Agentic Reasoning and Refinement through Semantic Interaction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912623435448320 |
|---|---|
| author | Tang, Xuxin Abulikemu, Rehema Krokos, Eric Whitley, Kirsten Wang, Xuan North, Chris |
| author_facet | Tang, Xuxin Abulikemu, Rehema Krokos, Eric Whitley, Kirsten Wang, Xuan North, Chris |
| contents | Sensemaking report writing often requires multiple refinements in the iterative process. While Large Language Models (LLMs) have shown promise in generating initial reports based on human visual workspace representations, they struggle to precisely incorporate sequential semantic interactions during the refinement process. We introduce VIS-ReAct, a framework that reasons about newly-added semantic interactions in visual workspaces to steer the LLM for report refinement.
VIS-ReAct is a two-agent framework: a primary LLM analysis agent interprets new semantic interactions to infer user intentions and generate refinement planning, followed by an LLM refinement agent that updates reports accordingly. Through case study, VIS-ReAct outperforms baseline and VIS-ReAct (without LLM analysis) on targeted refinement, semantic fidelity, and transparent inference. Results demonstrate that VIS-ReAct better handles various interaction types and granularities while enhancing the transparency of human-LLM collaboration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_02157 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Agentic Reasoning and Refinement through Semantic Interaction Tang, Xuxin Abulikemu, Rehema Krokos, Eric Whitley, Kirsten Wang, Xuan North, Chris Human-Computer Interaction Sensemaking report writing often requires multiple refinements in the iterative process. While Large Language Models (LLMs) have shown promise in generating initial reports based on human visual workspace representations, they struggle to precisely incorporate sequential semantic interactions during the refinement process. We introduce VIS-ReAct, a framework that reasons about newly-added semantic interactions in visual workspaces to steer the LLM for report refinement. VIS-ReAct is a two-agent framework: a primary LLM analysis agent interprets new semantic interactions to infer user intentions and generate refinement planning, followed by an LLM refinement agent that updates reports accordingly. Through case study, VIS-ReAct outperforms baseline and VIS-ReAct (without LLM analysis) on targeted refinement, semantic fidelity, and transparent inference. Results demonstrate that VIS-ReAct better handles various interaction types and granularities while enhancing the transparency of human-LLM collaboration. |
| title | Agentic Reasoning and Refinement through Semantic Interaction |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2510.02157 |