Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
In this work, we investigate the effect of lookahead branching strategies in neural network verification. We present a general recipe to integrate lookahead into any branch-and-bound verifier and demonstrate how one of the current state-of-the-art branching heuristics, FSB, can be viewed as a special instantiation of the lookahead branching strategy.
High quality temporal graph benchmarks with rich semantics and ground-truth anomaly labels are essential for training graph neural networks, yet remain scarce due to privacy constraints and annotation costs. We present SAGA (Synthetic Agentic Graph Architecture), a system for generating large-scale, semantically rich temporal graphs via a four-phase pipeline.
An AI agent passed every metric in the eval harness I published, then the CFO killed it — its successful resolutions cost more than the humans it replaced. The one metric that predicts whether an agent survives production, and how to measure it without a rebuild.
Deep neural networks trained on natural images are shown to produce outputs consistent with human observers for brightness illusions. While this phenomenon has been documented across architectures, all evidence, to date, is measured at the output level: restored pixels, decoded trajectories, or classification decisions.
End-to-end autonomous driving models are now able to navigate complex road scenarios, mapping raw sensor observations directly to observed paths for open-loop evaluation and often effective driving in closed-loop evaluation. Yet the internal logic of these safety-critical systems remains largely opaque, due to the complexity of traffic scenes.
Everyone is talking about loop engineering, but most discussions assume an LLM sits at the center of the loop. I wanted to isolate the architecture itself.
Autonomous exploration of unknown 3D environments is traditionally driven by coverage-maximizing geometric heuristics. However, these methods typically determine exploration targets without considering the underlying structural context.
Hyperspectral image (HSI) classification systems are increasingly deployed on platforms with strict computational budgets, such as UAVs and small spaceborne sensors. In these settings, accuracy alone is not enough; the model must also run within tight latency and memory constraints.
arXiv:2607. 14890v1 Announce Type: new Abstract: Autonomous coding agents increasingly execute multi-step software work, but lifecycle states such as reviewed, tested, DONE, and ready-to-merge remain claims unless supported by current evidence.
arXiv:2607. 14287v1 Announce Type: cross Abstract: Defect segmentation in additive manufacturing (AM) X-ray computed tomography (XCT) images remains challenging due to severe class imbalance and large distribution shifts across scan conditions.
arXiv:2607. 14494v1 Announce Type: new Abstract: Complex knowledge base question answering (KBQA) is commonly approached through either information retrieval over a question-specific subgraph or semantic parsing into an executable logical form.
arXiv:2607. 14817v1 Announce Type: cross Abstract: Current evaluation of epistemic uncertainty relies on tasks such as out-ofdistribution detection and active learning.
arXiv:2607. 14336v1 Announce Type: cross Abstract: Trustworthy deployment of LLM-based agents in software systems requires evaluating how they perform on application-specific workflows, with enough granularity to localize where they succeed and fail.
arXiv:2607. 14108v1 Announce Type: cross Abstract: This paper introduces tool efficiency, a new quantitative metric to evaluate the rate of useful tool calls in an LLM agent trajectory.
arXiv:2607. 14105v1 Announce Type: cross Abstract: For Large Language Models to reliably answer user queries, users must clearly specify requirements, context, and constraints.
arXiv:2607. 14658v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) excel in general tasks, rigorous scientific reasoning remains challenging due to the limitations of monolithic, linear planning.
arXiv:2505. 17974v2 Announce Type: replace-cross Abstract: The Fisher information is a fundamental concept for characterizing the sensitivity of parameters in neural networks.
arXiv:2607. 14510v1 Announce Type: new Abstract: Industrial time series serve as the foundation for Prognostics and Health Management (PHM) to ensure the reliability and safety of industrial equipment such as aero-engines.
arXiv:2607. 14474v1 Announce Type: cross Abstract: This paper details the DS@GT ARC team's approach to BirdCLEF+ 2026, multi-label detection of animal vocalizations in soundscapes from the Pantanal wetlands.
arXiv:2607. 14341v1 Announce Type: cross Abstract: Robust robotic grasping remains a fundamental challenge for complex real-world applications.