…Here, we introduce SciAgentArena, a systematic benchmark for evaluating AI agents in real-world scientific research scenarios drawn from emerging needs across multiple domains. SciAgentArena comprises approximately 200 tasks with stepwise verification…
…Can AI Agents Complete Real-World Post-Production Tasks? (2026) WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation (2026) AlphaEval: Evaluating Agents in Production (2026) RealClawBench: Live OpenClaw Benchmarks from…
…By temporally reversing real-world videos at zero cost as natural counterfactual samples, YoCausal establishes an arbitrarily extensible evaluation protocol. Level 1 introduces the Reverse Surprise Index (RSI), quantifying arrow-of-time…
…large tool ecosystems , where real-world tasks require discovering relevant tools, inferring implicit sub-goals , and adapting to dynamic environments over long horizons . However, existing benchmarks rarely evaluate planning under retrieval-limited…
…To systematically evaluate such proactive personalization in realistic interactions, we propose Ψ-Bench, a benchmark for assessing LLMs ' ability to influence realistic users through conversation. We design three real-world interaction scenarios…
…A Comprehensive Framework for Evaluating LLMs in Realistic Interactions (2026) T1-Bench: Benchmarking Multi-Scenario Agents in Real-World Domains (2026) WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation (2026…
…Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings (2026) OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation (2026) Vision2Web: A Hierarchical Benchmark…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Real-world data analysis is inherently iterative, yet existing benchmarks mostly evaluate isolated or short interactive tasks, leaving agents' ability to track evolving analytical…
…Overall, RoboStressBench provides a principled evaluation framework for diagnosing and improving VLM perception under real-world physical stress, supporting the development of more reliable embodied AI systems. View arXiv page View PDF…
…for evaluation benchmarks that capture the complexity of real-world development. Such environments typically involve both complex code and large-scale data (i.e., file system). However, existing benchmarks usually evaluate code…