Year: 2026
Type: conference-paper
Abstract: Coding agents working on sequential maintenance tasks re-read the same files across related tasks, wasting more than a third of their input tokens on redundant context.The natural fix, caching file summaries, fails to reliably reduce cost: tool-use traces are consistent with agents over-relying on generic descriptions, skipping re-reads, and offsetting token savings with less effective downstream decisions, leaving net cost roughly unchanged.We introduce Prism, a content-hash-keyed file memory that augments summaries with bounded facets: identifier-grounded facts distilled from the agent's own prior reasoning.On 12 SWE-Chain dependency-upgrade chains, Prism reduces cost by 24.9% on GPT-5 and 9.9% on GPT-5.4-mini, while maintaining comparable aggregate Build+Fix F1.Against no memory, a summary-only ablation yields only a nominal 2.4% cost decrease that falls within runto-run variability, while a static Aider-style repo-map baseline costs substantially more at 13% over no memory.Two controlled ablations isolate the causal contributions: wiping the persistent store before every task raises cost by 37% over no memory, and replacing facets with a 3× larger unstructured summary raises it by 41%.Code
Authors: Ziyun Zhang, Yihao Liu, Yuzhe Zhang, Huaqian Cai
Institution: Peking University
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W7224445265