Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911205284642816 |
|---|---|
| author | Yang, Dongjie Lu, Chengqiang Wang, Qimeng Ma, Xinbei Gao, Yan Hu, Yao Zhao, Hai |
| author_facet | Yang, Dongjie Lu, Chengqiang Wang, Qimeng Ma, Xinbei Gao, Yan Hu, Yao Zhao, Hai |
| contents | Unlike reasoning, which often entails a deep sequence of deductive steps, complex real-world planning is characterized by the need to synthesize a broad spectrum of parallel and potentially conflicting information and constraints. For example, in travel planning scenarios, it requires the integration of diverse real-world information and user preferences. While LLMs show promise, existing methods with long-horizon thinking struggle with handling multifaceted constraints, leading to suboptimal solutions. Motivated by the challenges of real-world travel planning, this paper introduces the Multiple Aspects of Planning (MAoP), empowering LLMs with "wide-horizon thinking" to solve planning problems with multifaceted constraints. Instead of direct planning, MAoP leverages the strategist to conduct pre-planning from various aspects and provide the planning blueprint for planners, enabling strong inference-time scalability by scaling aspects to consider various constraints. In addition, existing benchmarks for multi-constraint planning are flawed because they assess constraints in isolation, ignoring causal dependencies within the constraints, e.g, travel planning, where past activities dictate future itinerary. To address this, we propose Travel-Sim, an agent-based benchmark assessing plans via real-world simulation, thereby inherently resolving these causal dependencies. This paper advances LLM capabilities in complex planning and offers novel insights for evaluating sophisticated scenarios through simulation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_12421 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints Yang, Dongjie Lu, Chengqiang Wang, Qimeng Ma, Xinbei Gao, Yan Hu, Yao Zhao, Hai Artificial Intelligence Computation and Language Unlike reasoning, which often entails a deep sequence of deductive steps, complex real-world planning is characterized by the need to synthesize a broad spectrum of parallel and potentially conflicting information and constraints. For example, in travel planning scenarios, it requires the integration of diverse real-world information and user preferences. While LLMs show promise, existing methods with long-horizon thinking struggle with handling multifaceted constraints, leading to suboptimal solutions. Motivated by the challenges of real-world travel planning, this paper introduces the Multiple Aspects of Planning (MAoP), empowering LLMs with "wide-horizon thinking" to solve planning problems with multifaceted constraints. Instead of direct planning, MAoP leverages the strategist to conduct pre-planning from various aspects and provide the planning blueprint for planners, enabling strong inference-time scalability by scaling aspects to consider various constraints. In addition, existing benchmarks for multi-constraint planning are flawed because they assess constraints in isolation, ignoring causal dependencies within the constraints, e.g, travel planning, where past activities dictate future itinerary. To address this, we propose Travel-Sim, an agent-based benchmark assessing plans via real-world simulation, thereby inherently resolving these causal dependencies. This paper advances LLM capabilities in complex planning and offers novel insights for evaluating sophisticated scenarios through simulation. |
| title | Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2506.12421 |