EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Trajectory Memory Compression for Long-Horizon Dialogue Agents with Provenance Preservation

Philip Ho, Joanna Ma

Journal of Social Sciences, Humanities and Innovation · 08.10.2026 · 2 (2) · 221-234

DOI: 10.66238/jsshi.v2i2.58 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Social Sciences, Humanities and Innovation, online erschienen am 08.10.2026. Verfasst von Philip Ho und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid advancement of artificial intelligence has facilitated the development of dialogue agents capable of highly sophisticated interactions. However, sustaining coherence and factual consistency over extended interactions remains a formidable challenge due to the inherent constraints of context windows in large language models. This paper investigates the critical problem of trajectory memory compression in long-horizon dialogue agents, introducing a novel paradigm that integrates provenance preservation into the compression pipeline. Traditional memory compression techniques often discard granular contextual details, leading to hallucinations and a loss of traceability when the agent attempts to recall historical information. By conceptualizing dialogue history as a continuous trajectory of events, we propose a methodology that selectively compresses semantic content while meticulously maintaining cryptographic and structural pointers to the original episodic occurrences. This dual-track approach ensures that the agent can retrieve highly compressed semantic representations without sacrificing the ability to ground its responses in specific past utterances. Through rigorous theoretical analysis and extensive empirical evaluation across multiple long-context dialogue datasets, we demonstrate that our provenance-aware compression mechanism significantly enhances both the computational efficiency of memory retrieval and the factual reliability of the generated responses. The findings offer a scalable framework for deploying autonomous agents in domains requiring prolonged interaction and strict auditing, such as healthcare and legal counseling.

Zitieren

APA

Ho, P., & Ma, J. (2026). Trajectory Memory Compression for Long-Horizon Dialogue Agents with Provenance Preservation. Journal of Social Sciences, Humanities and Innovation, 2(2), 221-234. https://doi.org/10.66238/jsshi.v2i2.58

Vancouver

Ho P, Ma J. Trajectory Memory Compression for Long-Horizon Dialogue Agents with Provenance Preservation. Journal of Social Sciences, Humanities and Innovation. 2026;2(2):221-234. doi:10.66238/jsshi.v2i2.58

BibTeX
@article{Ho2026,
  author = {Ho, Philip and Ma, Joanna},
  title = {Trajectory Memory Compression for Long-Horizon Dialogue Agents with Provenance Preservation},
  journal = {Journal of Social Sciences, Humanities and Innovation},
  year = {2026},
  volume = {2},
  number = {2},
  pages = {221--234},
  doi = {10.66238/jsshi.v2i2.58}
}
Kostenlos starten →