Algorithms for Context Engineering in LLM Inference: Optimization of Placement, Compression, and Scheduling
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41537-41539
DOI: 10.1609/aaai.v40i48.42332 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Teresa Zhang.
Abstract (Originalsprache)
Scaling long-context and agentic LLMs is increasingly limited by memory capacity and bandwidth rather than FLOPs. I propose an algorithmic framework for context engineering that models placement, compression, and scheduling as coupled optimization problems with explicit accuracy-efficiency trade-offs. Concretely, I aim to develop (1) salience-aware retention/eviction policies with provable approximation guarantees relative to an ideal oracle; (2) tier-dependent compression schemes that bound error propagation across memory levels; and (3) probabilistic prefetch/scheduling that controls tail latency. I will evaluate on long-context language modeling and reasoning benchmarks, isolating each component via ablations and comparing against heuristic baselines under controlled bandwidth/capacity regimes. Results target improved throughput and energy metrics at near-baseline quality, advancing principled, hardware-aware inference without requiring custom hardware.
Zitieren
APA
Zhang, T. (2026). Algorithms for Context Engineering in LLM Inference: Optimization of Placement, Compression, and Scheduling. Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41537-41539. https://doi.org/10.1609/aaai.v40i48.42332
Vancouver
Zhang T. Algorithms for Context Engineering in LLM Inference: Optimization of Placement, Compression, and Scheduling. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41537-41539. doi:10.1609/aaai.v40i48.42332
BibTeX
@article{Zhang2026,
author = {Zhang, Teresa},
title = {Algorithms for Context Engineering in LLM Inference: Optimization of Placement, Compression, and Scheduling},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41537--41539},
doi = {10.1609/aaai.v40i48.42332}
}
EUVIMED