독서리서치레이더투자 프레임워크
로그인 / 회원가입
전체기술제품투자상장시장기타

독서

2026-08-251 게시물

새로고침

Isolated review context saves 33% tokens

검증됨 2026-08-25 08:00 GMT+8

Put a search agent's final review in a separate context and it uses 33% fewer tokens while keeping comparable performance across four tests.

Previously search execution and final review were often carried by the same context, so the model was easily swayed by its own earlier decisions and the review could not be independent.

The authors claim a model that took part struggles to judge its own prior decisions objectively; with isolated contexts performance across the four tests was comparable and tokens fell 33%, measured by the authors themselves.

The result has not yet been reproduced or compared item by item by other teams, and cross-model reproduction and component-ablation experiments are still needed; it reports only an agent phenomenon and cannot be directly extrapolated to the same mechanism in human investors. The paper was submitted on 24 August, is marked EMNLP 2026, and its version and experimental claims are at arXiv:2608.23045.

출처:论文摘要、版本与实验主张

리서치

이 뷰에서 모든 콘텐츠를 확인했습니다

로그인 / 회원가입
독서리서치레이더투자 프레임워크