… Open-sourced here: https://x-plug.github.io/ToolCUA/ View arXiv page View PDF Project page GitHub 32 Add to collection Community We introduce ToolCUA, an end-to-end agent for optimal GUI-Tool path orchestration, by leveraging an automated interleaved trajectory scaling pipeline and two-staged train… …
… The following papers were recommended by the Semantic Scholar API EnterpriseLab: A Full-Stack Platform for developing and deploying agents in Enterprises 2026 AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents 2026 AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-A… …
Papers arxiv:2605.09252 LLM Agents Already Know When to Call Tools -- Even Without Reasoning Published on May 10 Submitted by Chung-En, Sun on May 13 Authors: Chung-En Sun , , , , Abstract When2Tool benchmark identifies conditions under which tool calls are necessary for LLM agents, revealing that … …
… Across 8 multimodal deep search benchmarks, ODE improves the Qwen3-VL-8B agent from 24.9% to 39.0% on average, surpassing Gemini-2.5 Pro in standard agent-workflow setting 37.9% . …
… The following papers were recommended by the Semantic Scholar API Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents 2026 Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows 2026 Beyond Binary Correctness: Scaling Evaluation of Long-Horizon Agents on Subjective Ente… …
… The following papers were recommended by the Semantic Scholar API Small Model as Master Orchestrator: Learning Unified Agent-Tool Orchestration with Parallel Subtask Decomposition 2026 Utility-Guided Agent Orchestration for Efficient LLM Tool Use 2026 SWE-Shepherd: Advancing PRMs for Reinforcing Co… …
… The following papers were recommended by the Semantic Scholar API InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing 2026 HippoCamp: Benchmarking Contextual Agents on Personal Computers 2026 VisionCreator: A Native Visual-Generation Agentic Mode… …
… By unifying three disparate technologies, namely MCP, World Model, and Agent, we demonstrate that a "Bring Your Own World Model" BYOWM strategy allows agents to simulate state transitions and refine plans in a latent space before execution. …
… As LLMs become more capable in agentic loops, agents can continuously refine their behavior, including tool use and reasoning, based on feedback from the environment. …
… The following papers were recommended by the Semantic Scholar API 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: Verific… …
