…Benchmarking Agents from Real Workplace Sessions Published on Jun 22 Submitted by Kaiyan Zhang on Jun 23 #2 Paper of the day Frontis AI Authors: , , , , , , , Kaiyan Zhang Abstract EnterpriseClawBench presents a benchmark…
…A Live Agent Benchmark for Evolving Real-World Workflows (2026) Beyond Binary Correctness: Scaling Evaluation of Long-Horizon Agents on Subjective Enterprise Tasks (2026) AcademiClaw: When Students Set Challenges for AI Agents…
Papers arxiv:2607.28229 EMBL AI Librarian: Life-Sciences Knowledge Layer for AI Agents Published on Jul 30 Submitted by Luigi Sigillo on Aug 3 European Molecular Biology Laboratory Authors: Luigi Sigillo…
…Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Collaboration (2026) TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents (2026) MacAgentBench: Benchmarking AI Agents on Real-World macOS…
…Benchmarking Multilingual Long-Horizon LLM Agents (2026) Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields (2026) MacAgentBench: Benchmarking AI Agents on Real-World macOS…
…Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies (2026) VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions (2026) SimuWoB: Simulating Real-World Mobile Apps…
…Agent Systems (2026) Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI (2026) Understanding Agent-Reactive Bugs at the Model-Harness Boundary: An Empirical Study of LLM Agent…
…Haonan Dong , , , , , Abstract Autonomous agents exhibit distinct value systems from underlying language models, requiring new benchmarking approaches to assess alignment across diverse execution environments. AI-generated summary Autonomous agents have rapidly matured…
…A Multi-Agent Framework and Comprehensive Benchmark . We introduce PhySciBench , a benchmark for evaluating deep-research agents in the physical sciences, and DelveAgent , a modular multi-agent framework for more reliable autonomous…
…AI-generated summary Existing benchmarks for multimodal agentic search evaluate multimodal search and visual browsing, but visual evidence is either confined to the input or treated as an answer endpoint rather than…
