AstroAgentBench: Evaluating Agentic Planning on Space Mission Planning Tasks
Weiyi Wang, Xinchi Chen, Jingjing Gong, Xuanjing Huang, Xipeng Qiu
Fudan University Shanghai Innovation Institute
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
Recent LLM-for-Space systems address mission planning, scheduling, operations support, simulator control, and autonomy, but their evaluations use different task contracts, control settings, simulators, and success criteria.We introduce AstroAgentBench, 1 a seven-family benchmark for executable space mission planning in the domains of scheduling, observation planning, constellation design, and relay support.For each case, an agent submits a planning artifact that is checked by an external verifier for schema, timing, geometry, resources, and mission value.Results report validity and normalized scores, with comparisons to task-specific solver references.Across five LLM agent systems and 35 held-out cases, the strongest systems approach or exceed solverreference scores on several families, while weaker systems often fail to produce highvalue valid plans and even strong systems lose quality on geometric, product-level, or designheavy tasks.Trace analyses separate two failure points: task-contract misformulation and weak solution construction.Successful runs instead calibrate agent-written implementations against verifier feedback and adapt search to case-specific structure.Ablations show that procedure injection and memory accumulation help selectively, when they supply the missing formulation, calibration, or search support.
逐年被引趋势
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
计算机 / AIAI-based Problem Solving and Planning
Artificial Intelligence Applications · Satellite Communication Systems
参考文献 37
此处列出前 3 条
引用本文 3
按被引量排序,此处列出前 3 条