Mingxin Li, Enge Song, Yueshang Zuo, Xiaodong Liu, Rong Wen, Qiang Fu, Gianni Antichi, Jian He 等 30 位作者
LLM agents increasingly rely on tool calling to complete tasks. Model Context Protocol (MCP) standardizes tool calling between LLM agents and tool providers. It reduces integration cost and drives rapid growth in tool scale. In production deployments, tool access becomes difficult to scale. On the tool provider side, legacy services are not directly callable through MCP; the rapid protocol development creates ongoing compatibility cost. On the agent side, the number of mounted tools is limited by the LLM context window and inference overhead; mounting a large tool set increases token usage and inference latency and can reduce task success rate. Moreover, for stateful MCP backends with multiple replicas, preserving session affinity increases client-side complexity. We present a cloud-scale MCP Gateway system. It breaks the direct-connect model on the data plane and offloads legacy service integration, consolidating incompatible MCP variants, access control, tool recommendation, and session-aware routing at the gateway. The conversion module supports 315 OpenAPI services in the cloud and integrates MCP transport variants. Session-aware routing decouples the scalability of the gateway layer and the MCP service layer. The hybrid retrieval engine sustains $\sim$98\% Top-15 recall; it scales agent tool access to 3{,}000+ tools with improved tool selection accuracy. We also share the lessons learned from deploying the gateway system in production.
Shaonan Liu Shenzhen University, Guo Yu, Xiaoling Luo Shenzhen University, Shiyi Zheng, Jie Liu City University of Hong Kong, Wenting Chen, Linlin Shen Shenzhen University
Medical Multimodal Large Language Models (Med-MLLMs) require egocentric clinical intent understanding for real-world deployment, yet existing benchmarks fail to evaluate this critical capability. We introduce MedGaze-Bench, the first benchmark leveraging clinician gaze as a Cognitive Cursor to assess intent understanding across surgery, emergency simulation, and diagnostic interpretation. Our benchmark addresses three fundamental challenges: visual homogeneity of anatomical structures, strict temporal-causal dependencies in clinical workflows, and implicit adherence to safety protocols. We propose a Three-Dimensional Clinical Intent Framework evaluating: (1) Spatial Intent—discriminating precise targets amid visual noise, (2) Temporal Intent—inferring causal rationale through retrospective and prospective reasoning, and (3) Standard Intent—verifying protocol compliance through safety checks. Beyond accuracy metrics, we introduce Trap QA mechanisms to stress-test clinical reliability by penalizing hallucinations and cognitive sycophancy. Experiments reveal current MLLMs struggle with egocentric intent due to over-reliance on global features, leading to fabricated observations and uncritical acceptance of invalid instructions.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Jiahui Geng Linköping University, Fengyu Cai Technische Universität Darmstadt, Shaobo Cui Shanghai Jiao Tong University, Qing Li Mohamed bin Zayed University of Artificial Intelligence, Liangwei Chen Google, Chenyang Lyu Alibaba Group, Haonan Li Mohamed bin Zayed University of Artificial Intelligence, Derui Zhu Technical University of Munich 等 11 位作者
Code retrieval is vital to modern software engineering as it boosts reuse and speeds up debugging. However, current benchmarks primarily emphasize functional relevance while neglecting code quality. To address this gap, we introduce CoQuIR, the first large-scale, multilingual benchmark specifically designed to evaluate quality-aware code retrieval across four critical dimensions: correctness, efficiency, security, and maintainability. CoQuIR includes fine-grained quality annotations over 42,725 queries and 134,907 code snippets in 11 programming languages. Evaluating 23 retrievers (both open-source and proprietary) shows that even state-of-the-art models often fail to separate buggy or insecure code from robust counterparts. We further investigate methods for explicitly training retrievers to recognize code quality, demonstrating that quality-aware metrics can be improved without loss of semantic relevance; downstream code generation benefits from these gains. CoQuIR underscores the importance of embedding quality signals into retrieval systems as a crucial component for more trustworthy developer tools.
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
Saeed Almheiri, Bilal Elbouardi Mohamed bin Zayed University of Artificial Intelligence, Salsabila Zahirah Pranida, Irina Nikishina, Ashwath Rao B Manipal University, Parameswari Krishnamurthy International Institute of Information Technology Hyderabad, Muhammad Cendekia Airlangga, Rifo Ahmad Genadi Mohamed bin Zayed University of Artificial Intelligence 等 19 位作者
Idiomatic expressions pose a major challenge for multilingual NLP because their meanings shift between figurative and literal usage, often requiring context for accurate interpretation. Prior work has focused on high-resource languages typically evaluates isolated idiom-meaning questions, overlooking realistic discourse. We introduce MIDI, a multilingual idiom dataset spanning 3 high-, 3 medium-, and 12 low-resource languages, curated by native speakers. Unlike previous datasets, MIDI provides idioms embedded in both sentence-level and conversational contexts, capturing both literal and figurative readings. Benchmarking state-of-the-art models shows that idiom comprehension degrades in low-resource languages and that, in all resource tiers, literal interpretations are substantially harder than figurative ones. Conversational context improves performance but does not eliminate these disparities. Through controlled tests and interventions on hidden representations, we further separate memorization from reasoning, exposing core limitations of current models.
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
Zhuohan Xie Mohamed bin Zayed University of Artificial Intelligence, Daniil Orel, Rushil Thareja, Dhruv Sahnan, Hachem Madmoun Imperial College London, Fan Zhang, Debopriyo Banerjee G42, Georgi Nenkov Georgiev 等 25 位作者
Multi-step symbolic reasoning is essential for robust financial analysis; yet, current benchmarks largely overlook this capability. Existing datasets such as FinQA and ConvFinQA emphasize final numerical answers while neglecting the intermediate reasoning steps required for transparency and verification. To address this gap, we introduce FinChain, the first benchmark specifically designed for verifiable Chain-of-Thought evaluation in finance. FinChain spans 58 topics across 12 financial domains, each represented by parameterized symbolic templates with executable Python code that enable fully machine-verifiable reasoning and scalable, contamination-free data generation.To assess reasoning capacity, we propose ChainEval, a dynamic alignment measure that jointly evaluates both the final-answer correctness and the step-level reasoning consistency. Our evaluation of 26 leading LLMs reveals that even frontier LLMs exhibit clear limitations in symbolic financial reasoning, while domain-adapted and math-enhanced fine-tuned models can substantially narrow this gap.Overall, FinChain exposes persistent weaknesses in multi-step financial reasoning and provides a foundation for developing trustworthy, interpretable, and verifiable financial AI. This project is available at https://github.com/mbzuai-nlp/finchain.git.
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