Metraipolis › archive › dc_d84040b3ebed

UNISON: A Co-Designed Near-Memory Scheduler of Session KV Residency for LLM Agents — arXiv:2609.09643

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.09643
License (as archived)
CC0-1.0
Archived
2026-10-16T07:54:08.562Z
SHA-256 of the archived text
caa74876ac84798491fc8c421f92d021b1b90fa2cb231f9aa28c684cd9b9334d
Stable URL of this page
https://metraipolis.com/documento/dc_d84040b3ebed

How to cite

UNISON: A Co-Designed Near-Memory Scheduler of Session KV Residency for LLM Agents — arXiv:2609.09643 — arXiv (en), https://arxiv.org/abs/2609.09643 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d84040b3ebed (Metraipolis archive dc_d84040b3ebed, sha256 caa74876ac84798491fc8c421f92d021b1b90fa2cb231f9aa28c684cd9b9334d)
BibTeX
@misc{dcd84040b3ebed,
  title = {UNISON: A Co-Designed Near-Memory Scheduler of Session KV Residency for LLM Agents — arXiv:2609.09643},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09643},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d84040b3ebed; sha256 caa74876ac84798491fc8c421f92d021b1b90fa2cb231f9aa28c684cd9b9334d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09643. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models are increasingly composed into agent loops that plan, call tools, and resume the same task after each action. These loops press a shared memory hierarchy harder than conventional multi-turn chat, because they hold a growing key-value (KV) prefix across tool waits and place many sessions on one SRAM/HBM pool, so that eviction and hierarchical placement become a session-level efficiency problem orthogonal to compute-mode optimization. Existing proxies based on recency, timeout, or identity miss the mechanism information of the loop and therefore treat a live wait as a cold, discardable unit. We present Unified Native Inter-turn Session Orchestration Nexus (UNISON), an event-driven near-memory scheduler in which Survival-Penalty Eviction for Agent Return-gap (SPEAR) and Tiering in Idle-window DMA Events (TIDE) share one live ranking. SPEAR selects who leaves from a gap average and a turn-indexed hazard, while TIDE spends the observed wait as a DMA budget for who sits in the fast tier. On coding and general-mission benchmarks with three model families, totaling 1,415 sessions and 33,596 turns, the joint policy is the best non-oracle entry on every trace, raising hit rate by 0.3% to 23.1%, reducing AMAT by 22% to 51%, and lowering TTFT by 58% to 89% on long-horizon traces. A structural necessity analysis shows that the unified near-memory design cannot be decomposed into independent IPs or realized in software without re-introducing documented failure modes. The 28-nm CMOS scheduling core occupies 0.169 mm^2 at 13.6 mW and 150 MHz, a negligible overhead relative to the KV hierarchy it manages, reproducing the floating-point ranking at Kendall tau exceeding 0.998.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-10 in cs.AR).
Categorie arXiv: Hardware Architecture (cs.AR).
Pagina del lavoro: https://arxiv.org/abs/2609.09643 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T07:25:33.735Z dalla pagina https://arxiv.org/catchup/cs.AR/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).