arXiv:2606. 29225v1 Announce Type: new Abstract: LLM agents handle user requests on behalf of organizations through tool calls and must follow the company policies stated in their system prompts.
By Seongjae Kang, Taehyung Yu, Sung Ju Hwang
The paper introduces JevAct, a runtime verification framework that intercepts selected actions of large language model (LLM) agents before execution. JevAct compiles domain policies into executable state checks and uses a prefill-only decision model to provide probability‑based judgments, enabling feedback‑driven correction without modifying the underlying agent. Evaluations on eleven LLM agents across Airline, Telecom, and BFCL benchmarks show that JevAct improves agent reliability, especially on Telecom and BFCL tasks.
By Iftach Shoham, Yuval David, Offer Akrabi, Erez Bilgory, Ido Levy, Sami Marreed, Sergey Zeltyn, Segev Shlomov
arXiv:2609.26048v1 Announce Type: cross
Abstract: Language-model agents often reach a working solution and then fail to consistently deliver it. We study runtime policies: targeted natural-language i...
By Nikita Agarwal, Nivedit Jain
arXiv:2611.02332v1 Announce Type: cross
Abstract: Tool-using language-model agents often execute actions that their domain policies forbid. We present LeanGuard, a runtime that checks every proposed...
By Sreehari Sankar, Debargha Ganguly, Vikash Singh, Mohsen Hariri, Weicong Chen, Yanyan Zhang, Shouren Wang, Wang Yang, Chaoda Song, Alexander Nemecek, Osama Zafar, Idan Davidovich, Yuting Shao, Kai Ye, Biyao Zhang, Xinpeng Li, Joe Stubbs, Erman Ayday, Jing Ma, Vipin Chaudhary
The paper studies how to curate the fixed context files that large language model agents load at the start of each session. It models this as a capacitated assortment problem, proving bounds on optimal file size and showing that simply appending all positive‑value instructions can be far suboptimal. The authors analyze censored feedback from past sessions, derive evidence‑collection thresholds for adding instructions, bound regret under limited human review, and empirically demonstrate that irrelevant rules in real context files hurt model compliance.
By Zexuan Liu, Yuning Yang, Tiancheng Zhao
The paper argues that large language model agents should not be the sole authority on whether they have satisfied a task. It identifies two gaps—understanding–execution and state–authority—where agents may claim completion without actually meeting the specification. The authors propose SpecHarness, a framework that separates agent proposals from authoritative state by requiring evidence from qualified providers to confirm compliance, and demonstrate its effectiveness on guideline‑following and artifact‑generation tasks.
By Haiqing Li, Xin Ma, Yinhao Wu, Wenliang Zhong, Feng Jiang, Thao M. Dang, Xiao Hu, Hehuan Ma, Yuzhi Guo, Junzhou Huang