AIOct 28, 2025

Improving LLM Reasoning via Dependency-Aware Query Decomposition and Logic-Parallel Content Expansion

arXiv:2510.24390v1h-index: 16
Originality Incremental advance
AI Analysis

This addresses a critical bottleneck for Web services like AI-powered search and conversational agents by improving both efficiency and quality, though it is incremental as it builds on existing reasoning frameworks.

The paper tackles the challenge of enabling high-quality, complex reasoning in LLMs for real-time Web applications while meeting low-latency and high-throughput requirements, achieving up to 4.33x faster token generation, 3.42x lower latency, and 18.75% improved reasoning quality.

The integration of Large Language Models (LLMs) into real-time Web applications, such as AI-powered search and conversational agents, presents a fundamental Web infrastructure challenge: reconciling the demand for high-quality, complex reasoning with the stringent low-latency and high-throughput requirements of interactive services. Current LLM reasoning, hindered by computationally inefficient sequential generation and rigid reasoning strategies, creates a critical bottleneck for the Web services. Existing approaches typically optimize the LLM reasoning for either efficiency or quality but struggle to achieve both, and thus fail to meet the dual requirements of modern Web platforms. To overcome these limitations, we propose Orion, a novel and efficient reasoning framework that enables dependency-aware query decomposition and logic-parallel content expansion. Concretely, Orion decomposes a single query reasoning process into two synergistic phases: (1) \textit{key point generation}, which distills logically structured key points through retrieval-augmented few-shot prompting, and (2) \textit{content parallel expansion}, which concurrently elaborates on these points based on a dependency graph to ensure logical consistency. Furthermore, Orion introduces a pipeline scheduling mechanism that exploits the complementary computational characteristics of the two phases (generation imposes pressure on GPU computing and expansion stresses on GPU memory) across multiple queries, enabling cross-query parallelism and dramatically improving reasoning performance (\ie, efficiency and quality). Experiments on diverse benchmarks show that Orion not only delivers up to 4.33x higher token generation speed and 3.42x lower answer latency over the baselines but also improves reasoning quality by up to 18.75% through explicitly modeling inter-point dependencies.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes