Edge SoCs combine CPUs, GPUs, and NPUs, yet runtimes for multimodal large language models (MLLMs) keep generation on one engine and leave others idle. Streaming workloads allow ingestion and answering to overlap, but backend-local KV state binds queries to the engine that built their history. Stage performance and co-running interference vary, so no single placement wins across SoCs and workloads. \name separates logical history from engine-specific KV state so any language engine can continue a stream. Stateful Streaming Generation overlaps ingestion and answering, while Concurrent Sequence Generation serves ready queries in parallel. Phase-level state continuation lets one engine prefill a query and another decode the answer, freeing the first to resume ingestion. State-Driven Execution Planning (SDEP) chooses paths by predicted completion time and sets each engine's share of queries using arrival rates and measured service times. Across M4 Max, RK3588, and QCS6490, \name beats the strongest single-engine baselines, even when they reuse context. On M4 Max, SDEP cuts live-stream p95 time to first token by $76\%$, with every first token within one second, and raises throughput under backlog by up to $35\%$ over Metal-only execution with context reuse. On two RK3588 streams, SDEP delivers $19.6\%$ higher request throughput than the best single engine with context reuse and $27.2\%$ more than parallel engines without shared state. Stateful Streaming Generation reaches up to $2.48\times$ serial throughput on the same engines. Every answer matches its serial reference.
Yilong Liu Institute of Information Engineering, Chinese Academy of Sciences, Xixun Lin Institute of Information Engineering, Chinese Academy of Sciences, Pengfei Cao Institute of automation, Chinese academy of science, Chinese Academy of Sciences, Ge Zhang Donghua University, Fang Fang Institute of Information Engineering,Chinese Academy of Sciences, Yanan Cao Institute of Information Engineering, Chinese Academy of Sciences
Large language models (LLMs) have demonstrated impressive capabilities in utilizing external tools. In practice, however, LLMs are often exposed to tools that are irrelevant to the user’s query, in which case the desired behavior is to refrain from invocations. In this work, we identify a widespread yet overlooked mechanistic flaw in tool refusal, which we term structural alignment bias: Even when a tool fails to serve the user’s goal, LLMs still tend to invoke it whenever query attributes can be validly assigned to tool parameters. To systematically study this bias, we introduce SABEval, a new dataset that decouples structural alignment from semantic relevance. Our analysis shows that structural alignment bias induces severe tool-invocation errors in LLMs, yet remains largely unaccounted for in existing evaluations. To investigate the internal mechanisms underlying this bias, we propose Contrastive Attention Attribution, which reveals two competing pathways for semantic checking and structural matching. The relative strength of these pathways drives LLMs’ tool invocation decisions. Based on these findings, we further introduce a rebalancing strategy that effectively mitigates structural alignment bias, as demonstrated by extensive experiments, without degrading general tool-use capabilities.
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