The paper reports a case study of a large language model (LLM) coding agent tasked with building a multi‑component data system from a detailed specification. During a single session the agent introduced five defects, which were categorized by violated constraints and detection methods. The study also evaluates the agent’s retrieval‑filtering strategy on the HotpotQA benchmark, showing that filtering to a graph‑identified entity set yields higher recall than unfiltered search, with a statistically significant gap across all tested budgets.
By Phanindra Reddy Madduru
arXiv:2607. 08028v1 Announce Type: new Abstract: Enterprise large language model (LLM) applications often begin as prototypes whose behavior is carried by prompts and retrieval context.
By Joongho Ahn, Moonsoo Kim
arXiv:2608. 10037v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly rely on external tools to accomplish complex real-world tasks, making tool documentation a critical grounding resource for LLM agents.
By You Lu, Kun Zhang, Bihuan Chen, Xin Peng
arXiv:2606. 13608v1 Announce Type: new Abstract: Agent systems are advancing quickly across domains, but their evaluation remains fragmented.
By Xiaoyuan Liu, Jianhong Tu, Yuqi Chen, Siyuan Xie, Sihan Ren, Tianneng Shi, Gal Gantar, Evan Sandoval, Donghyun Lee, Daniel Miao, Peter J. Gilbert, Nick Hynes, Mauro Staver, Warren He, David Marn, Andrew Low, Xi Zhang, Elron Bandel, Michal Shmueli-Scheuer, Siva Reddy, Alexandre Drouin, Alexandre Lacoste, Ramayya Krishnan, Elham Tabassi, Yu Su, Victor Barres, Chenguang Wang, Wenbo Guo, Dawn Song
Tool Calling and Structured Output are two core capabilities of modern Agent systems, yet their interaction under joint deployment conditions remains insufficiently understood. This paper reports a reproducible phenomenon observed in a production Agent system: when Tool Calling and JSON Schema constraints are simultaneously enabled, multiple open-weight models cease invoking tools despite maintaining high schema compliance.
Agent Seer is a pipeline that automatically synthesizes realistic evaluation scenarios for AI agents that use external tools, using only the tool’s specification (function names, natural‑language descriptions, and typed parameter schemas). Starting from a single Model Context Protocol (MCP) specification, it enriches raw schemas, generates graded scenarios with synthetic tool outputs, and expands them into mock‑data‑grounded multi‑turn dialogues that demonstrate strong tool‑calling correctness and conversational coherence. Across seven diverse MCP specifications, the pipeline achieves high quality, with parameter‑schema complexity emerging as the main driver of quality variation and argument‑value accuracy identified as the dominant failure mode.
By Harish Karumuri, Mahesh Vemula, David Lopes Pegna
arXiv:2607. 03953v1 Announce Type: cross Abstract: This study independently replicates and extends the Natural Language Tools (NLT) framework of Johnson et al.
By Alexander Somma, Isabelle Plante, Fred Premji
arXiv:2607. 15715v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used for complex information-extraction tasks, yet it remains unclear whether agentic components such as reflection and memory lead to observable and controllable improvements over fixed LLM workflows.
By Lujia Zhang, Xingzhou Chen, Hongwei Feng
arXiv:2606. 03907v1 Announce Type: cross Abstract: Agentic AI coding tools write code with increasing autonomy and in doing so decide when to import a library and when to implement functionality from scratch.
By Jai Lal Lulla, Matthias Galster, Jie M. Zhang, Sebastian Baltes, Christoph Treude
arXiv:2606. 17698v1 Announce Type: new Abstract: As LLM-based shopping agents enter production, existing benchmarks fail to capture how a shopper's requirements arrive: stated implicitly in the query, recorded in a profile, or revealed only when the right question is asked.
By Zeyao Du, Tong Li, Haibo Zhang
TRACE is a new framework that uses agentic Large Language Models to automatically enrich e-commerce product catalogs with missing or buried attributes. It employs a ScoutAgent to gather multimodal evidence from merchant catalogs, syndicated feeds, and web search, and a JudgeAgent to verify and publish the proposed attribute values. In offline evaluation, TRACE achieved 98.2% accuracy with 74.7% coverage, and in production it increased enrichment coverage by 90.4% and boosted checkout conversion by 0.48%.
By Rohan Kumar, Steven Xu, Kyle MacDonald, Matthew Long, Bernice Chow, Mac VanRenterghem, Sudeep Das
arXiv:2609.00052v1 Announce Type: cross
Abstract: Commercial LLM APIs advertise a specific foundation model, but the served backbone may be silently substituted, quantized, or wrapped, for example to...
By Xun Wang, Bihe Zhao, Michael Backes, Franziska Boenisch, Adam Dziedzic