Service-Oriented Architecture and Web Services

Neueste Paper

• ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning

  Bingchen Pei, Lichong Chen, Bingxi Zhao, Ziang Wu, Sirui Wang, Min Zhang, Yanhao Chen, Qingxu Liu, Qiang Gao, Chang-Tien Lu, Bo Gao · 2. Oktober 2026

  Remote multimodal models offer strong numerical reasoning capabilities over charts and speech, but sending private inputs risks exposing sensitive content. Text-only sanitization cannot directly satisfy fixed media interfaces, while identity anonymization leaves the underlying task content exposed. …

• Can You Check That? The Checkability Boundary for Local LLM Network Automation

  Maleeha Masood, Momina Nofal · 28. September 2026

  Sending every network-automation input to a third-party frontier LLM exports sensitive artifacts such as production configurations, topologies, and logs. Querying small language models (SLMs) locally avoids this egress, but SLM outputs can be error-prone for direct use. This work introduces checkabi…

• Extending FunctionGemma for Practical On-Device Mobile Function Calling

  Ali Rezagholizadeh, Soheila Samiee · 23. September 2026

  On-device assistants require function-calling models that map natural language to local system actions, but existing resources emphasize web APIs or narrow mobile-action catalogs. We extend FunctionGemma 270M-it to practical Android workflows by introducing MOBILEACTIONSEXTENDED, a synthetic, schema…

• Measuring the Serving Stack Instead of the Model: Hidden Confounds in Local Tool-Use Evaluation

  Lijuan Tang, Yuemeng Zheng · 23. September 2026

  A coding agent must emit a valid tool call--a parseable invocation of a tool in the provided schema--before the harness can execute its chosen action. We study how local serving stacks affect this protocol step and show that measured outcomes can depend on the serving layer rather than model behavio…

• this-that-model-1.0: A typed decision model that decides in 30 ms, for a millionth of a cent

  Zehua Cheng, Wei Dai, Jiahao Sun · 22. September 2026

  Software delegates more of its branches to models every year: which queue a ticket enters, whether a command is safe to run, whether a claim clears without a person. What the program needs back is not prose. It is one of n declared options and a number it can threshold. Today that costs a round trip…

• Machine-Interpretable Information: Compiling Documents into Searchable and Readable Protocol States

  Yifan Wang, Dejing Dou · 22. September 2026

  Long-context language models interface with external knowledge through raw natural language. In retrieval-augmented systems, this creates a persistent index-payload schism: dense vectors enable searchable routing, but models must re-ingest lengthy text payloads for reasoning at O(N^2) attention cost…

• BENCHCOMPASS: From Scores to Signals for Training and Harness Decisions in Payment-Domain LLMs

  Sijie Dong, Wei Ren, Xuanwei Hu, Jiawei Luo, Zifan Wang, Xiaoyun Feng, Hui Cai, Lyuxin Xue, Peng Lu, Jianshe Li, Xin Zhang, Wei Wu · 17. September 2026

  Payment operations are a critical financial infrastructure, but the value of large language models in this domain remains unclear because payment rules change quickly, evidence is fragmented, and decisions depend on transaction state, participant role, region, and payment rail. Existing benchmarks d…

• The Menu Is an Execution Prior: State-Path Tool Menus for Online Agents

  Bo Yan, Weikai Lin, Song Wang · 10. September 2026

  Language models act through tools, yet practical agents face libraries containing thousands of interfaces. We introduce the tool menu as the short, ordered subset of available tools shown to an agent before execution. The agent can call only tools in this menu. Multi-step tasks require the final act…

• AAS-RAIL: Improving Information Extraction for Asset Administration Shells through Retrieval-Augmented In-Context Learning

  Janek Gro{\ss}, Jens Heidrich · 9. September 2026

  The Asset Administration Shell (AAS) is a cornerstone of Industry 4.0 and the Digital Product Passport, providing standardized digital representations of industrial assets. While manufacturers already maintain extensive technical product documentation, generating AAS instances from existing product …

• Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Recipe

  Dain Kim, Eungi Cho, Kyumin Kim, Shinyeong Noh, Kyuseong Lim · 7. September 2026

  Data-sovereignty regulations increasingly require public institutions to deploy open-source, on-premise LLM agents that chain multiple tool-calls across live government APIs. However, open-source models consistently underperform in this multi-step setting, and no existing benchmark measures the gap.…

• Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives

  Haibo Jin, Suijin Wang, Xucheng Yu, Haojing Luo, Haohan Wang · 3. September 2026

  Large language models (LLMs) augmented with external tools have demonstrated remarkable capability in solving complex real-world tasks. However, existing approaches suffer from two key challenges: brittle multi-step and multi-turn reasoning caused by incompatible tool output types and API schemas, a…

• RegCL: Compact Continual SAM Adaptation for Visual Grounding in Multi-Sensorial Media

  Yuan-Chen Shu, Zhiwei Lin, Xiaoyu Zhou, Yongtao Wang · 31. August 2026

  Multi-sensorial media systems, including AR/VR, remote operation, and embodied AI, require visual grounding modules that remain reliable as sensing environments and application domains evolve. The Segment Anything Model (SAM) provides a strong foundation for dense visual segmentation, but its perfor…

• Natural-Language Policies to Executable Decisions: An Interpretable Large Language Model Framework

  Ziqiang Zhang, Jing Ma, Zilong Wang, Jiayuan Chen, Yi Qiao, Yu He, Wei Zhang, Dai Cheng, Xiaoyu Shen · 28. August 2026

  Pricing automation in large-scale tourism is challenging because travel orders are highly unstructured, while pricing policies are complex, rapidly evolving, and inherently open-ended. Traditional rule engines are brittle and costly to maintain, whereas unconstrained LLM agents lack the reliability …

• Routed Graph Handoff: Adaptive Format Selection for Multi-Agent LLM Delegation

  Pratyay Banerjee, Ankit Chadha · 27. August 2026

  Multi-agent LLM systems coordinate through natural-language messages that consume 40--60\% of their token budget. Replacing these with structured graphs reduces cost but fails on tasks requiring adaptive reasoning. We propose \textbf{Routed Graph Handoff}, where a lightweight LLM router (155 tokens,…

• Hybrid Semantic Tool Discovery for Enterprise MCP Gateway: Architecture and Implementation

  Olympia Saha, Amy Wang, Srinivasan Manoharan · 26. August 2026

  Large language model (LLM) agents invoke external tools to retrieve and reason over information beyond pretrained knowledge. The Model Context Protocol (MCP) standardizes how such tools are surfaced, and a proxy MCP server aggregates many backend servers behind a single endpoint providing a secure, …

• Industrial-Instruction: An End-to-End Framework for Building Instruction-Tuning and Benchmark Datasets from Industrial Technical Reports

  Parsa Bakhtiari, Hassan Bashiri, Alireza Khalilipour, Masoud Nasiripour, Moharram Challenger · 25. August 2026

  Industrial technical reports contain high-value knowledge for maintenance, troubleshooting, and product engineering, but their heterogeneous structure (dense prose, specifications, tables) makes them difficult to index and reason over with standard retrieval and QA pipelines, and no public instructi…

• CacheRouter: A Dual-Path Tool Routing Architecture with Cache-Preserving Main-Model Isolation for Long-Tail Tool Discovery

  Donghui Zha, Lingwei Xu, Linxiao Wu, Yixue Dong, Haochen Li · 25. August 2026

  Tool use in LLM systems faces a structural trade-off. Progressive disclosure keeps the prompt small by showing only the tools relevant to the current task, while prompt caching rewards a request prefix that stays fixed across calls; every change to the visible tool list invalidates the cached prefix…

• Small Reasoning Models are Instruction Followers in Function Calling

  Yalda Taheri, Mohammad Hassan Heydari, Erfan Naaman, Afsaneh Fatemi · 25. August 2026

  Function calling represents the core capability of agentic large language models (LLMs). Existing research has focused on enhancing LLMs function-calling accuracy through fine-tuning, reinforcement learning (RL), and multi-agent frameworks, particularly for native function-calling LLMs. This work de…

• From SQL Generation to Tool Selection: A Domain-Oriented Pattern for MCP Servers

  Bartolomeo Bogliolo · 25. August 2026

  Agents built on Large Language Models (LLMs) increasingly reach enterprise data through the Model Context Protocol (MCP), and many MCP database servers maximize flexibility by exposing a single generic SQL execution tool. This paper proposes the Domain-Oriented Tooling Pattern: instead of generating…

• Flama: a Python framework for development and deployment of production-ready APIs, machine learning, and LLM services

  Jos\'e A. Perdiguero L\'opez, Miguel A. Dur\'an-Olivencia · 20. August 2026

  We present Flama, an open-source Python framework for developing and deploying production-ready web APIs, machine learning services, and large-language-model (LLM) applications. Built on the Asynchronous Server Gateway Interface (ASGI), Flama offers a type-driven, async-first programming model that …

• ORBITER: Conflict-Aware Decision-Making for Agentic Last-Mile Delivery

  Mingzhao Li, Chenxi Liu, Yan Zhao, Hao Miao · 20. August 2026

  Last-mile delivery aims to handle dynamically arriving orders with couriers while modeling complex spatial and temporal correlations. Recent learning-based methods model spatiotemporal dependencies among orders to predict courier service sequences, but leave next-order decision making unexplained. D…

• Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQL

  Changruo Zhao, Zujun Peng, Yu Tian, Yuting Liu, Yiyun Su, Huiying Zhu, Luyan Zhang, Heming Zeng · 18. August 2026

  LLM-based Text-to-SQL progress is reported across heterogeneous benchmarks, backbones, and inference protocols, making cross-system comparison fragile. We reframe the field as a leaderboard aggregation: we collect the metrics authors themselves report and organize them along an inference-autonomy ax…

• SemPlan: Benchmarking Structured Semantic Planning for LLM-Based Queries over Enterprise Data

  Bruno Santos Teixeira · 17. August 2026

  Natural-language interfaces to enterprise data must translate underspecified requests into governed, executable behavior while controlling invalid queries, policy failures, cost, and nondeterminism. SemPlan Benchmark evaluates this architectural design space with a deterministic synthetic bilingual …

• VAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use Policies

  Ankita Rajaram Naik, Anupama Murthi, Benjamin Elder, Siyu Huo, Raavi Gupta, Abhinav Jain, Praveen Venkateswaran, Abdulhamid Adebayo, Danish Contractor · 13. August 2026

  Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities in isolation. We introduce VAKRA (e\textbf{V}aluating \textbf{A}PI and \textbf{K}nowledge \textbf{R}etrieval \textbf{A}gents), a benchmark of over $…

• XBridge: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication

  Wooseong Yang, Wei-Chieh Huang, Weizhi Zhang, Yu Wang, Philip S. Yu, Junhyun Lee · 13. August 2026

  Heterogeneous multi-agent LLM systems, where agents are powered by different model families, can outperform homogeneous configurations by reducing redundant reasoning patterns. Yet existing communication protocols either operate through text, discarding the sender's internal representations, or requ…