arXiv:2606. 08094v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies are typically shipped as Python/PyTorch stacks that assume a workstation-class GPU, a mismatch for the hardware on which robots actually run.
arXiv:2604. 13072v2 Announce Type: replace-cross Abstract: OpenClaw-style personal assistants extend LLM agents from isolated tool use to open-ended, stateful, and personalized software environments.
arXiv:2607. 22595v1 Announce Type: new Abstract: Mechanistic interpretability (MI) has emerged as a powerful approach for analyzing and intervening in inference computations, with a growing number of applications such as jailbreak attempt detection, truthfulness evaluation, and hallucination detection.
arXiv:2609.40284v1 Announce Type: cross Abstract: Computer use agents (CUAs), which use graphical user interfaces (GUIs) to complete tasks on a computer, have recently surpassed human performance on...
UniACE is a unified framework that standardizes the evaluation of large language model (LLM) agents by representing each benchmark as an instruction–tool–environment triplet and running models through a shared, task‑agnostic harness in isolated runtimes. It preserves native success criteria, offers an offline mode for dynamic‑resource tasks, and standardizes efficiency metrics, execution records, and failure attribution. Applying UniACE to 7 benchmarks across 24 domains and 15 models revealed significant score shifts, ranking reversals, and sensitivity to evidence representation, highlighting the impact of evaluation configuration on reported agent performance.
The paper introduces VLA-ULAP, a lightweight local action predictor that interleaves remote vision–language–action (VLA) calls with on‑edge inference. ULAP, with only 7.4 M parameters, predicts action chunks in a single pass using current views, proprioception, and action history, eliminating the need for VLA hidden states or server round‑trips. Experiments on Jetson Orin Nano and simulated benchmarks show that VLA-ULAP can remove 48.8–76.7 % of VLA calls while preserving 95–97.5 % of baseline success, and it outperforms local VLA‑acceleration alternatives in both inference time and energy consumption.
arXiv:2607. 01813v1 Announce Type: cross Abstract: Evaluation benchmarks are essential for assessing vision-language models (VLMs), but most multimodal benchmarks are static, making them vulnerable to temporal staleness, data contamination, and costly maintenance.
HoliBench is a modular benchmarking and deployment toolkit that jointly measures accuracy, latency, and energy for foundation models across a wide range of devices, from single-board computers to GPU servers. It provides a platform abstraction layer that calibrates cross-device measurements and supports multiple model modalities, inference engines, and quantization levels. Using HoliBench, the authors evaluated 20 models on 7 device types, revealing tradeoffs such as limited latency gains from quantization on low‑precision hardware and diminishing accuracy returns relative to energy consumption, while also showing that single-model profiles can predict multi-model pipeline performance within a few percent.
The paper introduces OmniEvaluator, a composable evaluation system designed to streamline reproducible testing of omni‑modal foundation models across text, image, video, and audio. It unifies disparate inference engines, prompt conventions, and metric implementations by providing a single interface that supports four inference backends, four evaluation frameworks, and over a thousand benchmarks. Each evaluation run is logged as an artifact for exact reproducibility, with results displayed on a shared dashboard; a federated mode allows GPU inference servers to be shared, and a lightweight verifier ensures stable scoring across engines and prompts without incurring API costs.
arXiv:2605. 21854v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have rapidly converged on a small set of architectural patterns: discrete-token autoregression (e.
Dooly is a profiling tool for large language model (LLM) inference that eliminates the need to re‑profile every operation for each configuration. By labeling input dimensions with taint propagation and only profiling operations missing from its latency database, Dooly builds a configuration‑agnostic, redundancy‑aware latency database that can be used as a drop‑in backend for simulators. In experiments across two GPU platforms, three attention backends, and multiple model architectures, Dooly achieves simulation accuracy within 5% MAPE for time‑to‑first‑token and 8% for total‑processing‑time while cutting profiling GPU‑hours by 56.4% compared to traditional methods.
arXiv:2606. 12344v1 Announce Type: new Abstract: General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not by itself satisfy the clean Docker workspace, patch, and prediction contract required for scoring.