The authors designed a multi-agent coding system with distinct roles: a planner agent parses exemplar QA templates, a coder agent generates Python scripts that call a library of geometric utilities, and a reviewer agent validates outputs.
Multi-agent framework generates spatial QA data via code execution
Exemplar2VQA uses collaborative agents with geometric utilities to bypass LLM spatial reasoning flaws, producing scalable synthetic datasets.
Chinese Tech
Jiayu Ying · Qijian Tian · Ruijie Xu · Xinnan Zhu · Daoguo Dong · Jiachen Xu · +1 more
East China Normal University · Shanghai Jiao Tong University · Fudan University · Tencent
Research Digest··2 min read
Ying et al.
Why this paper
From Tencent and 3 others · Released code
In one line
Exemplar2VQA uses multi-agent coding to synthesize large-scale spatial QA data, improving MLLM performance.
What it released
Code
What we could check
- ✓Code link in the paper (github.com)
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors (2 noted)
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§