跳到正文
arXiv cs.AI· Zijian Zhang, Wenqing Tian, Qiang Liu, Liang Wang·· 10 小时前AI 评分38

Space-X:将线索编织成证据链的自进化空间推理智能体框架

Space-X: Self-Evolving Spatial Agents Weaving Clues into Evidence Chains

AI 导读

Space-X 是一个自进化空间推理框架,通过 Execution Agent 逐题获取、关联并判断证据,Control Agent 从执行轨迹中诊断证据链断裂并联合修订工具、接口、技能、记忆组织与决策规则。

正文 · 原文

View PDF HTML (experimental)

Abstract:Spatial reasoning connects visual observations, geometric estimates, and linguistic decisions into a coherent derivation. Yet tool-augmented agents often acquire evidence without clear targets, combine outputs under inconsistent object or reference-frame semantics, and misjudge evidence sufficiency. Thus, more tools or calls do not reliably improve reasoning. We introduce Space-X, a spatial-reasoning framework that self-evolves toward complete, continuous evidence-chain construction. An Execution Agent acquires, associates, and judges evidence per problem using role-specific memory. A Control Agent diagnoses evidence-chain breaks from execution traces and jointly revises tools, interfaces, skills, memory organization, and decision rules. This loop co-evolves capability and evidence use: evidence needs guide capability development; usable results guide actions. Across multiple benchmarks, Space-X yields gains with four base models. Relative to baselines, GPT-6-sol improves answer accuracy on ViewSpatial and MMSI by 50.39% and 23.07%, respectively; Gemini-3.8-Flash gains 47.50% and 25.22% on these benchmarks. This provides a unified route from fragmented spatial clues to traceable, derivable answers.
Subjects: Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.24004 [cs.AI]
  (or arXiv:2611.24004v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.24004

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Zijian Zhang [view email]
[v1] Wed, 18 Nov 2026 07:53:29 UTC (18,794 KB)

来源:arXiv cs.AI · arxiv.org