mlsanityData to 7 Oct 2026

Agent Team Work Zone: An Automated, Persistent Workspace for Long-Lived Claude Code Agent Teams

arXiv 2607.22917 ↗First posted 24 Jul 2026cs.AI cs.LG cs.MAcited by 0

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Large Language Model (LLM) agents have significantly improved coding and programming workflows. Claude Code, in particular, is one of the most powerful LLM coding agents and is capable of conducting complex coding tasks. However, several drawbacks can undermine long-term agentic workflows. (1) Irrecoverable agent teams: The Agent Teams feature is powerful, but the working state accumulated by each teammate is lost and cannot be resumed once the process stops, for example, when a terminal is closed. (2) Compaction erodes working detail: Compaction condenses the conversation into a summary, causing an agent's working details to become vague. (3) Agentic "technical debt": Over time, a user's decisions and the agents' operations become trapped in compacted old chats, making the project increasingly difficult to maintain and review. (4) Heavy prompt writing: Assigning or handing off tasks requires users to repeatedly write long prompts to achieve the expected agentic performance. We propose ATWZ (Agent Team Work Zone), a filesystem-based operations layer built around Claude Code's native Agent Teams that addresses these problems. Its central design principle is to treat each agent and teammate as a human employee and preserve their important working state in files stored in a dedicated directory called a "workstation," together with the skills, hooks, and scripts that use and maintain these files. With ATWZ, an agent team can periodically back up its working state, allowing an agent's knowledge to be recovered after compaction. After a process ends, the team can be restored with a single command. These features also substantially mitigate the agentic "technical debt" described above. Moreover, within ATWZ, agent "employees" can send documents to one another, greatly reducing the effort required to write prompts.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 60 of its 74 references that are in the map. First posted on arXiv 24 Jul 2026.

Builds on

60 of 74 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024Large Language Model-Based Agents for Software Engineering: A Survey4 Sep
  2. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agents23 Jul
  3. 2024Agentless: Demystifying LLM-based Software Engineering Agents1 Jul
  4. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering6 May
  5. 2024Executable Code Actions Elicit Better LLM Agents1 Feb
  6. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation16 Aug
  7. 2023ChatDev: Communicative Agents for Software Development16 Jul

Other references · 53

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  6. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  7. 2020Scaling Laws for Neural Language Modelscited by 6,411
  8. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  9. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  10. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  11. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  12. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
38 more
  1. 2017Deep reinforcement learning from human preferencescited by 3,846
  2. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  3. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  4. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  5. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  7. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  8. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  9. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  10. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  11. 2023A Survey of Large Language Modelscited by 2,537
  12. 2022Emergent Abilities of Large Language Modelscited by 2,483
  13. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  14. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  15. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  16. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  17. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,838
  18. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  19. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  20. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  21. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  22. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  23. 2023A Survey on Evaluation of Large Language Modelscited by 1,227
  24. 2023AgentBench: Evaluating LLMs as Agentscited by 1,211
  25. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  26. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,134
  27. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  28. 2025OpenAI GPT-5 System Cardcited by 910
  29. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
  30. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  31. 2022Towards Reasoning in Large Language Models: A Surveycited by 593
  32. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 580
  33. 2023Tool Learning with Foundation Modelscited by 302
  34. 2024AutoCodeRover: Autonomous Program Improvementcited by 272
  35. 2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Surveycited by 164
  36. 2025Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?cited by 9
  37. 2026Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggerscited by 5
  38. 2026When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoningcited by 5

50 most cited of 53 All 53 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026TraceLab: Characterizing Coding Agent Workloads for LLM Serving
  2. 2026A Phased Workflow for Operating LLM-Based Coding Agents
  3. 2026AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace
  4. 2025AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities
  5. 2026AgentRadio: Passive Awareness for Long-Horizon Multi-Agent Collaboration
  6. 2026When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding
  7. 2026Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
  8. 2026Promises, Perils, and (Timely) Heuristics for Mining Coding Agent Activity