arXiv cs.AI· Jiawei Lu, Chen Zhang, Jinwei Lu, Yuanwei Song, Yuanfeng Song, Raymond Chi-Wing Wong·· 3 小时前AI 评分41
RSIV-Harness：面向开放域对话式文本到可视化的递归自我改进框架
RSIV-Harness: A Recursive Self-Improvement Harness Framework for Open-Domain Conversational Text-to-Visualization
AI 导读
一篇 arXiv 论文提出 RSIV-Harness，在保持语言模型权重不变的情况下，利用智能体自身失败记录对 agent harness 进行递归自我改进，并通过四层框架评估修订以兼顾灵活性与稳定性。
正文 · 原文
Abstract:Users often request charts without knowing which database or table holds the relevant data. Such requests may be ambiguous, and users may ask follow-up questions to deepen their analysis or iteratively refine existing charts. A useful assistant must therefore discover relevant data sources among heterogeneous databases, ask clarifying questions when needed, and track evolving user intent while preserving constraints established in earlier turns. Yet recent text-to-visualization agents typically rely on static agent harnesses that are predefined and remain unchanged despite recurring failures across tasks. To address this limitation, we introduce RSIV-Harness, which keeps the language model weights fixed and applies Recursive Self-Improvement to revise the surrounding harness from the agent's own failure traces. To balance flexible self-improvement with stability, we introduce a four-layer framework that evaluates proposed harness revisions through anchor and memory checks, refining those that pass and restoring the best validated harness otherwise. We further introduce ODAC-Vis, a benchmark with 640 tasks for Open-Domain, Ambiguous, and Conversational text-to-visualization that jointly evaluates open-domain data discovery, ambiguity resolution, multi-turn visualization refinement, and executable chart generation. Experiments show that a single round of RSIV-Harness improves all six evaluation metrics relative to the seed harness, with particularly large gains in executability (+28.02 points) and chart structure (+34.01 points), demonstrating the ability to learn from task-solving experience and turn recurring failures across tasks into substantial performance improvements.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.35316 [cs.AI] |
| (or arXiv:2610.35316v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35316 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiawei Lu [view email]
[v1]
Mon, 26 Oct 2026 12:16:14 UTC (4,473 KB)
来源：arXiv cs.AI · arxiv.org