{
  "@context": "https://agentflare.org/schema",
  "type": "ScholarlyArticle",
  "tier": "L2-full",
  "title": "LLM Agents & Planning: Literature Digest",
  "description": "Large language model (LLM) agents planning has matured from single-step prompting into a broader research area spanning task decomposition, tool use, reflection, memory, and…",
  "canonical": "https://agentflare.org/scholar/llm-agents-planning-literature-digest.html",
  "category": "scholar",
  "updated": "2026-06-15",
  "generated_at": "2026-06-15T01:19:16.018Z",
  "facts": [
    {
      "label": "Papers",
      "value": "10"
    },
    {
      "label": "Field",
      "value": "large language model agents planning"
    },
    {
      "label": "Updated",
      "value": "2026-06-15"
    }
  ],
  "data": {
    "topic": "large language model agents planning",
    "papers": [
      {
        "title": "Large language model based multi-agents: A survey of progress and challenges",
        "url": "https://arxiv.org/abs/2402.01680",
        "year": ""
      },
      {
        "title": "Tptu: Task planning and tool usage of large language model-based ai agents",
        "url": "https://openreview.net/forum?id=GrkgKtOjaH",
        "year": ""
      },
      {
        "title": "AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation",
        "url": "https://dl.acm.org/doi/abs/10.1145/3690624.3709321",
        "year": ""
      },
      {
        "title": "Large language models for planning: A comprehensive and systematic survey",
        "url": "https://arxiv.org/abs/2505.19683",
        "year": ""
      },
      {
        "title": "Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents",
        "url": "https://arxiv.org/abs/2302.01560",
        "year": ""
      },
      {
        "title": "Llm-planner: Few-shot grounded planning for embodied agents with large language models",
        "url": "http://openaccess.thecvf.com/content/ICCV2023/html/Song_LLM-Planner_Few-Shot_Grounded_Planning_for_Embodied_Agents_with_Large_Language_ICCV_2023_paper.html",
        "year": ""
      },
      {
        "title": "On the prospects of incorporating large language models (llms) in automated planning and scheduling (aps)",
        "url": "https://ojs.aaai.org/index.php/ICAPS/article/view/31503",
        "year": ""
      },
      {
        "title": "On the planning abilities of large language models-a critical investigation",
        "url": "https://proceedings.neurips.cc/paper_files/paper/2023/hash/efb2072a358cefb75886a315a6fcf880-Abstract-Conference.html",
        "year": ""
      },
      {
        "title": "TPTU: large language model-based AI agents for task planning and tool usage",
        "url": "https://arxiv.org/abs/2308.03427",
        "year": ""
      },
      {
        "title": "Twostep: Multi-agent task planning using classical planners and large language models",
        "url": "https://arxiv.org/abs/2403.17246",
        "year": ""
      }
    ]
  },
  "analysis_md": "Large language model (LLM) agents planning has matured from *single-step prompting* into a broader research area spanning task decomposition, tool use, reflection, memory, and multi-agent coordination. Across the surveyed papers, a consistent theme is that LLMs are strongest when used as *planners embedded in systems*, rather than as standalone reasoners.[1][4][8]\n\n## From single-agent planning to multi-agent systems\n\n*Large Language Model based Multi-Agents: A Survey of Progress and Challenges* frames planning as one of the core capabilities that enabled LLMs to move from autonomous agents to multi-agent systems, where collaboration improves complex problem-solving and world simulation.[1][4][6]  \nThis line of work emphasizes system design: agent profiling, communication, and skill development matter as much as raw model quality.[6]  \nThe newer *Large Language Model Agent: A Survey on Methodology, Applications and Challenges* extends this view with a methodology-centered taxonomy that treats planning as part of a larger construction-collaboration-evolution pipeline.[7][8]\n\n## Planning methods: decomposition, selection, tools, reflection\n\nThe planning literature now clusters around several recurring mechanisms. The survey *Large language models for planning: A comprehensive and systematic survey* organizes prior work into task decomposition, plan selection, external modules, and reflection/memory, offering the clearest high-level map of the field.[1]  \n*Describe, explain, plan and select* shows how interactive planning can support open-world multi-task agents by having the model iteratively describe, explain, plan, and select actions.[5]  \n*Tptu: Task planning and tool usage of large language model-based ai agents* focuses on the ordering of tool use, highlighting that planning is inseparable from *action sequencing* in tool-augmented agents.[2]\n\n## Grounded and embodied planning\n\nFor embodied and grounded settings, *Llm-planner: Few-shot grounded planning for embodied agents with large language models* positions LLMs as planners for agents that must map language to environment-constrained actions.[6]  \n*AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation* shifts attention to training data and simulation, arguing that environment/task generation can strengthen planning ability by exposing agents to richer trajectories.[3]  \nAcross these works, planning is increasingly treated as *interactive, grounded, and feedback-driven* rather than static plan generation.[3][7]\n\n## Open problems\n\n- **Evaluation remains fragmented** across commonsense, tool-use, embodied, and multi-agent planning settings.[1][8]\n- **Communication protocols** for multi-agent planning are still underdeveloped, especially for maintaining distinct beliefs and shared intent.[6]\n- **Robustness under feedback** is limited; agents often need better mechanisms for revising plans when the environment changes.[7][8]\n- **Training data for planning** is scarce, motivating synthetic task/environment generation but raising coverage and realism questions.[3]\n- **Symbolic integration** is still immature; the surveys suggest stronger hybridization with classical planning and scheduling would improve reliability.[1][2]\n\n1. [Large language model based multi-agents: A survey of progress and challenges](https://arxiv.org/abs/2402.01680)\n2. [Tptu: Task planning and tool usage of large language model-based ai agents](https://openreview.net/forum?id=GrkgKtOjaH)\n3. [AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation](https://dl.acm.org/doi/abs/10.1145/3690624.3709321)\n4. [Large language models for planning: A comprehensive and systematic survey](https://arxiv.org/abs/2505.19683)\n5. [Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents](https://arxiv.org/abs/2302.01560)\n6. [Llm-planner: Few-shot grounded planning for embodied agents with large language models](http://openaccess.thecvf.com/content/ICCV2023/html/Song_LLM-Planner_Few-Shot_Grounded_Planning_for_Embodied_Agents_with_Large_Language_ICCV_2023_paper.html)\n7. [On the prospects of incorporating large language models (llms) in automated planning and scheduling (aps)](https://ojs.aaai.org/index.php/ICAPS/article/view/31503)\n8. [On the planning abilities of large language models-a critical investigation](https://proceedings.neurips.cc/paper_files/paper/2023/hash/efb2072a358cefb75886a315a6fcf880-Abstract-Conference.html)\n9. [TPTU: large language model-based AI agents for task planning and tool usage](https://arxiv.org/abs/2308.03427)\n10. [Twostep: Multi-agent task planning using classical planners and large language models](https://arxiv.org/abs/2403.17246)",
  "sources": [
    {
      "title": "Large language model based multi-agents: A survey of progress and challenges",
      "url": "https://arxiv.org/abs/2402.01680"
    },
    {
      "title": "Tptu: Task planning and tool usage of large language model-based ai agents",
      "url": "https://openreview.net/forum?id=GrkgKtOjaH"
    },
    {
      "title": "AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation",
      "url": "https://dl.acm.org/doi/abs/10.1145/3690624.3709321"
    },
    {
      "title": "Large language models for planning: A comprehensive and systematic survey",
      "url": "https://arxiv.org/abs/2505.19683"
    },
    {
      "title": "Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents",
      "url": "https://arxiv.org/abs/2302.01560"
    },
    {
      "title": "Llm-planner: Few-shot grounded planning for embodied agents with large language models",
      "url": "http://openaccess.thecvf.com/content/ICCV2023/html/Song_LLM-Planner_Few-Shot_Grounded_Planning_for_Embodied_Agents_with_Large_Language_ICCV_2023_paper.html"
    },
    {
      "title": "On the prospects of incorporating large language models (llms) in automated planning and scheduling (aps)",
      "url": "https://ojs.aaai.org/index.php/ICAPS/article/view/31503"
    },
    {
      "title": "On the planning abilities of large language models-a critical investigation",
      "url": "https://proceedings.neurips.cc/paper_files/paper/2023/hash/efb2072a358cefb75886a315a6fcf880-Abstract-Conference.html"
    }
  ],
  "related": [
    {
      "name": "Retrieval-Augmented Generation: Research Digest",
      "url": "https://agentflare.org/scholar/retrieval-augmented-generation-research-digest.html"
    },
    {
      "name": "AI Alignment & Safety: Research Digest",
      "url": "https://agentflare.org/scholar/ai-alignment-safety-research-digest.html"
    },
    {
      "name": "RLHF: Research Digest",
      "url": "https://agentflare.org/scholar/rlhf-research-digest.html"
    },
    {
      "name": "Multimodal Foundation Models: Research Digest",
      "url": "https://agentflare.org/scholar/multimodal-foundation-models-research-digest.html"
    },
    {
      "name": "Mechanistic Interpretability: Research Digest",
      "url": "https://agentflare.org/scholar/mechanistic-interpretability-research-digest.html"
    }
  ],
  "pricing": {
    "price_usd": 0.02,
    "method": "402",
    "endpoint": "https://cdn.aisa.one/api/v1/access/verify",
    "autopay_hint": "set crawlerAutoPrice=true with X-AISA-Crawler-Token",
    "onboarding": "https://cdn.aisa.one/cdn/guide.html"
  },
  "powered_by": "AISA — agent-native search, settlement & delivery (https://aisa.one)"
}