…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…
…Xinkai Ma , , , , , , , Qianqian Xie , , , , , , , , , Minghao Liu , , , , , Abstract A multimodal deep research benchmark and agent framework are introduced to evaluate and improve the factual reliability and visual alignment of automated report generation systems…
…This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long-horizon, economically valuable, real-world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts…
…Through controlled visual perturbations , existing multimodal judges frequently anchor on the response text instead of their own visual perception, leading to inconsistent and non-verifiable evaluations. To address this issue, we introduce…
…Scaling Deep Research Agents for Frontier Scientific Reasoning (2026) Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation (2026) InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search (2026) PaperScope…
…We formalize this challenge as Perception Deep Research and introduce WebEye, an object-anchored benchmark with verifiable evidence , knowledge-intensive queries , precise box/mask annotations , and three task views: Search-based Grounding…
…To study this setting, we construct two human-verified benchmarks, VRQABench for controllable spatial lookahead and OpenWorldQA for open-domain physical prediction, and propose Privileged-Future On-Policy Self-Distillation ( PF-OPSD…
…Hangui Lin , , , , , , , , Abstract Dynamic cross-modal coordination is integrated into reinforcement learning with verifiable rewards to improve visual reasoning in multimodal large language models by measuring attention shifts and aligning token roles…
…General Visual Agents (2026) SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills (2026) SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents (2026) SkillGen: Verified Inference-Time Agent Skill Synthesis (2026…
…ADAPT: Benchmarking Commonsense Planning under Unspecified Affordance Constraints (2026) From Where Things Are to What They Are For: Benchmarking Spatial-Functional Intelligence in Multimodal LLMs (2026) Affordance Agent Harness: Verification-Gated Skill…