Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· pp. 8124-8134· 0 citations· 13 references
TL;DR
DualLane, a novel parallel dual-path planning architecture designed for AI agents, adaptively manages the highly skewed frequency distribution characteristic of real-world user queries and underscores the practical viability and effectiveness of adaptive dual-path planning in large-scale, interactive AIOps systems.
Abstract
Ticket support in cloud services involves technical engineers using expert tools to resolve customer queries—% a process closely resembling information integration. To enhance both operational efficiency and resolution accuracy, we propose DualLane, a novel parallel dual-path planning architecture designed for AI agents. This framework adaptively manages the highly skewed frequency distribution characteristic of real-world user queries. For low-frequency long-tail scenarios, the slow path employs a two-stage planning mechanism that decouples task decomposition from parameter generation, effectively optimizing dependency propagation and reducing context complexity. In contrast, for high-frequency routine scenarios, the fast path bypasses expensive LLM-based full-plan generation by utilizing pre-validated execution templates, thereby improving response accuracy and reducing latency. After more than one year of extensive deployment in Alibaba Cloud's ECS production environment, DualLane has demonstrated remarkable robustness and stability. Offline benchmarks indicate a high accuracy rate of 96.5%, accompanied by superior latency performance. Crucially, online metrics reveal a median plan-execution latency of merely 4.2 seconds, with an agent-induced error rate maintained at a low 7.1%. These results underscore the practical viability and effectiveness of adaptive dual-path planning in large-scale, interactive AIOps systems.
As on-device LLM agents evolve into personal copilots, the mobile operating system has become a key testbed for this paradigm, making rigorous capability evaluation essential. Yet existing benchmarks fall into two camps, each with a critical blind spot: GUI-centric benchmarks test surface-level screen manipulation while overlooking background tool use and long-horizon planning, whereas static function-calling benchmarks rely on offline API matching that is detached from real runtime constraints. To close this gap, we present \textbf{MobilePA-Bench}, an interactive, stateful, and tool-centric benchmark for evaluating the tool-calling and planning abilities of mobile planning agents. MobilePA-Bench runs on an executable sandbox that maintains live application databases and returns structured feedback, spanning $13$ functional domains and $212$ realistic mobile tools. Beyond basic tool use, it evaluates a central planning agent along three advanced dimensions: \emph{(1)~Sub-agent Collaboration}---decomposing a complex task and delegating specialized work to capable sub-agents; \emph{(2)~Memory Usage}---recalling stored memories, user profiles, and past preferences to resolve implicit requests; and \emph{(3)~Skill Usage}---invoking pre-packaged composite skills instead of planning every step from scratch. Extensive experiments show that current frontier LLMs remain unreliable in mobile settings: performance drops sharply under strict tool ordering, permission limits, and unexpected runtime errors. By pairing an interactive function-calling sandbox with evidence-based verification, MobilePA-Bench serves as both a practical diagnostic benchmark and an interactive foundation for agentic reinforcement learning---accelerating the development of dependable mobile agents.
Yi Zhu, Xiongwei Wu, Qiyi Wang et al.· 0 citations
Tool-augmented large language model (LLM) services can solve complex tasks through retrieval and external tools, but current execution paradigms often trade adaptability for efficiency. Fixed workflows are predictable but rigid, while freeform reasoning loops such as ReAct may over-execute and issue redundant tool calls. We propose a lightweight utility-guided orchestration framework that formulates agent control as a costaware sequential decision problem over a compact action space: respond, retrieve, tool call, verify, and stop. An interpretable utility function balances expected gain, step-cost proxies, uncertainty, and redundancy. Experiments on multi-hop question answering show that the policy offers a controllable quality-cost trade-off and reduces token consumption by up to 10.6% in the semantic-redundancy setting while preserving similar answer quality. The framework is intended as an inspectable control layer for practical LLM services rather than a universally dominant accuracy optimizer.
Bowen Liu, Gongming Zhao, Hongliu Xu et al.· Fall Joint Computer Conferen...· 0 citations
Travel planning is a complex, multi-dimensional challenge requiring travelers to manually synthesize information across fragmented platforms—flight aggregators, hotel portals, weather services, and restaurant guides. The process is time-consuming, error-prone, and poorly adaptive to real-time disruptions. This paper presents an AI-Powered Personalized Trip Planner—a full-stack intelligent system that dynamically generates end-to-end itineraries tailored to individual preferences, budget constraints, and live environmental conditions. The architecture integrates a multi-agent orchestration layer, Large Language Model (LLM) inference augmented by Retrieval-Augmented Generation (RAG), a hybrid collaborative and content-based recommendation engine, and asynchronous real-time APIs for weather, geospatial Points of Interest (POI), transport scheduling, and local events. A Genetic Algorithm solves the multi-constraint Constraint Satisfaction Problem (CSP) to optimize daily schedules. The system generates complete, bookable itineraries in under 30 seconds. Evaluation over 50 diverse trip scenarios demonstrates 91.4% recommendation precision, 96.2% budget adherence, a Mean Opinion Score of 4.6/5, and 88.7% real-time re-planning success rate—substantially advancing the state of the art in intelligent travel planning.
Index Terms — Artificial Intelligence, Trip Planner, Large Language Models, Retrieval-Augmented Generation, Multi-Agent Systems, Recommendation Engine, Constraint Satisfaction, Real-Time APIs, Streamlit, NLP.
Aryan Kumar Gupta, B. S, C. Kumar et al.· International Journal of Cre...· 0 citations
LLM-based multi-agent embodied planning remains impractical due to prohibitively high execution latency. We identify failed actions as the dominant bottleneck, stemming from two core challenges: inaccurate state tracking under partial observability and inefficient coordination that produces redundant or conflicting actions. We introduce Mosaic, a runtime-efficient multi-agent planning framework that addresses both challenges. Mosaic maintains accurate yet lightweight state tracking through agent-centric semantic memory that stores objects in relative coordinates, enabling geometric transformations and coordination. It ensures efficient coordination through Integer Linear Programming that allocates actions at every planning step, enforcing physical feasibility and inter-agent coordination constraints. Across AI2-THOR and search-and-rescue benchmarks, Mosaic achieves 27-32% faster execution, 30-33% fewer LLM calls, 25-31% fewer steps, and 4-10% points higher success rates. These results demonstrate that efficient memory and constraint-guided coordination are critical for scalable, low-latency multi-agent planning.
Kunjal Panchal, Saayan Mitra, Sunav Choudhary et al.· 0 citations
Eluna is a graph-guided, multi-agent framework that encodes SOPs as directed acyclic graphs with progressive disclosure and delegates independent tasks to parallel sub-agents, each with persistent code execution and live data access.
Ning Liu, Kalle Kujanpää, Zhaoxuan Zhu et al.· 1 citation
This work reframe trajectory evaluation as a distance between the agent's execution graph and a set of valid solution graphs, and instantiates OTAP via an unbalanced fused Gromov-Wasserstein transport problem over attributed dependency graphs, which is a pseudo-metric that is provably invariant to dependency-preserving reorderings and has bounded sensitivity to redundant steps.
Babak Barazandeh, Subhabrata Majumdar, G. Michailidis· 0 citations