arXiv:2607. 10059v1 Announce Type: new Abstract: Agent systems based on large language models (LLMs) are increasingly deployed for autonomous tasks, yet existing evaluations mostly focus on task success rather than whether agents know when to abstain.
By Xun Liu, Yi Evie Zhang, Vira Kasprova, Parisa Rabbani, Pardis Sadat Zahraei, Tianyu Zhang, Ali Ebrahimpour-Boroojeny, Varun Chandrasekaran
The paper introduces RAS‑Eval, a specification‑based security evaluation framework for large language model agents that uses Linear Temporal Logic (LTL) to define utility and security objectives over tool‑call trajectories and dynamic environment observations. Unlike traditional LLM‑as‑a‑Judge or Agent‑as‑a‑Judge approaches, RAS‑Eval derives deterministic verdicts via a model checker, reducing evaluator uncertainty and enabling reliable assessment over long‑horizon tasks. The authors also present a multi‑agent dataset pipeline and a benchmark of 200 normal and 800 attack tasks covering indirect prompt injection, tool poisoning, skill code injection, and tool code injection.
whyItMatters":"RAS‑Eval addresses key limitations of existing security evaluations—such as evaluator hallucination and missed transient violations—by providing deterministic, environment‑aware verdicts that are crucial for safely deploying LLM agents in unattended, long‑horizon scenarios."
By Yuchuan Fu, Minghe Wang, Xiaohan Yuan, Chenlin Zou, Kaitong Jia, Jinfeng Li, Dongxia Wang
arXiv:2607. 04542v1 Announce Type: cross Abstract: Every LLM agent run re-derives its behavior token by token on a frontier model: brilliant, expensive, slow, and unbounded.
By Jaber Jaber, Osama Jaber
The paper introduces Soei, a structured observability framework for AI coding agents, addressing the need to track what work was done, by whom, and whether it is finished. It evaluates an existing tool, Agenttrail, revealing inconsistencies and security gaps, and presents empirical findings from 45 real coding-agent sessions, highlighting issues such as unverified code edits and credential exposure. Soei comprises an event schema, hash‑chained ledger, PROV‑aligned graph, and verification layer, achieving efficient storage, fast verification, and tamper detection on the same dataset.
By Mohammed Nayeem Khan, K S Sarun Kumar
arXiv:2604. 13072v2 Announce Type: replace-cross Abstract: OpenClaw-style personal assistants extend LLM agents from isolated tool use to open-ended, stateful, and personalized software environments.
By Xiang Long, Li Du, Yilong Xu, RongJian Xu, Qiyanhui Lu, Ying Gao, Qinhua Xie, Fangcheng Liu, Ning Ding, Haoqing Wang, Ziheng Li, Changjiang Zhou, Jianyuan Guo, Yehui Tang
arXiv:2610.14146v1 Announce Type: new
Abstract: Long-horizon terminal benchmarks measure whether an agent can sustain progress through extended workflows with process rewards, not only whether its fi...
By Zongxia Li, Zhongzhi Li, Yucheng Shi, Ruhan Wang, Junyao Yang, Chengsong Huang, Zhichao Liu, Xiyang Wu, Anhao Li, Yue Yu, Ergan Shang, Fuxiao Liu, Tong Zheng, Ninghao Liu, Lichao Sun, Haitao Mi, Leowei Liang
arXiv:2508.18370v3 Announce Type: replace-cross
Abstract: Large language models (LLMs) have demonstrated exceptional capabilities when trained within executable runtime environments, notably excellin...
By Terry Yue Zhuo, Dingmin Wang, Hantian Ding, Varun Kumar, Zijian Wang
The paper introduces agent‑native primitives—reusable building blocks that embed a language model within a resource to apply it contextually—and HEELO, a harness‑engineering framework that composes these primitives into task‑specific graphs, verifies outcomes, and iteratively refines or adds primitives. Using eight primitive families, the authors demonstrate significant performance gains across multiple benchmarks, raising Terminal‑Bench 4.0 resolution from 37.3% to 55.5% and improving pass rates on ToolBench and GAIA‑Text‑103. When integrated with HEELO, Claude Opus 5.5 and GPT‑6.1 Sol achieve higher completion counts, faster runtimes, and lower costs on 46 real‑world tasks.
By Haibo Jin, Peng Kuang, Xiaopeng Yuan, Lucheng Fu, Jerry Wang, Xucheng Yu, Yaoning Yu, Dehao Wu, Runguo Li, Colin Su, Jingxuan Sun, Xuyang Liu, Haojing Luo, Haohan Wang
BekchiAI introduces a benchmark and platform for evaluating large language model agents. The benchmark comprises 13 tool‑using ReAct agents across seven task categories, totaling 2,057 deterministic test tasks with verifier‑checkable gold answers. The platform offers web‑based observability, token and latency telemetry, and remote run termination for live agents.
By Mesut Toruk
arXiv:2607. 16345v1 Announce Type: cross Abstract: Modern agentic systems increasingly rely on skills: installable packages of natural language and code that teach an LLM agent to perform a domain task.
By Tejas Singh Anand, Yuet Ying Christina Wang, Wanting Jiang, Steve Masson, Tian Zheng, Bingjie Zhou
arXiv:2604. 16706v2 Announce Type: replace Abstract: Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, yet this assumption is rarely validated against human annotation.
By Bhaskar Gurram
Large language models are deployed as long-horizon agents that compose diverse tools across MCP services into executable workflows. Existing MCP environment-scaling methods are data-centric: they firs...