mlsanityData to 14 Oct 2026

How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning

arXiv 2605.23023 ↗First posted 21 May 2026cs.MA cs.HCcited by 2

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

In orchestrated multi-agent systems, humans often struggle to manage plans due to their complexity and limited transparency. Existing approaches rely on outcome-level supervision, where users verify only final outputs without visibility into intermediate reasoning. We formalize a design space for human-LLM co-planning interactions along three axes: mode (semantic vs. structural), scope (global vs. targeted), and level (low vs. high-level edits). We realize it in AMBIPOM, a prototype supporting process-level supervision through both semantic and structural interactions. Through a user study, we characterize how users navigate this space, revealing hybrid workflows and effort-control-risk trade-offs; through a controlled benchmark, we analyze how LLMs revise plans under varying scope and revision strategies. Our findings yield design insights for more transparent, controllable, and effective human-AI co-planning. We release code and data at https://github.com/megagonlabs/ambipom.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 22 of its 53 references that are in the map. First posted on arXiv 21 May 2026.

Builds on

22 of 53 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025AIPOM: Agent-aware Interactive Planning for Multi-Agent Systems29 Sep
  2. 2025Multi-Agent Coordination across Diverse Applications: A Survey20 Feb
  3. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMs10 Jan
  4. 2024Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration20 Dec
  5. 2024Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning10 Jun
  6. 2024Understanding the planning of LLM agents: A survey5 Feb
  7. 2023A Survey on Large Language Model based Autonomous Agents22 Aug
  8. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents5 Jun

Other references · 14

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  3. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  4. 2023On the Planning Abilities of Large Language Models : A Critical Investigationcited by 312
  5. 2023Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?cited by 106
  6. 2025Interactive Debugging and Steering of Multi-Agent AI Systemscited by 68
  7. 2025Levels of Autonomy for AI Agentscited by 48
  8. 2024Cocoa: Co-Planning and Co-Execution with AI Agentscited by 39
  9. 2023Interactive Task Planning with Language Modelscited by 37
  10. 2023DirectGPT: A Direct Manipulation Interface to Interact with Large Language Modelscited by 32
  11. 2023Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processescited by 15
  12. 2025Traceability and Accountability in Role-Specialized Multi-Agent LLM Pipelinescited by 10
2 more
  1. 2025Dango: A Mixed-Initiative Data Wrangling System using Large Language Modelcited by 5
  2. 2025Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Modelscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Modelcited by 3
  2. 2026Position: AI Agents in Scientific Teams Should Be Studied as Human-Agent Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026From Process Loss to Assembly Bonus: Human-Grounded Diagnosis of Multi-Agent LLM Collaboration
  2. 2026From Human-Human Collaboration to Human-Agent Collaboration: A Vision, Design Philosophy, and an Empirical Framework for Achieving Successful Partnerships Between Humans and LLM Agents
  3. 2025Can LLM Agents Solve Collaborative Tasks? A Study on Urgency-Aware Planning and Coordination
  4. 2024A Human-Like Reasoning Framework for Multi-Phases Planning Task with Large Language Models
  5. 2025A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy
  6. 2026When AI Designs AI: Innovation or Imitation?
  7. 2024FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents
  8. 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems