Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.07043 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918451017154560 |
|---|---|
| author | Qin, Tian Bai, Felix Hu, Ting-Yao Vemulapalli, Raviteja Koppula, Hema Swetha Xu, Zhiyang Jin, Bowen Cemri, Mert Lu, Jiarui Wang, Zirui Cao, Meng |
| author_facet | Qin, Tian Bai, Felix Hu, Ting-Yao Vemulapalli, Raviteja Koppula, Hema Swetha Xu, Zhiyang Jin, Bowen Cemri, Mert Lu, Jiarui Wang, Zirui Cao, Meng |
| contents | Human decision-making often involves constrained optimization. As LLM agents are deployed to assist with real-world tasks like travel planning, shopping, and scheduling, they must mirror this capability. We introduce COMPASS, a benchmark that evaluates whether LLM agents can perform constrained optimization in realistic travel planning settings. To success in these tasks, agents must engage in multi-turn conversations with user to gather task information as well as use tools to gather information from the database. Then agents must propose a solution that not only satisfies hard constraints but also optimizes user's utility objective. Evaluating state-of-the-art models, we reveal a significant feasible-optimal gap: while models achieve 70-90% feasibility (constraint satisfaction), they reach only 20-60% optimality (utility optimization). Our analysis shows that tool use is not the bottleneck. Instead, the core limitation is insufficient exploration of the search space, with success strongly correlating with information gathered. Coding agents show a promising approach to mitigate this gap. Together, COMPASS provides a testbed for developing LLM agents that can truly mirror human decision-making by both satisfying constraints and optimizing objectives. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07043 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | COMPASS: Benchmarking Constrained Optimization in LLM Agents Qin, Tian Bai, Felix Hu, Ting-Yao Vemulapalli, Raviteja Koppula, Hema Swetha Xu, Zhiyang Jin, Bowen Cemri, Mert Lu, Jiarui Wang, Zirui Cao, Meng Machine Learning Human decision-making often involves constrained optimization. As LLM agents are deployed to assist with real-world tasks like travel planning, shopping, and scheduling, they must mirror this capability. We introduce COMPASS, a benchmark that evaluates whether LLM agents can perform constrained optimization in realistic travel planning settings. To success in these tasks, agents must engage in multi-turn conversations with user to gather task information as well as use tools to gather information from the database. Then agents must propose a solution that not only satisfies hard constraints but also optimizes user's utility objective. Evaluating state-of-the-art models, we reveal a significant feasible-optimal gap: while models achieve 70-90% feasibility (constraint satisfaction), they reach only 20-60% optimality (utility optimization). Our analysis shows that tool use is not the bottleneck. Instead, the core limitation is insufficient exploration of the search space, with success strongly correlating with information gathered. Coding agents show a promising approach to mitigate this gap. Together, COMPASS provides a testbed for developing LLM agents that can truly mirror human decision-making by both satisfying constraints and optimizing objectives. |
| title | COMPASS: Benchmarking Constrained Optimization in LLM Agents |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.07043 |