Evaluating 12 state-of-the-art models, from 4B open-weight to frontier proprietary systems, shows that current models still lack robust visual tool-calling capability: even the best model achieves below 50% success rate, suggesting fundamentally different research directions for improving models at different capability levels.
Abstract
We introduce MM-ToolSandBox, a benchmark and evaluation framework for visually grounded tool-calling agents. The framework provides a stateful execution environment spanning 500+ tools across 16 application domains, supporting multi-image, multi-turn tasks where agents must ground progressively arriving visual inputs into executable tool calls while handling realistic conversational phenomena (goal revisions, error corrections, state mutations). An automated scenario generation pipeline produces diverse, visually grounded scenarios through information-flow-guided planning and multi-stage quality filtering, yielding 258 human-verified nominal scenarios and 50 variants targeting interactive UI applications. Evaluating 12 state-of-the-art models, from 4B open-weight to frontier proprietary systems, shows that current models still lack robust visual tool-calling capability: even the best model achieves below 50% success rate. Our failure analysis further reveals that visual precision, not only planning, is a primary bottleneck for capable models: 53% of failures stem from incorrect information extraction from images despite otherwise correct task workflows. A planning-to-precision crossover emerges with scale: smaller models fail at deciding what to do, while larger models fail at perceiving what they see, suggesting fundamentally different research directions for improving models at different capability levels. The framework and the benchmark are publicly available at https://github.com/apple/ml-mmtoolsandbox
Large language models (LLMs) rely on tool calling as a fundamental agent capability, enabling them to invoke external systems and complete tasks beyond text generation. However, clean end-to-end (E2E) success cannot identify where a tool-use failure originates or how it propagates through a call. We introduce ToolRobustBench, a stage-wise diagnostic benchmark for tool-calling agents, where a tool-calling agent is an LLM system that selects a tool, supplies structured arguments, and interprets its returned feedback. ToolRobustBench aligns four perturbation families with the tool-use pipeline: tool-interface, user-intent, tool-output/observation, and runtime-environment perturbations. It attributes failures to tool selection, schema grounding, argument binding, tool-output/runtime-feedback handling, and E2E task success. Experiments on 15,456 single-family instances across 7 models, 16 sampled local tools, 4 perturbation families, and 14 subtypes show high but non-uniform clean performance and substantial robustness degradation, with tool-output/observation perturbation the dominant bottleneck. Mixed-family experiments reveal non-additive failure patterns that are not explained by isolated single-family results. Thus, ToolRobustBench provides a deterministic and cascade-aware benchmark for diagnosing robustness beyond clean tool-calling accuracy;
E-Bench is introduced, a fully synthetic benchmark with 323 state-changing tasks across three product domains: Honor of Kings, QQ Music, and Tencent Meeting, and it shows that multi-step tool use remains challenging: Pass^3 stays below 60% for the strongest models, and even with code execution in the E-Bench-Code extension, reliability remains below 70%.
Weihuang Zheng, Tianyuan Zou, Eileen Ye et al.· 1 citation
Powerful code agents can execute scripts, call tools, and manage files, yet many important applications remain accessible primarily through graphical user interfaces. We argue that screenshot-and-click is an inefficient interface for software-operating agents: screenshots are state-incomplete, and GUI actions are brittle, semantically weak, and poorly matched to long-horizon planning. We introduce ASIL (Agent-Software Interaction Layer), an agent-native interface that exposes software through structured JSON observations and code-executable semantic actions, realized through the deepest feasible access path for each application. We instantiate ASIL across 15 applications and a benchmark of 300 single-application and 80 multi-application tasks. ASIL reaches above 80 with closed models while executing fewer than five actions per task. Under a repaired runtime and a 50-step screenshot budget, the same tasks yield 6.6 and 26.6 strict success under screenshot-and-click control, rising to 15.0 and 53.3 on an easier OSWorld-comparable band. Against application-native interfaces on matched tasks, ASIL exceeds LibreOffice's UNO API by 28-38 strict points but only matches draw.io's MCP content contract. The structured modality also suits training: small-scale SFT raises Qwen3.5-2B from 58.0 to 72.1 and Qwen3.5-9B from 66.6 to 80.4, and resource-limited on-policy RL further raises them to 74.4 and 82.2.
SyntheticAgentTraceQA is proposed, an execution- first framework for generating scalable supervision data for tool- augmented agents and shows that execution-grounded supervision improves tool execution behavior, reference-trace agreement, and answer-generation performance on the evaluated tasks.
Hafsa Ouajdi, Francesco Giannuzzo, Alaa Boukhary et al.· 1 citation· ⚡1
ICAE-Bench, a benchmark for evaluating coding agents under interactive project-building settings, starts from a fuzzy product requirement, simulating the dynamic paradigm with an automated User Agent, and introduces three key designs.
Zhongyuan Peng, Dan Huang, Chuyu Zhang et al.· 1 citation
Automated Program Repair (APR) has witnessed significant progress with the advent of Large Language Models (LLMs). However, as modern software systems increasingly expose rich graphical user interfaces, effectively leveraging visual information from bug screenshots has become essential for understanding bugs and generating accurate fixes in multimodal scenarios. Real-world issue reports frequently contain heterogeneous visual attachments including UI screenshots, IDE snapshots, GIFs, and text-centric images, each with distinct visual patterns and domain-specific semantics that impose substantial perceptual demands on MLLMs. Furthermore, bug screenshots often contain large expanses of uninformative and bug-irrelevant regions, distracting the model's attention and limiting patch diversity. To address these challenges, we propose VisualRepair, an MLLM-based framework for visual software issue repair comprising two core modules: Image Type-aware Tool Calling (ITTC), which classifies input images and dynamically invokes a tailored tool-calling chain for robust visual interpretation, and Dynamic Test-time Region Focusing (DTRF), which grounds multiple bug-related region candidates and refines them via an adaptive zoom-in and zoom-out strategy to improve fault localization and promote diverse patch generation. Extensive experiments on the SWE-bench Multimodal benchmark demonstrate that VisualRepair consistently outperforms state-of-the-art approaches. VisualRepair resolves 196 and 25 instances on the test and dev sets, respectively, surpassing the best baseline by 10 and 11 instances. These results highlight the effectiveness of type-aware visual understanding and region-focused localization for automated visual software issue repair.
Jingyu Xiao, Zhongyi Zhang, Haoran Hou et al.· 1 citation