches in decentralized financial networks rely on manual review processes conducted by human committees, which introduces subjective bias, creates…
- arXiv cs.AIresearchTeaching neural decoders with language
arXiv:2610.12921v1 Announce Type: new Abstract: Brain-computer interfaces decode neural activity, yet class-label supervision (CLS) leaves relationships among classes implicit. We propose Language as Supervision (LaS), w…
- arXiv cs.AIresearchCollaborative Learning and Reasoning over Model Slices
arXiv:2610.12927v1 Announce Type: new Abstract: Large language models (LLMs) excel across diverse tasks, benefiting from knowledge priors, in-context reasoning, and test-time computation. Despite these strengths, single-…
- arXiv cs.AIresearchLearning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training
arXiv:2610.12933v1 Announce Type: new Abstract: Large language models have achieved remarkable advances in complex reasoning. However, scaling reasoning post-training with ever-larger corpora can substantially increase t…
- arXiv cs.AIresearchMathVis: Can AI Reason through Drawing? A Benchmark for Mathematical Figure Generation
arXiv:2610.12954v1 Announce Type: new Abstract: This paper introduces MathVis, a benchmark designed to evaluate LLMs' ability to visualize frontier mathematical problems and perform diagram-assisted reasoning. The benchm…
- arXiv cs.AIresearchBeyond Semantic IDs: Finite-Beam Reachability and Continuous-Query Generation in Generative Recommendation
arXiv:2610.12977v1 Announce Type: new Abstract: Generative recommendation (GR) of social media platforms commonly retrieves items by autoregressively decoding discrete Semantic IDs (SIDs) with finite-width beam search. T…
- arXiv cs.AIresearchBenchmarking Embedding Geometries and Clustering Algorithms for Unsupervised Patent Claim Classification
arXiv:2610.12997v1 Announce Type: new Abstract: Prior-art retrieval systems are structurally organized around classification codes, making cross-code discovery difficult. This paper asks if an unsupervised representation…
- arXiv cs.AIresearchProvenance-Aware Belief Updating in Human-AI Feedback Loops
arXiv:2610.13008v2 Announce Type: replace Abstract: In repeated human-AI interaction, a single observation can be quoted, summarized, and returned to a model as multiple reports, making repetition look like independent c…
- arXiv cs.AIresearchAttention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMs
arXiv:2610.13078v1 Announce Type: new Abstract: Safety-aligned large language models (LLMs) remain vulnerable to jailbreaks and can over-refuse benign requests. Understanding these failures requires distinguishing harmfu…
- arXiv cs.AIresearchSWEAR: Section-Wise Efficient Audio Reasoning via Self-Rated Difficulty
arXiv:2610.13081v1 Announce Type: new Abstract: Recent work on large audio-language models (LALMs) explores adaptive reasoning to balance accuracy and efficiency. However, existing approaches often rely on coarse-grained…
- arXiv cs.AIresearchDoes Location Matter? A Black-Box Causal Audit Reveals Model-Dependent Audio Grounding in LALM Hallucination
arXiv:2610.13112v1 Announce Type: new Abstract: Large audio-language models (LALMs) frequently exhibit object hallucination, affirming absent sounds. The dominant mitigation, Audio-Aware Decoding (AAD), contrasts logits…
- arXiv cs.AIresearchLooking Ahead and Back: Anticipatory Generative Modeling for Road-Network Trajectories
arXiv:2610.13131v1 Announce Type: new Abstract: Trajectory generation underpins urban applications such as traffic management and urban planning. Within road networks, vehicle movement along road segments is largely dete…
- arXiv cs.AIresearchDP-MIND: Differentially private memory-guided Long context Inference
arXiv:2610.13132v1 Announce Type: new Abstract: LLM-as-a-Service has become a dominant paradigm for accessing large language models without requiring local deployment. However, the process raises severe privacy concerns…
- arXiv cs.AIresearchVIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs
arXiv:2610.13145v1 Announce Type: new Abstract: Large language models (LLMs) increasingly generate structured layouts and executable scene programs from natural-language instructions. However, executability does not impl…
- arXiv cs.AIresearchAdaC-GRPO: Towards Mastering Long-Horizon Visual Sudoku Puzzles via Adaptive Curriculum Learning
arXiv:2610.13184v1 Announce Type: new Abstract: While reinforcement learning with verifiable reward (RLVR) enhances reasoning in large language models, its efficacy in long-horizon multimodal tasks remains underexplored.…
- arXiv cs.AIresearchBoundaryEvo: Data-Model Co-Evolution at the Capability Boundary for Long-Chain Reasoning Distillation
arXiv:2610.13285v1 Announce Type: new Abstract: Distilling long-chain reasoning trajectories from large teacher models provides an effective way to improve the reasoning ability of small language models. However, existin…
- arXiv cs.AIresearchAlphaNIST: Emergent Assembly Skills from Binary Task Rewards
arXiv:2610.13354v1 Announce Type: new Abstract: The NIST Assembly Task Board #1 remains a challenging benchmark for learning-based methods in robotic manipulation. Over short horizons, it demands precise, contact-rich co…
- arXiv cs.AIresearchRegulaTutor: A Theory-Informed Framework for Long-Term Personalized Learning
arXiv:2610.13399v1 Announce Type: new Abstract: Long-term personalized tutoring requires language models to translate a learner's evolving history into appropriate instructional support. Existing LLM-based tutoring syste…
- arXiv cs.AIresearchLocal Diagnostics of Learned Event Representations for Anomaly Detection at the HL-LHC
arXiv:2610.13437v1 Announce Type: new Abstract: Anomaly detection, the identification of collision events that deviate from Standard Model expectations, is one of the most promising model-agnostic strategies for new-phys…
- arXiv cs.AIresearchSqueezeBench: Saturation-Resilient Evaluation of Mathematical Capability
arXiv:2610.13461v1 Announce Type: new Abstract: AI systems are making rapid progress in mathematics, but this progress is hard to measure. Benchmarks of solved problems saturate, and in benchmarks of open problems each p…
- arXiv cs.AIresearchBranching On-Policy Distillation
arXiv:2610.13481v1 Announce Type: new Abstract: On-policy distillation (OPD) provides teacher supervision on student-generated trajectories, but a single trajectory realizes only one continuation at each decision, limiti…
- arXiv cs.AIresearchRetrieval-Augmented Multimodal Language Model with Heterogeneous Evidence Integration for Clinical Prognosis
arXiv:2610.13510v1 Announce Type: new Abstract: Clinical prognosis requires integrating structured measurements, physiological waveforms, longitudinal history, and population context. We introduce PRISM (Population-Retri…
- arXiv cs.AIresearchCausal Effect Identifiability in Causal Abstractions: A Strict Hierarchy of Criteria
arXiv:2610.13520v1 Announce Type: new Abstract: Identifying causal effects from observational data typically requires a fully specified causal graph, an assumption that is often unrealistic in complex or high-dimensional…
- arXiv cs.AIresearchBeyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation
arXiv:2610.13521v2 Announce Type: replace Abstract: Multi-teacher on-policy distillation (MOPD) extends on-policy distillation (OPD) by routing domain-specific data to specialized teachers, integrating their capabilities…
- arXiv cs.AIresearchConstructing Pareto Frontiers of Optimal Reasoning Termination Methods for Overthinking in Reasoning Models
arXiv:2610.13570v1 Announce Type: new Abstract: Reasoning models can benefit from test-time scaling, but continued reasoning may become ineffective or harmful, a phenomenon termed overthinking. Evaluations against full t…
- arXiv cs.AIresearchMENTOR: Learning from Failure with On-Policy Pedagogical Intervention
arXiv:2610.13594v1 Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) is a key driver for Large Reasoning Models, but it is vulnerable to "zero-reward collapse", a training failure where a…
- arXiv cs.AIresearchLearning Size Independent Constraint Models from Input Data and Positive and Negative Example Solutions
arXiv:2610.13640v1 Announce Type: new Abstract: In this paper we describe a Constraint Acquisition Tool that generates size independent constraint programs from input data and positive and negative example solutions of m…
- arXiv cs.AIresearchA Step Harder, Not a Step Too Far: The Benefits and Limits of Curriculum Difficulty Progression in GRPO
arXiv:2610.13669v1 Announce Type: new Abstract: Curriculum learning typically organizes training samples from easy to hard. In GRPO, medium-difficulty samples are attractive for online selection because they are more lik…
- arXiv cs.AIresearchAdaptive DHiSparse: Speculative Decoding over a Load-Adaptive KV Hierarchy
arXiv:2610.13708v1 Announce Type: new Abstract: Long-context serving runs out of KV memory before the hardware reaches its useful throughput. HiSparse stores history in host memory and fetches only the selected entries,…
- arXiv cs.AIresearchA Privileged Teacher That Only Scores Cannot Search: Critique-Conditioned On-Policy Self-Distillation for Reasoning
arXiv:2610.13744v1 Announce Type: new Abstract: On-policy self-distillation promises to replace the sparse outcome signal of verifiable-reward RL with dense token-level credit: a teacher conditioned on the reference solu…
- arXiv cs.AIresearchUkrMeme: Multimodal Explainable Persuasion Detection in Ukrainian Memes
arXiv:2610.13783v1 Announce Type: new Abstract: Memes play a central role in modern online communication, especially in contexts of political conflict where visual and textual cues combine to convey persuasive messages.…
- arXiv cs.AIresearchStudying Comics at Scale with Artificial Intelligence: The PAGE Framework and Three Studies of American Comics and Japanese Manga
arXiv:2610.13840v1 Announce Type: new Abstract: Comics are one of the great visual records of the twentieth century: hundreds of thousands of pages in which a mass readership saw its leaders, its wars and its heroes. Mos…
- arXiv cs.AIresearchCan Language Models Play the Wikipedia Game?
arXiv:2610.13948v1 Announce Type: new Abstract: Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requires specialist ling…
- arXiv cs.AIresearchImagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination
arXiv:2610.02626v4 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models increasingly incorporate intermediate reasoning to improve robotic manipulation, yet existing approaches primarily reason abou…
- arXiv cs.AIresearchKairos: Toward a Byte-Level Foundation Model for Every Modality
arXiv:2610.12495v1 Announce Type: cross Abstract: Small language models trained on a single local machine leave little room for architectural trial and error. Kairos combines bidirectional gated-DeltaNet linear attention…
- arXiv cs.AIresearchEnergy-Efficient Spiking Neural Networks for Sensing-Aided Beam Prediction
arXiv:2610.12507v1 Announce Type: cross Abstract: Sensing-aided beam prediction can reduce the beam-training overhead of millimeter-wave (mmWave) systems by leveraging environmental information from complementary modalit…
- arXiv cs.AIresearchCircuitTree: Composing Circuits into A Syllable Transcriber
arXiv:2610.12520v1 Announce Type: cross Abstract: The goal of circuit discovery is to decompose a monolithic neural network into tiny modular subnetworks which are interpretable in the sense that each does an identifiabl…
- arXiv cs.AIresearchAutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of Edits
arXiv:2610.12545v1 Announce Type: cross Abstract: Autoregressive decoding is less suited to non-causally ordered data, e.g., cross-references or future dependencies, since their outputs cannot be revised post hoc, unlike…
- arXiv cs.AIresearchSelf-Preservation in Language Models
arXiv:2610.12602v1 Announce Type: cross Abstract: Continual learning (CL) seeks to adapt pretrained models while preserving prior capabilities. Yet the tasks supplied for preservation cover only part of what a model know…