mlsanityData to 14 Oct 2026

StackPlanner: A Centralized Hierarchical Multi-Agent System with Task-Experience Memory Management

arXiv 2601.05890 ↗First posted 9 Jan 2026cs.AIcited by 13

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

Multi-agent systems based on large language models, particularly centralized architectures, have recently shown strong potential for complex and knowledge-intensive tasks. However, central agents often suffer from unstable long-horizon collaboration due to the lack of memory management, leading to context bloat, error accumulation, and poor cross-task generalization. To address both task-level memory inefficiency and the inability to reuse coordination experience, we propose StackPlanner, a hierarchical multi-agent framework with explicit memory control. StackPlanner addresses these challenges by decoupling high-level coordination from subtask execution with active task-level memory control, and by learning to retrieve and exploit reusable coordination experience via structured experience memory and reinforcement learning. Experiments on multiple deep-search and agent system benchmarks demonstrate the effectiveness of our approach in enabling reliable long-horizon multi-agent collaboration.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 33 of its 55 references that are in the map. First posted on arXiv 9 Jan 2026.

Builds on

33 of 55 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents11 Mar

Other references · 32

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  6. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  8. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  9. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  10. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  11. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  12. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
20 more
  1. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  2. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,251
  3. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  4. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  5. 2023GAIA: a benchmark for General AI Assistantscited by 1,128
  6. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  7. 2025DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agentscited by 248
  8. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 241
  9. 2024Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generationcited by 162
  10. 2025Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RLcited by 150
  11. 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automationcited by 131
  12. 2020GSum: A General Framework for Guided Neural Abstractive Summarizationcited by 129
  13. 2021ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mindcited by 58
  14. 2025Free-MAD: Consensus-Free Multi-Agent Debatecited by 29
  15. 2024TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systemscited by 28
  16. 2023HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responsescited by 25
  17. 2024KnowPO: Knowledge-aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language Modelscited by 20
  18. 2025Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analyticscited by 20
  19. 2024Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuningcited by 14
  20. 2024CoAct: A Global-Local Hierarchy for Autonomous Agent Collaborationcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 13.

13 papers.

Sort:

By area:

  1. 2026What Do Agents Learn from Trajectory-SFT: Semantics or Interfaces?cited by 6
  2. 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systemscited by 6
  3. 2026Toward a Theory of Hierarchical Memory for Language Agentscited by 5
  4. 2026DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text Detectioncited by 4
  5. 2026Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Imagescited by 3
  6. 2026TokenPilot: Cache-Efficient Context Management for LLM Agentscited by 3
  7. 2026ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Researchcited by 2
  8. 2026MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Expertscited by 2
  9. 2026LoongReflect: Boosting Long-Horizon Reflection in Search Agents via Global Perspective Distillationcited by 1
  10. 2026Harness-RL: Black-Box Reinforcement Learning with Action-Args Decoupling for Central-Agent Multi-Agent Harnessescited by 1
  11. 2026MemoryWalker: Stop Training Agents on Contexts They Never Sawcited by 0
  12. 2026Rethinking Multi-Agent Collaboration: When More Is Lesscited by 0
1 more
  1. 2026GenMem: Generative Symbolic Memory for Self-Evolving Harnesscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
  2. 2026LatentMem: Customizing Latent Memory for Multi-Agent Systems
  3. 2025Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory
  4. 2026MiTa: A Hierarchical Multi-Agent Collaboration Framework with Memory-integrated and Task Allocation
  5. 2026MemCo: Memory-Centric Collaboration for Generalizing LLM Agents to Unseen Environments
  6. 2026Learning to Share: Selective Memory for Efficient Parallel Agentic Systems
  7. 2026AMA: Adaptive Memory via Multi-Agent Collaboration
  8. 2026AdMem: Advanced Memory for Task-solving Agents