Paper Detail

EvoSpatial: Experience-Driven Skill and Tool Evolution for Spatial Reasoning Agents

Bin Yu, Shijie Lian, Zhaolong Shen, Xiaopeng Lin, Yao Zhang, Haishan Liu, Haotian Li, Yuliang Wei, Kai Hu, Yichao Du, Zhirui Zhang, Bailing Wang, Kai Chen

arxiv Score 13.8

Published 2026-10-12 · First seen 2026-10-14

Research Track A · General AI

Abstract

Tool-augmented vision-language agents compose perception and measurement to reason about spatial relationships, but effective execution also requires tracking geometric assumptions and checking intermediate evidence. Preserving this experience across tasks requires retaining procedural knowledge together with the computations it governs. We introduce EvoSpatial, an experience-driven framework that evolves a library of linked skills and tools. Our key insight is that successful and failed spatial trajectories reveal both how to compute and when to trust the result. EvoSpatial retrieves skills, reuses tools, and synthesizes reusable computational functions (generated helpers) during reasoning. After answer submission, supervised outcome feedback guides skill refinement and tool consolidation for subsequent tasks. Across 20 benchmarks, EvoSpatial attains the highest average score among the compared spatial agents, exceeding SpatialClaw by 4.0 percentage points. Further experiments show cross-benchmark transfer and improved reasoning through skill-guided distillation without external skills at evaluation. These results support accumulating spatial experience for both inference-time reuse and trajectory-based training.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{yu2026evospatial,
  title = {EvoSpatial: Experience-Driven Skill and Tool Evolution for Spatial Reasoning Agents},
  author = {Bin Yu and Shijie Lian and Zhaolong Shen and Xiaopeng Lin and Yao Zhang and Haishan Liu and Haotian Li and Yuliang Wei and Kai Hu and Yichao Du and Zhirui Zhang and Bailing Wang and Kai Chen},
  year = {2026},
  abstract = {Tool-augmented vision-language agents compose perception and measurement to reason about spatial relationships, but effective execution also requires tracking geometric assumptions and checking intermediate evidence. Preserving this experience across tasks requires retaining procedural knowledge together with the computations it governs. We introduce EvoSpatial, an experience-driven framework that evolves a library of linked skills and tools. Our key insight is that successful and failed spatial},
  url = {https://arxiv.org/abs/2610.16679},
  keywords = {cs.CV},
  eprint = {2610.16679},
  archiveprefix = {arXiv},
}

Metadata

{}