Smartphone agents increasingly work as teams, in which a large planner directs parallel workers across long sessions. Running such a team on the device requires 200B-class models and contexts that exceed phone DRAM many times over, yet existing tiers treat flash as storage: UFS starves per-token weight streaming, and mobile High-Bandwidth Flash (HBF) needs a redesigned SoC and cannot absorb continuous KV writes. We show that a non-volatile memory can join an unmodified LPDDR6 bus as a plain rank only if its access latency fits the DRAM timing window, a condition no NAND tier meets. We present NORmal, to our knowledge the first main-memory architecture for 3D ferroelectric NOR flash. We have fabricated and experimentally characterized back-end-of-line (BEOL) 3D FeNOR arrays that co-integrate dense 3-bit MLC and fast, high-endurance in-place-writable SLC with sub-7.5 ns sensing. NORmal turns these co-fabricated arrays into a byte-addressable, deterministic-timing load/store rank on an unmodified LPDDR6 interface through an under-array DRAM-emulation bridge, staggered bank reads with zero-cycle weight swizzling, and posted SLC writes. Across this rank and DRAM, NORmal places agent state by mutability and lifetime rather than by hotness, serving 200B-class models and persistent planner contexts in place while dynamically partitioning subchannels across agent phases. In serving-level simulation on production agent traces, NORmal is 8.9$\times$--28.0$\times$ faster than UFS offloading, within 0.4% of an unlimited-DRAM ideal, and 2.8$\times$--6.3$\times$ faster than HBF on sessions beyond 256K tokens, with 8.1$\times$--17.8$\times$ less memory energy per token.
Xin Huang, Teng Ma, Zhuoran Li, Yibo Zhao, Zhaoshi Li, Qianchao Zhu, Wei Yang, Chenxi Wang 等 10 位作者
KV cache reuse accelerates LLM serving, but existing systems manage host DRAM and NVMe SSD as a tiered hierarchy where DRAM acts as an intermediate cache. Production LLM workloads break both premises of this hierarchy. First, bimodal reuse defeats DRAM temporal filtering, since workloads are dominated either by one-shot blocks with long reuse distances or by multi-gigabyte agentic sessions that exceed DRAM capacity, putting SSD on the critical read path. Second, DRAM staging and eviction-ordered layout bottleneck SSD restoration. Holding host staging buffers for in-flight prefixes causes contention under load that aborts prefetches, while incremental eviction scatters a session's blocks across the SSD and prevents large sequential reads. We present FlatCake, a flat KV storage architecture that exposes host DRAM and NVMe SSD as peer media in a unified 64-bit address space. Exploiting the fact that KV blocks are write-once, immutable, and reused at session scope, FlatCake places each block directly onto its target medium in session-contiguous, layer-major order at creation time and never migrates it. FlatCake streams coalesced SSD reads directly into a bounded GPU window via GPUDirect Storage and decouples DRAM and SSD request queues to prevent head-of-line blocking. On a production Claude Code trace with DeepSeek-V4-Flash, FlatCake sustains a 94% cache hit rate as load increases (versus 64% for Mooncake), eliminates Mooncake's $6.5\times$--$6.7\times$ SSD read amplification, and reduces peak-load mean TTFT by $1.6\times$ while improving total token throughput by $1.6\times$. Across 8K--128K contexts on Llama-3.1-70B, FlatCake further reduces mean TTFT by up to $2.4\times$ over Mooncake and $1.8\times$ over Mooncake-GDS.
Ziheng Li, Liu Kang, Feng Xiao, Luxi Xing Alibaba Group, Qingyi Si JD.com, Zhuoran Li Beijing University of Posts and Telecommunications, Weikang Gong Fudan University, Deqing Yang Fudan University 等 10 位作者
Group Relative Policy Optimization (GRPO) has emerged as a promising critic-free reinforcement learning paradigm for reasoning tasks. However, standard GRPO employs a coarse-grained credit assignment mechanism that propagates group-level rewards uniformly to to every token in a sequence, neglecting the varying contribution of individual reasoning steps. We address this limitation by introducing Outcome-grounded Advantage Reshaping (OAR), a fine-grained credit assignment mechanism that redistributes advantages based on how much each token influences the model’s final answer. We instantiate OAR via two complementary strategies: (1) OAR-P, which estimates outcome sensitivity through counterfactual token perturbations, serving as a high-fidelity attribution signal; (2) OAR-G, which uses an input-gradient sensitivity proxy to approximate the influence signal with a single backward pass. These importance signals are integrated with a conservative Bi-Level advantage reshaping scheme that suppresses low-impact tokens and boosts pivotal ones while preserving the overall advantage mass. Empirical results on extensive mathematical reasoning benchmarks demonstrate that while OAR-P sets the performance upper bound, OAR-G achieves comparable gains with negligible computational overhead, both significantly outperforming a strong GRPO baseline, pushing the boundaries of critic-free LLM reasoning.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表