…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…
…Benchmarking Causal Thinking of LLM Agents in Games (2026) TabCausal: Pretraining Across Causal Environments for Tabular Causal Discovery (2026) Benchmarking AI Agents for Addressing Scientific Challenges Across Scales (2026) Causal Scaffolding for…
…Can Agents Distill In-the-Wild Guides into Self-Evolving Skills? (2026) AgenticVBench: Can AI Agents Complete Real-World Post-Production Tasks? (2026) ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents…
…Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows (2026) SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents (2026) Skill Retrieval Augmentation for Agentic AI (2026) WildClawBench…
…Simulating Real-World Mobile Apps for Fast and Faithful GUI Agent Benchmarking (2026) Benchmarking AI Agents for Addressing Scientific Challenges Across Scales (2026) Please give a thumbs up to this comment if…
…The following papers were recommended by the Semantic Scholar API Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack (2026) Terminal Wrench: A Dataset of 331 Reward…
…View arXiv page View PDF GitHub 4 Add to collection Community TASTE is a new way to automatically create diverse, harder, and verified benchmarks for tool-using AI agents. Instead of writing…
…A Hierarchical Benchmark for Visual Website Development with Agent Verification (2026) WebTestBench: Evaluating Computer-Use Agents towards End-to-End Automated Web Testing (2026) Test-Driven AI Agent Definition (TDAD): Compiling Tool…
…Benchmarks as User-Driven Long-Horizon Coding Sessions Published on Jun 29 Submitted by Anisha Gunjal on Jul 1 Scale AI Authors: , , , Abstract SWE-Interact presents a testbed that evaluates coding agents…