arXiv:2608. 16502v1 Announce Type: new Abstract: Large-scale agents increasingly rely on retrieval to access external capabilities.
By Yiqi Liu, Joseph James, Yang Wang, Chenghao Xiao, Chenghua Lin
CARGO is a framework for evaluating agentic AI systems in production that addresses the problem of reference-instance divergence (RID), where reference-based judges penalize correct answers that involve different entity identifiers. It treats retrieved references as procedural exemplars, grounds judgments in the live instance’s context, assigns a three-way status to claims, and gates evaluation by retrieval confidence. Using the CARGO-Bench diagnostic suite, CARGO eliminates false penalties and improves discrimination while revealing a limitation in detecting procedural corruptions.
By Mukul Chhabra, Shail Patel, Luigi Medrano
arXiv:2606. 12451v1 Announce Type: new Abstract: Large language models deployed as agents over large tool catalogs face a critical tool-retrieval bottleneck.
By Ashutosh Hathidara, Sai Shruthi Sistla, Sebastian Schreiber, Sahil Bansal
arXiv:2607. 24882v1 Announce Type: cross Abstract: Modern coding agents are usually evaluated by whether they eventually produce a correct patch, but patch generation depends on an earlier context-acquisition stage: finding the repository files needed for the task.
By Bowen Qin, Yi Xie
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. 09794v1 Announce Type: new Abstract: Context learning is an emerging inference-time task where LLMs must learn and apply novel, task-specific knowledge from intricate contexts absent from pre-training; even frontier models score under 24% task success.
By Jike Zhong, Ming Li, Yuxiang Lai, Ziyan Yang, Jingyu Xie, Jihyung Kil, Zheda Mai, Shao-Yuan Lo, Ren Xiang, Konstantinos Psounis, Yuanyuan Lei