RunningTab: Direct Workspace Interaction with Environment-Side Tabs
[Sztuczna inteligencja] Autorzy: Jinheon Baek, Soyeong Jeong, Yumin Choi i 2 więcej
Much knowledge work produces new deliverables from files a workspace already holds, and LLM agents are beginning to take such work over. Through direct corpus interaction, an agent can search and read any of those files from a terminal with no indexing, and producing a deliverable from many of them in this way is what we call direct workspace interaction (DWI). Reaching the files, however, is only half the task: nothing keeps track of what the task asks for, what has been read, and what was listed but never opened, all of which slip through the context window without leaving a trace, so an agent may extract a figure and still deliver a report without it. To address this, we present RunningTab, a framework that equips direct workspace interaction with an environment-side tab: a per-task record of what the task still owes, kept by the environment alongside the agent. Specifically, the age…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja