paper-with-me

홈 › Papers

WMF-AM: Probing LLM Working Memory via Depth-Parameterized Cumulative State Tracking

2026-03-28 · Dengzhe Hou, Lingyu Jiang, Deng Li, Zirui Li, Fangzhou Lin, Kazunori D Yamada arxiv

Existing large language models (LLMs) evaluations use fixed-difficulty benchmarks that cannot adapt as models improve, and rarely isolate specific cognitive processes. We introduce Working Memory Fidelity-Active Manipulation (WMF-AM), a probe of cumulative state tracking, the ability to maintain and update intermediate results across K sequential operations within a single query, without a scratchpad. Unlike multi-step agent benchmarks that stress task orchestration, WMF-AM isolates within-pass cumulative load by parameterizing depth K. The core probe uses arithmetic accumulation on 28 models from 12 families (0.5B to frontier); a matched non-arithmetic extension (permissions, schedules, inventories) confirms the design generalizes beyond arithmetic. Three construct-isolation ablations confirm that cumulative load, not arithmetic skill or entity tracking, drives difficulty. We release WMF-AM as a lightweight, recalibratable diagnostic for characterizing where models degrade under cumulative load. Code and data can be accessed at https://github.com/dengzhe-hou/WMF-AM

📄 PDF Abstract BibTeX arXiv:2603.27343

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Transformer Working Memory Enables Regular Language Reasoning and Natural Language Length Extrapolation

2023-05-05 · Ta-Chung Chi, Ting-Han Fan, Alexander I. Rudnicky, Peter J. Ramadge

Unlike recurrent models, conventional wisdom has it that Transformers cannot perfectly model regular languages. Inspired by the notion of working memory, we propose a new Transformer variant named RegularGPT. With its no…

Learning to Remember, Forget and Ignore using Attention Control in Memory

2018-09-28 · T. S. Jayram, Younes Bouhadjar, Ryan L. McAvoy, Tomasz Kornuta 외

Typical neural networks with external memory do not effectively separate capacity for episodic and working memory as is required for reasoning in humans. Applying knowledge gained from psychological studies, we designed …

Are they human? Detecting large language models by probing human memory constraints

2026-03-10 · Simon Schug, Brenden M. Lake arxiv

The validity of online behavioral research relies on study participants being human rather than machine. In the past, it was possible to detect machines by posing simple challenges that were easily solved by humans but n…

(Frisch-Waugh-Lovell)': On the Estimation of Regression Models by Row

2023-11-27 · Damian Clarke, Nicolás Paris, Benjamín Villena-Roldán

We demonstrate that regression models can be estimated by working independently in a row-wise fashion. We document a simple procedure which allows for a wide class of econometric estimators to be implemented cumulatively…

regression

MeSH: Memory-as-State-Highways for Recursive Transformers

2025-10-09 · Chengting Yu, Xiaobo Shu, Yadao Wang, Yizhen Zhang 외 arxiv

Recursive transformers reuse parameters and iterate over hidden states multiple times, decoupling compute depth from parameter depth. However, under matched compute, recursive models with fewer parameters often lag behin…