Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning
Multimodal large language models increasingly use visual chain-of-thought (Visual CoT) to reason about spatial, temporal, and embodied environments. By generating intermediate reasoning images, Visual CoT provides an intuitive mechanism for visual foresight but introduces substantial inference overh...
Improved Confidence Estimates for Black-Box Large Language Models
arXiv:2608.19323v1 Announce Type: new
Abstract: Uncertainty quantification (UQ) is essential for the safe deployment of large language models (LLMs). Existing methods, from verbalized confidence to ones requiring multiple generations, are often zero-shot and produce scores quantifying uncertainty w...
Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis
arXiv:2608.19297v1 Announce Type: new
Abstract: While multimodal large language models (MLLMs) excel in medical applications, most of them favor static images or short-term signals. In the critical field of dynamic electrocardiograms (ECG), models struggle with complex temporal reasoning and diagno...
Towards On-Board Implementation of ML-Based Helicopter Weight Estimator
arXiv:2608.19210v1 Announce Type: new
Abstract: This paper focuses on the implementation of a novel supervised Machine Learning model for estimating helicopter weight during takeoff, utilizing extensive datasets from Airbus's global in-service fleet. The study details a learning assurance process a...
H$^2$EDL: Hyper Evidential Deep Learning for Hierarchical Classification
arXiv:2608.18185v1 Announce Type: new
Abstract: Fine-grained recognition often involves hierarchical label spaces, where a model may be confident about a coarse semantic concept while remaining uncertain among its descendant classes. Such structured ambiguity requires uncertainty representations th...
Accelerating Visual On-Policy Distillation with Batched Speculative Jacobi Rollouts
arXiv:2608.18183v1 Announce Type: new
Abstract: Visual on-policy distillation (OPD) improves the training of compact visual autoregressive models by learning from trajectories generated by the current student. However, these online rollouts are still produced token by token with autoregressive deco...
Towards Reversible Forgetting: Managing Obsolete Knowledge in Continual Enterprise AI Agents
arXiv:2608.18177v1 Announce Type: new
Abstract: Continual learning has traditionally treated forgetting as a failure, emphasizing preservation of previously acquired knowledge as environments evolve. We argue that this objective is incomplete for enterprise AI agents operating in non-stationary env...
arXiv:2608.18147v1 Announce Type: new
Abstract: Adaptive stochastic quantization (ASQ) is a recently introduced quantization approach that optimizes the Mean Squared Error (MSE) for a given input while preserving unbiasedness. It is designed to alleviate the communication and memory bottlenecks of ...
Position: Current Model Cards Are Insufficient for Downstream Governance of Open-Weight Foundation Models
arXiv:2608.18086v1 Announce Type: new
Abstract: The growth of open-weight foundation models (OWFMs) has prompted the AI community to re-evaluate strategies for effective downstream governance. Although model cards have been widely adopted as transparency artifacts in model repositories, existing fr...
Position: Behavioral Systems Require Behavioral Tests
arXiv:2608.18081v1 Announce Type: new
Abstract: Artificial agentic systems increasingly operate as behavioral systems by interacting with dynamic environments, pursuing goals, and adapting over time. Yet, current evaluation methods largely focus on performance outcomes, not the underlying behaviora...
Position: Profiling Game Worlds by Transition Complexity
arXiv:2608.18079v1 Announce Type: new
Abstract: Game world modeling (GWM) and reinforcement learning (RL) are often confounded because research papers rarely quantify how difficult the underlying transition prediction problem is at the declared interface (pixels/tokens/latents with finite history)....
Position: Collusion Risks Among AI Reasoning Agents Justify Certification Requirements for Making Market Decisions
arXiv:2608.18078v1 Announce Type: new
Abstract: This position paper argues that AI agents with chain-of-thought reasoning capabilities are predisposed to exhibit collusive behavior and should be required to obtain behavioral certification before making decisions that affect economic markets. This i...
Scaling Laws for Mixture Pretraining Under Data Constraints
As language models scale, the amount of data they require grows – yet many target data sources, such as low-resource languages or specialized domains, are inherently limited in size. A common strategy is to mix this scarce but valuable target data with abundant generic data, which presents a fundame...
Multilingual Knowledge Transfer under Data Constraints via Lexical Interventions
Cross-lingual knowledge transfer is critical for building high-performing multilingual language models for languages with insufficient training data. When target language data is scarce, the knowledge required for many downstream tasks involving scientific reasoning, commonsense inference, and world...
The Problem Is the Problem: Towards Scalable Mathematical Discovery
arXiv:2608.16977v1 Announce Type: new
Abstract: AI systems are increasingly capable of contributing to mathematical research. In research practice, frontier-model reasoning is a limited resource, and expert mathematical review is even more sharply constrained. Allocating these scarce resources well...
The Price of Thinking: Reasoning Effort as a Model-Specific API Contract
arXiv:2608.16956v1 Announce Type: new
Abstract: API buyers purchase a dated contract, not a model name alone: the contract includes the requested and served model, reasoning-effort term or its omission, output rail, service product, prompt, and price schedule. We study the reasoning-effort term thr...
Runtime Governance for Agentic AI: Action-Boundary Control with Trusted Provenance and Fail-Closed Execution
arXiv:2608.16891v1 Announce Type: new
Abstract: Agentic AI systems request tool actions that can modify files, send messages, launch jobs, or change workflow state. This shifts the safety problem from harmful text generation to harmful operational side effects. Prompt-level governance can shape mod...
GxP-Agent: Process-DAG Topology for Reliable Clinical Trial Programming with LLM Agents
arXiv:2608.16890v1 Announce Type: new
Abstract: Clinical trial programming -- transforming study protocols into analysis-ready datasets under CDISC standards -- is a bottleneck in regulatory submissions, yet LLM-based code generation fails catastrophically on this task: across 11 single-shot attemp...
Benchmarking Classical and Transformer-Based Models for Document Sensitivity Classification
arXiv:2608.16928v1 Announce Type: new
Abstract: Automatic sensitivity classification of organizational documents is a critical yet underserved problem, where the consequences of misclassification range from regulatory violations to security breaches. While AI-based approaches offer a scalable alter...
Hierarchical Data Selection via Manifold Coverage and Sparse Feature Coverage in LLM Post-training
arXiv:2608.16927v1 Announce Type: new
Abstract: As supervised fine-tuning data continues to scale, selecting high-value subsets from large candidate pools is crucial for reducing training cost and improving model performance. Existing methods often measure diversity directly in the original embeddi...
Data-DPO: Direct Preference Optimization for Target Model Data Selection in LLM Post-Training
arXiv:2608.16926v1 Announce Type: new
Abstract: Data selection in supervised fine-tuning aims to select a small set of effective samples from large-scale candidate data, reducing training cost while preserving model performance. However, existing methods usually treat data value as a relatively sta...
Detecting and Discriminating Operator Misspecification in Hybrid PDE-Parameter Learning: a Reference-Free Instrument, with Discrimination Bounded In Sample
arXiv:2608.16925v1 Announce Type: new
Abstract: We build an instrument that reads, from a single fit and with no oracle, whether the operator a hybrid PDE-parameter estimator postulates is wrong-and separates that from a merely unidentifiable parameter. On one self-adjoint parabolic inverse problem...
The P-Completeness of Inverted Index Traversal: On the Complexity of Evaluating Boolean Query DAGs
Modern AI agents increasingly rely on search infrastructure to execute complex, neuro-symbolic reasoning workflows. These workflows often compile into deeply nested, non-monotonic Boolean queries over text fields. However, standard query evaluation strategies over inverted indices face severe theore...