# Do LLM Agents Execute the Plans They Declare? From Planning-Mode Declaration to Pattern-Specific Execution

arXiv: https://arxiv.org/abs/2609.38108 · HTML: https://mlsanity.com/paper/2609.38108/

## Key facts

- No citing papers in the map yet (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 15 of its 49 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 15 of 15)

- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels](https://mlsanity.com/paper/2603.19312/) (2026)
- [ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models](https://mlsanity.com/paper/2305.18323/) (2023)
- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [WebCanvas: Benchmarking Web Agents in Online Environments](https://mlsanity.com/paper/2406.12373/) (2024)
- [AgentOrchestra: Orchestrating Multi-Agent Intelligence with the Tool-Environment-Agent(TEA) Protocol](https://mlsanity.com/paper/2506.12508/) (2025)
- [Aegis: Automated Error Generation and Attribution for Multi-Agent Systems](https://mlsanity.com/paper/2509.14295/) (2025)
- [AdaJEPA: An Adaptive Latent World Model](https://mlsanity.com/paper/2606.32026/) (2026)
- [ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning](https://mlsanity.com/paper/2511.02424/) (2025)
- [What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignment](https://mlsanity.com/paper/2510.08847/) (2025)
- [AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints](https://mlsanity.com/paper/2606.05622/) (2026)
- [Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents](https://mlsanity.com/paper/2606.04874/) (2026)
- [Planner Matters! An Efficient and Unbalanced Multi-agent Collaboration Framework for Long-horizon Planning](https://mlsanity.com/paper/2605.02168/) (2026)

## Abstract (arXiv)

Large language models (LLMs) enable agents to solve long-horizon tasks by generating a plan and then executing it in an environment. However, successful planning requires two distinct capabilities: selecting an appropriate plan for the task and executing it faithfully. Existing planner--executor systems can fail at either stage, while final task success alone cannot distinguish selection from execution failures. We therefore study the Plan Declaration--Execution Gap and introduce Planning-as-Routing, where an LLM declares one of four planning modes: Predefined, Sequential, Hierarchical, or Search, and a deterministic router dispatches the task to the corresponding pattern-specific executor. Across four benchmarks and three LLMs, we find three consistent patterns. First, generic Plan+ReAct often fails to preserve declared planning structure, especially for longer plans: across three benchmarks, only (22)--(45%) of trajectories preserve it, whereas pattern-specific executors enforce the intended structure. Second, planning-mode effectiveness varies across environments and models: Search performs best on ALFWorld, Hierarchical on SWE-bench, and the strongest pattern can vary across models within the same benchmark. Third, the largest gains come from execution: pattern-specific executors improve task success from (0.48) to (0.92) on ALFWorld and from (0.36) to (0.44) on SWE-bench Verified over Plan+ReAct. Current LLMs, however, do not reliably select the strongest mode for each task, although few-shot examples improve selection in some benchmark--model combinations. Overall, reliable agent planning requires both effective mode selection and faithful execution: routing substantially closes the execution gap, while task-specific mode selection remains open.