arXiv:2608. 03327v1 Announce Type: new Abstract: Hybrid computer-use agents can act through screenshots or call text tools.
arXiv:2606. 02357v1 Announce Type: cross Abstract: Tool-augmented multimodal agents show strong benchmark gains, often taken as evidence that agents have learned to use tools.
arXiv:2608.28795v1 Announce Type: cross Abstract: Modern artificial-intelligence coding agents can be equipped with tools for checking their own work e.g. a linter, a boot probe, a shell, a screensho...
The paper introduces a coroutine-bridge harness that lets a language model emit a Python program to manage tool calls in the CAR-bench evaluation. By decoupling model invocations from tool round-trips, the approach reduces model calls to a median of two per task while maintaining seven agent turns, achieving a median latency of 1.8 s on a Cerebras gpt‑oss‑120b. The harness achieved 60.0 % Pass³ on the official hidden evaluation, outperforming the baseline by 4.5× and matching frontier-model agents on GPT‑5.5, all while keeping the prompt largely cached and minimizing input compute.
arXiv:2607.28225v2 Announce Type: replace Abstract: Agentic vision-language models (VLMs), which interleave textual reasoning with explicit tool calls such as cropping and code-based image manipulati...
Two prompts can request the same code change and produce the same correct patch, yet cause a coding agent to perform radically different kinds and amounts of work. We study this effect in a preregistered benchmark spanning 4,644 valid runs, 24 deterministic coding tasks, seven reasoning models, and two real agent harnesses.
arXiv:2609.24161v1 Announce Type: cross Abstract: As LLM agents increasingly interact with external tools through standardized protocols such as MCP, tool-interface design becomes a critical yet unde...
arXiv:2608. 08907v1 Announce Type: cross Abstract: Thinking with images allows a multimodal model to compensate for limited perception by invoking visual tools through code.
The paper introduces ASIL, an Agent‑Software Interaction Layer that replaces traditional screenshot‑and‑click interfaces with structured JSON observations and code‑executable semantic actions. ASIL is implemented across 15 applications and evaluated on 300 single‑application and 80 multi‑application tasks, achieving over 80% success with fewer than five actions per task. The structured interface also improves training efficiency, boosting performance of Qwen models from 58–66% to 72–80% with small‑scale supervised fine‑tuning and further gains with on‑policy reinforcement learning.
arXiv:2607. 10569v1 Announce Type: cross Abstract: Modern coding agents expose multiple tool surfaces -- IDE primitives, bash, and Model Context Protocol (MCP) code-execution -- and the field has shipped three contradictory claims about which one matters.
arXiv:2609.24362v1 Announce Type: new Abstract: Sandboxed computer environments support multi-step reasoning with tools, executable programs, and persistent files, yet their extension from language m...
arXiv:2607. 02436v1 Announce Type: cross Abstract: Agentic coding assistants are increasingly given extra capabilities, such as browser based testing tools and design oriented system prompts, on the assumption that more capability yields better software.
SheetMind is a Manager‑Action‑Reflection framework that evaluates how much spreadsheet agent performance derives from the agents themselves versus the shared action interface. In a controlled study on all 221 tasks of the SheetCopilot Benchmark, replacing the high‑level action API with primitive cell operations drops accuracy by 47.1 points, while adding a Reflection Agent improves performance by 4.5 points and a Manager by 1.4 points. The framework also shows that decomposition changes failure modes, reducing silent wrong outputs from 33% to 25%, and that GPT‑5 and GPT‑5‑mini achieve similar performance, whereas GPT‑3.5 underperforms significantly.