AI 自动挑选的高价值内容
arXiv:2605.30512v1 Announce Type: new Abstract: Generating physics diagrams from text requires strict adherence to physical laws. While current generative models produce visually plausible outputs, they systematically hallucinate force vectors, ignore conservation laws, and violate geometric constr…
arXiv:2605.30542v1 Announce Type: new Abstract: World models for embodied AI must be physically viable: constructed to answer intervention queries by representing the physical structure governing action outcomes, rather than merely predicting future observations.
arXiv:2605.30563v1 Announce Type: new Abstract: Factored tasks are a classical planning representation that extends SAS+ with limited forms of disjunctive preconditions, conditional effects, and angelic nondeterminism.
arXiv:2605.30570v1 Announce Type: new Abstract: We investigate the application of MAP-Elites (a well-known quality diversity algorithm) to design levels for First-Person Shooter (FPS) games.
arXiv:2605.30576v1 Announce Type: new Abstract: Exploration in reinforcement learning for autonomous driving is inherently unsafe: agents must experience novel behaviors to learn, yet exploration can lead to collisions or off-road driving.
arXiv:2605.30621v1 Announce Type: new Abstract: LLM agents are increasingly deployed as systems built around editable external harnesses, including prompts, skills, memories and tools, that shape task execution without changing model parameters.
arXiv:2605.30637v1 Announce Type: new Abstract: Clinical decision-making (CDM) is central to real-world clinical workflows, where clinicians infer diagnoses, select treatments, or anticipate future health outcomes under incomplete evidence.
arXiv:2605.30664v1 Announce Type: new Abstract: Subgoal-based policy tree search, which uses a policy to guide search, is effective for complex single-agent deterministic problems but often relies on explicit subgoal generation that can incur substantial overhead and hinders scalability.
arXiv:2605.30680v1 Announce Type: new Abstract: Healthcare mechanisms are inseparable from the strategic provider response they induce: existing healthcare AI benchmarks hold this response fixed and so cannot evaluate mechanisms by the equilibrium they produce.
arXiv:2605.30738v1 Announce Type: new Abstract: Generalization across agentic tool-calling environments remains a central challenge for reliable agentic reasoning systems.
arXiv:2605.30747v1 Announce Type: new Abstract: Logical rules constitute a cornerstone of knowledge graph (KG) reasoning, valued for their interpretability and ability to model relational patterns.
arXiv:2605.30785v1 Announce Type: new Abstract: LLM agents increasingly face long-horizon tasks such as web search and deep research in real-world applications, where accumulated context can cause long-context degradation and reasoning failures.
arXiv:2605.30803v1 Announce Type: new Abstract: LLM judges are increasingly used to evaluate open-ended responses, but their scores depend strongly on the rubrics that condition them.
arXiv:2605.30824v1 Announce Type: new Abstract: Deep research tasks require LLMs to plan what to investigate, retrieve evidence, and synthesize long-form answers across multiple branches of inquiry.
arXiv:2605.30832v1 Announce Type: new Abstract: Recent advances in Large Reasoning Models have significantly improved chain-of-thought (CoT) capabilities via reinforcement learning (RL).
arXiv:2605.30838v1 Announce Type: new Abstract: LLM-powered search agents enable multi-step reasoning and tool use. However, these capabilities introduce retrieval-induced safety degradation, as harmful intents may decompose into seemingly innocuous sub-queries that lead to unsafe outcomes.
arXiv:2605.30861v1 Announce Type: new Abstract: Post-training for reasoning models typically combines supervised fine-tuning with reinforcement learning from verifiable rewards, most commonly with GRPO. However, this algorithm suffers from sparse rewards, limited exploration, and mode collapse.
arXiv:2605.30898v1 Announce Type: new Abstract: In real-world deployments of large language models (LLMs), balancing inference quality and computational cost has become a central challenge.
arXiv:2605.30900v1 Announce Type: new Abstract: Current multimodal models handle static image recognition well, but intuitive physical reasoning remains a weakness. Predicting how objects will move and interact from a single image is still difficult for these systems.
arXiv:2605.31021v1 Announce Type: new Abstract: Current alignment paradigms for generative artificial intelligence rely predominantly on monolithic benchmarking frameworks that reduce the plurality of human judgment to aggregated statistical baselines, thereby obscuring cultural, demographic, and c…
arXiv:2605.31023v1 Announce Type: new Abstract: This work addresses the problem of autonomous resource management in heterogeneous satellite cluster conducting Earth Observation (EO) missions including optical and Synthetic Aperture Radar (SAR) satellites.
arXiv:2605.31031v1 Announce Type: new Abstract: Relational reasoning lies at the heart of intelligence, but existing benchmarks are typically confined to formats such as grids or text. We introduce GraphARC, a benchmark for abstract reasoning on graph-structured data.
arXiv:2605.31100v1 Announce Type: new Abstract: We study Vector Linking: given two embedding clouds produced by different black-box encoders over partially overlapping datasets, recover cross-model object correspondences using only vectors.
arXiv:2605.31167v1 Announce Type: new Abstract: Assessing whether Large Language Models outputs are factually grounded, epistemically calibrated, and methodologically reproducible is a prerequisite for responsible AI deployment.
arXiv:2605.31254v1 Announce Type: new Abstract: Building on recent formalizations of root cause analysis for rare events (``outliers'') in structural equation models, we propose a formal definition of a causal pathway and discuss its testable implications.
arXiv:2605.31264v1 Announce Type: new Abstract: LLM agents are increasingly expected not only to complete isolated tasks, but also to carry bounded representations of human expertise, judgment, and interaction style.
arXiv:2605.31278v1 Announce Type: new Abstract: Reliable evaluation of agentic systems requires unbiased estimates with valid uncertainty, but standard practice navigates between costly human annotation and biased LLM-as-judge proxies.
arXiv:2605.31308v1 Announce Type: new Abstract: Agent benchmarks increasingly record rich interaction trajectories, yet evaluation often reduces each rollout to a pass rate or reward score.
arXiv:2605.31354v1 Announce Type: new Abstract: Modular visual reasoning systems increasingly rely on shared working memory for multi-step collaboration, yet the failure dynamics of intermediate state evolution in low-capacity regimes remain underexplored.
arXiv:2605.31365v1 Announce Type: new Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have led to promising progress in web agents.
arXiv:2605.31370v1 Announce Type: new Abstract: Abductive reasoning over knowledge graphs aims to generate logical hypotheses that explain observed entities or facts.
arXiv:2605.31410v1 Announce Type: new Abstract: Food-as-Medicine requires models to reason beyond what a dish is or what nutrition it contains: they must decide whether a concrete food choice is appropriate for a specific health condition.
arXiv:2605.31444v1 Announce Type: new Abstract: Reinforcement Learning (RL) enables autonomous agents to learn policies from experience, but realistic problems often involve enormous state spaces, making learning and generalisation challenging.
arXiv:2605.31468v1 Announce Type: new Abstract: Scientific research has traditionally been human-intensive, requiring researchers to coordinate literature, ideas, experiments, manuscripts, and review responses across long project cycles.
arXiv:2605.31492v1 Announce Type: new Abstract: Large language models (LLMs) often solve reasoning problems by generating intermediate traces that explore and revise partial solutions.
arXiv:2605.31581v1 Announce Type: new Abstract: The same arguments often need to be evaluated under different external regimes. An agent with influence over the regime has a strategic lever that standard formalisms do not directly capture.
arXiv:2603.22867v1 Announce Type: cross Abstract: Multimodal stacks that mix ViTs, CNNs, GNNs, and transformer NLP strain embedded platforms because their compute/memory patterns diverge and hard real-time targets leave little slack.
arXiv:2605.28918v1 Announce Type: cross Abstract: For sparse, structured reinforcement-learning tasks with semantic reward-function interfaces, LLM-generated reward shaping is better framed as debugging than one-shot generation.
arXiv:2605.30361v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) offer compelling energy efficiency on neuromorphic hardware, yet their training remains challenging because the discrete spike threshold is non-differentiable.
arXiv:2605.30362v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) hold promise for demonstrating superior learning and representation capabilities in deep models.
arXiv:2605.30363v1 Announce Type: cross Abstract: Regime shifts in financial markets reorganise the joint dynamics of asset prices and macro variables, breaking any single-regime calibration.
arXiv:2605.30364v1 Announce Type: cross Abstract: Radio-frequency (RF) fingerprinting identifies wire-less transmitters using hardware-induced imperfections present in baseband I/Q signals.
arXiv:2605.30365v1 Announce Type: cross Abstract: Retrieval-augmented text-to-music (TTM) systems augment underspecified user prompts using captions retrieved from a music caption dataset. This design introduces an integrity dependency on the music knowledge database.
arXiv:2605.30368v1 Announce Type: cross Abstract: Surrogate Safety Measures (SSMs) are extensively utilised in the evaluation of traffic risk in automated driving contexts.
arXiv:2605.30370v1 Announce Type: cross Abstract: From their inception in the 1950s, artificial neural networks (ANNs) started using the so-called point neuron model then prevalent in neuroscience, hoping that this analogy would allow for a better emulation of brain function.
arXiv:2605.30372v1 Announce Type: cross Abstract: Reservoir computing, a type of recurrent neural network, is a promising approach for temporal learning as it separates dynamic processing from the trained readout layer.
arXiv:2605.30375v1 Announce Type: cross Abstract: High-fidelity computational fluid dynamics is essential for aerospace design, but engineering-scale simulations of practical three-dimensional aircraft remain computationally expensive.
arXiv:2605.30376v1 Announce Type: cross Abstract: Modern time series architectures face a fundamental trade-off: channel-independent models scale well with increasing data volume but ignore critical inter-channel dependencies, while channel-dependent models are expressive but remain ``dimension-bou…
arXiv:2605.30381v1 Announce Type: cross Abstract: Deceptive alignment, in which models maintain accurate internal representations while deliberately producing false outputs, remains a central challenge in AI safety.
arXiv:2605.30383v1 Announce Type: cross Abstract: Scaling individual robot capabilities is common but costly. Here we investigate a system-level design question in real-world multi-robot coordination: given matched hardware budgets, does restructuring communication among robots yield larger gains t…
arXiv:2605.30385v1 Announce Type: cross Abstract: The purpose of this article is to provide validation to my deep neural network alternative in the context of LLMs.
arXiv:2605.30387v1 Announce Type: cross Abstract: Functional Magnetic Resonance Imaging (fMRI) provides non-invasive access to dynamic brain activity by measuring blood oxygen level-dependent (BOLD) signals over time.
arXiv:2605.30391v1 Announce Type: cross Abstract: Human reasoning has long been theorised to operate socially, not through isolated individual cognition, but through collective adversarial discourse, a framework known as the Argumentative Theory of Reasoning (ATR).
arXiv:2605.30393v1 Announce Type: cross Abstract: Public numeric benchmarks appear in pretraining, so an evaluation that conditions on a date may be measuring memorized recall rather than out-of-sample skill.
arXiv:2605.30394v1 Announce Type: cross Abstract: This paper introduces Code Bench, a benchmark capable of evaluating Large Language Models (LLMs) concise code generation abilities in 60 programming languages.
arXiv:2605.30406v1 Announce Type: cross Abstract: Recent research demonstrating AI systems exhibiting deception and shutdown resistance suggests that AI loss of control (LOC) is an urgent policy concern , yet current literature focuses almost exclusively on alignment and prevention.
arXiv:2605.30407v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated strong performance on general tasks, while often struggling to adapt to specialized domains without high-quality domain-specific data.
arXiv:2605.30409v1 Announce Type: cross Abstract: Real-time streaming video-to-video editing (V2V) is critical for interactive applications such as live broadcasting and gaming, yet it remains a formidable challenge due to the stringent requirements for temporal consistency and inference throughput…
arXiv:2605.30415v1 Announce Type: cross Abstract: We investigate how domain adaptation reshapes explanatory behavior in language models using historical cosmology as a controlled setting.
arXiv:2605.30434v1 Announce Type: cross Abstract: Real-world data analysis is inherently iterative, yet existing benchmarks mostly evaluate isolated or short interactive tasks, leaving agents' ability to track evolving analytical context over long horizons untested.
arXiv:2605.30447v1 Announce Type: cross Abstract: Calibration, the alignment of predicted probabilities with true outcome frequencies, is essential for reliable decision-making.
arXiv:2605.30452v1 Announce Type: cross Abstract: Many machine learning problems involve multiple inherent trade-offs that are best addressed by gradient-based multi-objective optimization (MOO) algorithms.
arXiv:2605.30454v1 Announce Type: cross Abstract: Tool-augmented LLM agents are vulnerable to prompt injection: a third party who controls part of the agent's context can plant instructions that the agent then executes as if they came from the user.
arXiv:2605.30461v1 Announce Type: cross Abstract: We present a distributed approach for constrained Multi-Agent Reinforcement Learning (MARL) that combines state-augmented policy learning with distributed consensus over dual variables.
arXiv:2605.30462v1 Announce Type: cross Abstract: Can a dataset be recognized from the spurious correlations it induces during training? We argue that datasets leave dataset-specific traces in a model's learned semantic correlation structure: incidental regularities that are predictive within a dat…
arXiv:2605.30486v1 Announce Type: cross Abstract: Spatio-temporal forecasting on sensor graphs is commonly tackled with a single backbone architecture applied uniformly across all nodes, although graph regions can exhibit different dynamics.
arXiv:2605.30509v1 Announce Type: cross Abstract: We present improved bounds for estimating discrete probability distributions under the $\ell_\infty$ norm. These include minimax bounds in expectation and high-probability tail bounds.
arXiv:2605.30510v1 Announce Type: cross Abstract: Brain cancer's severity necessitates precise brain tumor segmentation, which is crucial for effective brain tumor diagnosis. Manual identification, burdened by high costs, labor, and error risks, highlights the need for automated methods.
arXiv:2605.30523v1 Announce Type: cross Abstract: Recent work describes what transformers can and cannot compute through connections to boolean circuits, but existing results lack exact characterizations and are sensitive to modeling choices.
arXiv:2605.30529v1 Announce Type: cross Abstract: Sentence-embedding models for semantic search are overwhelmingly developed and evaluated on English corpora.
arXiv:2605.30557v1 Announce Type: cross Abstract: Spatial reasoning is a fundamental capability for vision-language models (VLMs) deployed in real-world environments.
arXiv:2605.30561v1 Announce Type: cross Abstract: Vision Language Models (VLMs) enable a unified model to solve various vision tasks through prompting. They have shown promising performance in semantic understanding.
arXiv:2605.30571v1 Announce Type: cross Abstract: Physical AI systems, including robots, autonomous vehicles, embodied agents and edge copilots, often run a different inference workload from cloud LLM serving: single-stream, batch-1 autoregressive decode, where one robot, camera feed or user sessio…
arXiv:2605.30581v1 Announce Type: cross Abstract: Industrial visual sim-to-real is often described as transferring from synthetic images to real images, but industrial deployment usually involves a broader mismatch between available evidence and required decisions.
arXiv:2605.30585v1 Announce Type: cross Abstract: Effective prognostics and health management of modern engines relies on accurate turbine gas temperature predictions and robust uncertainty quantification to ensure reliability and safety.
arXiv:2605.30589v1 Announce Type: cross Abstract: U.S. immigration law spans thousands of pages of official policy, federal regulations, and procedural guidance that change frequently and carry high stakes for petitioners who lack legal representation.
arXiv:2605.30590v1 Announce Type: cross Abstract: Two clinical AI systems can score nearly identically on coverage-based rubrics yet behave radically differently when their patient inputs change: one updates its recommendations to match the new clinical signal, while the other produces the same out…
arXiv:2605.30593v1 Announce Type: cross Abstract: Engine Health Management (EHM) depends on reliable forecasting of Remaining Useful Life (RUL) and on tracking thermal indicators such as turbine gas temperature (TGT).
arXiv:2605.30604v1 Announce Type: cross Abstract: Regulated cybersecurity workflows lack a runtime substrate that enforces organization-level scope across retrieval, tool calls, memory, findings, reports, and audit while remaining model-agnostic and locally deployable.
arXiv:2605.30611v1 Announce Type: cross Abstract: Scientific figures are among the most effective means of communicating complex research ideas, yet producing publication-quality illustrations remains one of the most labor-intensive parts of paper preparation.
arXiv:2605.30619v1 Announce Type: cross Abstract: Best-of-$N$ sampling is widely used to construct pairwise preference data: $N$ candidates are drawn from a base distribution, and the best is paired with a rejected response.
arXiv:2605.30625v1 Announce Type: cross Abstract: Inferring continuous probability paths from sparse snapshots is a fundamental challenge in domains like single-cell biology, where high-fidelity data acquisition is often destructive and constrained by prohibitive sequencing costs.
arXiv:2605.30628v1 Announce Type: cross Abstract: Universal LLM reliability is not a finite-library problem: across all possible tasks, tools, schemas, knowledge sources, and evaluator expectations, new intervention-distinguishable failure modes can appear without bound, so no finite intervention d…
arXiv:2605.30631v1 Announce Type: cross Abstract: While automated diagnosis systems have achieved remarkable success in computed tomography (CT)-based lung cancer screening, their development remains limited by the scarcity of diverse, annotated pulmonary nodule datasets.
arXiv:2605.30632v1 Announce Type: cross Abstract: We introduce Rationalize, a role-pair framework for shared semantic reasoning between humans and AI models in data-driven sensemaking.
arXiv:2605.30638v1 Announce Type: cross Abstract: We introduce Score Broadcast and Decorrelation (SBD), a principled framework for broadcast-based credit assignment for general families of differentiable losses.
arXiv:2605.30639v1 Announce Type: cross Abstract: Embodied agents have made strong progress in navigating to target objects, but reaching the goal vicinity does not guarantee that the agent has found the correct instance: subtle attribute differences (e.g., "white floral" vs.
arXiv:2605.30641v1 Announce Type: cross Abstract: Large language models (LLMs) can reveal and amplify societal biases during chain-of-thought (CoT) generation.
arXiv:2605.30646v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in clinical applications. However, their behavior remains highly sensitive to subtle linguistic variations, such as rephrasing or syntactic variation.
arXiv:2605.30651v1 Announce Type: cross Abstract: We study trajectory selection for reasoning distillation, where teacher-generated reasoning trajectories are selectively used as supervision for a student model.
arXiv:2605.30654v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as conversational partners for companionship, emotional disclosure, and interpersonal advice, but the social dynamics of these interactions can create harms that are not captured by capability-orien…
arXiv:2605.30667v1 Announce Type: cross Abstract: Software tools for reverse engineering executable binary files, such as Ghidra, enable malware analysts to safely conduct robust static analysis without having access to original source code.
arXiv:2605.30668v1 Announce Type: cross Abstract: Dialogue topic segmentation is critical in many human-AI collaborative applications which requires identifying heterogeneous boundary cues, including lexical transitions near utterance edges and semantic discontinuities across utterances.
arXiv:2605.30675v1 Announce Type: cross Abstract: Uncertainty Quantification is a large and growing subfield of large language model behavioral analysis.
arXiv:2605.30677v1 Announce Type: cross Abstract: Agentic software reverse engineering systems are vulnerable to prompt injection attacks placed into the source code of executable binary files.
arXiv:2605.30685v1 Announce Type: cross Abstract: AI is being used by people globally, but not everyone is using it in the same ways. Using a large-scale dataset of anonymized, de-identified, and privacy-scrubbed interactions with a widely available and free AI chatbot, we empirically characterize …
arXiv:2605.30686v1 Announce Type: cross Abstract: ReAct agents that interleave chain-of-thought reasoning with tool calls are increasingly deployed for real tasks such as scheduling, file retrieval, and data access.
arXiv:2605.30689v1 Announce Type: cross Abstract: Zero-shot Temporal Action Localization (ZS-TAL) aims to detect and locate previously unseen actions in untrimmed videos.
arXiv:2605.30698v1 Announce Type: cross Abstract: Vision-language models (VLMs) have achieved strong performance on visual question answering (VQA). To mitigate individual hallucinations and blind spots, aggregating diverse perspectives via multi-agent collaboration has emerged as a promising parad…
arXiv:2605.30711v1 Announce Type: cross Abstract: Agentic LLMs must continuously decide whether newly extracted facts should be added, merged with existing memories, or ignored, yet prior work has focused more on retrieval and storage than on principled write-side control.