$A^3$-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Jian, He, Yu, Wang, Zhiyuan, Wang, Zhangqi, He, Kai, Xu, Fangzhi, Lin, Qika, Liu, Jun
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908764041379840
author Zhang, Jian
He, Yu
Wang, Zhiyuan
Wang, Zhangqi
He, Kai
Xu, Fangzhi
Lin, Qika
Liu, Jun
author_facet Zhang, Jian
He, Yu
Wang, Zhiyuan
Wang, Zhangqi
He, Kai
Xu, Fangzhi
Lin, Qika
Liu, Jun
contents Scientific reasoning relies not only on logical inference but also on activating prior knowledge and experiential structures. Memory can efficiently reuse knowledge and enhance reasoning consistency and stability. However, existing benchmarks mainly evaluate final answers or step-by-step coherence, overlooking the \textit{memory-driven} mechanisms that underlie human reasoning, which involves activating anchors and attractors, then integrating them into multi-step inference. To address this gap, we propose $A^3$-Bench~ https://a3-bench.github.io, a benchmark designed to evaluate scientific reasoning through dual-scale memory-driven activation, grounded in Anchor and Attractor Activation. First, we annotate 2,198 science reasoning problems across domains using the SAPM process(subject, anchor & attractor, problem, and memory developing). Second, we introduce a dual-scale memory evaluation framework utilizing anchors and attractors, along with the AAUI(Anchor--Attractor Utilization Index) metric to measure memory activation rates. Finally, through experiments with various base models and paradigms, we validate $A^3$-Bench and analyze how memory activation impacts reasoning performance, providing insights into memory-driven scientific reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2601_09274
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle $A^3$-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation
Zhang, Jian
He, Yu
Wang, Zhiyuan
Wang, Zhangqi
He, Kai
Xu, Fangzhi
Lin, Qika
Liu, Jun
Artificial Intelligence
Scientific reasoning relies not only on logical inference but also on activating prior knowledge and experiential structures. Memory can efficiently reuse knowledge and enhance reasoning consistency and stability. However, existing benchmarks mainly evaluate final answers or step-by-step coherence, overlooking the \textit{memory-driven} mechanisms that underlie human reasoning, which involves activating anchors and attractors, then integrating them into multi-step inference. To address this gap, we propose $A^3$-Bench~ https://a3-bench.github.io, a benchmark designed to evaluate scientific reasoning through dual-scale memory-driven activation, grounded in Anchor and Attractor Activation. First, we annotate 2,198 science reasoning problems across domains using the SAPM process(subject, anchor & attractor, problem, and memory developing). Second, we introduce a dual-scale memory evaluation framework utilizing anchors and attractors, along with the AAUI(Anchor--Attractor Utilization Index) metric to measure memory activation rates. Finally, through experiments with various base models and paradigms, we validate $A^3$-Bench and analyze how memory activation impacts reasoning performance, providing insights into memory-driven scientific reasoning.
title $A^3$-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation
topic Artificial Intelligence
url https://arxiv.org/abs/2601.09274