RunningTab: Direct Workspace Interaction with Environment-Side Tabs

arXiv:2610.10444 · cs.AI, cs.CL · Submitted 2026-10-07 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-10-07

Updated: 2026-10-07

Code: https://github.com/earendil-works/pi

Terminology

• Direct Workspace Interaction — 35× in this paper
• Benchmark — 18× in this paper · explained in 2 episodes
• Agentic Search — 5× in this paper · explained in 1 episode
• Benchmarking — 5× in this paper · explained in 4 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Large Language Model — 3× in this paper
• Provenance — 3× in this paper · explained in 4 episodes
• Multi-Agent System — 2× in this paper · explained in 6 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Agent Memory — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• When Is Enough Not Enough? Illusory Completion in Search Agents
• A New Role for Relevance: Guiding Corpus Interaction in Agentic Search
• Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
• Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion
• LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks
• Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
• OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning
• MemGPT: Towards LLMs as Operating Systems
• GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks
• GrepSeek: Training Search Agents for Direct Corpus Interaction
• Is Grep All You Need? How Agent Harnesses Reshape Agentic Search
• Keyword search is all you need: Achieving RAG-Level Performance without vector databases using agentic tool use
• Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies
• OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation
• Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
• MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection