RunningTab: Direct Workspace Interaction with Environment-Side Tabs

Key points

• Much knowledge work produces new deliverables from files a workspace already holds, and LLM agents are beginning to take such work over.1
• 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).1
• 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.1
• We validate RunningTab on three benchmarks with three LLMs, where it consistently outperforms plain DWI and baselines that keep the record in the model, while its tab usually holds the values a deliverable needs once seen.1

Sources (1)

• [1]RunningTab: Direct Workspace Interaction with Environment-Side Tabs
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 05:16 PM

  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.

  Much knowledge work produces new deliverables from files a workspace already holds, and LLM agents are beginning to take such work over.

Extractive summary: sentences quoted from the sources.