What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation
- 类型：arxiv
- 标识：2609.03254
- 链接：https://arxiv.org/abs/2609.03254
- 主分类：multimodal
- 形态：method
- TLDR：Large Language Models (LLMs) often help users generate artifacts through iterative cycles of generation and revision in conversation. A challenge here is that, when users specify only a local change during revision, LLMs must instead identify the relevant dependencies and propagate the revision to all affected parts of the artifact. This paper studies this ability of LLMs on conversationally generated artifacts, where the artifact context and its dependencies may be embedded in the conversation history. Toward practical use, we also explore cost-effective test-time compute for this new setting
- 待LLM分类：否
- 来源文件：
- /inbox/tom/_candidates/2026-09-08-agent-rag-longcontext-candidates.json