Generalizability of Large Language Model-Based Agents: A Comprehensive Survey
ACM Computing Surveys · 31.07.2026 · 58 (10) · 1-44
DOI: 10.1145/3794858 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 02.04.2026. Verfasst von Minxing Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 144 Literaturangaben. Gefördert von: NSF, Learning Engineering Virtual Institute, NSF Graduate Research Fellowship Progra.
Abstract (Originalsprache)
Large Language Model (LLM)-based agents have recently emerged as a new paradigm that extends the capabilities of LLMs beyond text generation to dynamic interaction with external environments. A critical challenge lies in ensuring their g eneralizability – the ability to maintain consistently high performance across varied instructions, tasks, environments, and domains, especially those different from the agent’s fine-tuning data. Despite growing interest, the concept of generalizability in LLM-based agents remains underdefined, and systematic approaches to measure and improve it are lacking. We provide the first comprehensive review of generalizability in LLM-based agents. We begin by clarifying the definition and boundaries of agent generalizability. We then review existing benchmarks. Next, we categorize strategies for improving generalizability into three groups: methods targeting the backbone LLM, targeting agent components, and targeting their interactions. Furthermore, we introduce the distinction between g eneralizable frameworks and g eneralizable agents and outline how generalizable frameworks can be translated into agent-level generalizability. Finally, we identify future directions, including the development of standardized evaluation frameworks, variance- and cost-based metrics, and hybrid approaches that integrate methodological innovations with agent architecture-level designs. We aim to establish a foundation for principled research on building LLM-based agents that generalize reliably across diverse real-world applications.
Förderung
- NSF
- Learning Engineering Virtual Institute
- NSF Graduate Research Fellowship Progra
Zitieren
APA
Zhang, M., Yang, Y., Xie, R., Dhingra, B., Zhou, S., & Pei, J. (2026). Generalizability of Large Language Model-Based Agents: A Comprehensive Survey. ACM Computing Surveys, 58(10), 1-44. https://doi.org/10.1145/3794858
Vancouver
Zhang M, Yang Y, Xie R, Dhingra B, Zhou S, Pei J. Generalizability of Large Language Model-Based Agents: A Comprehensive Survey. ACM Computing Surveys. 2026;58(10):1-44. doi:10.1145/3794858
BibTeX
@article{Zhang2026,
author = {Zhang, Minxing and Yang, Yi and Xie, Roy and Dhingra, Bhuwan and Zhou, Shuyan and Pei, Jian},
title = {Generalizability of Large Language Model-Based Agents: A Comprehensive Survey},
journal = {ACM Computing Surveys},
year = {2026},
volume = {58},
number = {10},
pages = {1--44},
doi = {10.1145/3794858}
}
EUVIMED