…Unlike prior work that focuses on limited datasets or settings, MMDG-Bench unifies evaluation across multiple tasks, modalities, and real-world challenges, including corruption robustness, missing modalities, and model trustworthiness. the take…
…by Sajib Acharjee Dip on May 12 Virginia Polytechnic Institute and State University Authors: , , Abstract PlantMarkerBench presents a multi-species benchmark for evaluating literature-based plant marker evidence interpretation, assessing models on…
…Experiments across lexical, general-purpose, and reasoning-intensive retrievers show that aspect-aware and agentic evaluation expose behaviors hidden by standard metrics, while RTriever-4B substantially improves over its base model. View…
…A Platform for Prompt Injection Evaluation (2026) Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs (2026) Transient Turn Injection: Exposing Stateless Multi-Turn Vulnerabilities in Large Language Models…
…We further provide Workspace-Bench-Lite, a 100-task subset that preserves the benchmark distribution while reducing evaluation costs by about 70%. We evaluate 4 popular agent harnesses and 7 foundation models…
…Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks? Published on Jun 3 Submitted by taesiri on Jun 4 Authors: , , , Dongfu Jiang , , Hang Hua , , , , Lichi Li , , , , , , , , , Abstract AutoLab benchmark evaluates…
Papers arxiv:2605.26396 Advancing Creative Physical Intelligence in Large Multimodal Models Published on May 25 Submitted by Cheng Qian on May 28 University of Illinois at Urbana-Champaign Authors: , , , , , , , , , , , , Abstract Large…
…by taesiri on May 5 Authors: Junjie Yu , , , , , , , , , , , , , , , , , , , , , Abstract AcademiClaw presents a comprehensive benchmark for evaluating AI agents on complex academic tasks spanning multiple domains, revealing significant capability gaps in current models…
…on May 2 Submitted by 张道瑄 on May 6 Authors: Daoxuan Zhang , , , Abstract Embodied Search and Rescue task and benchmark are introduced to evaluate multimodal large language model-driven UAV agents in…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Reference-free faithfulness metrics verify each atomic claim a model makes against ground truth, and are increasingly used to evaluate grounded generation . We show…