The paper argues that when a human corrects an LLM assistant’s mistake, the correction often disappears after the session ends, highlighting an operations issue rather than a tooling one. Drawing on thirty years of systems engineering experience, the author maps the LLM stack onto traditional hardware and software components, identifies mismatches—such as stochastic generation and lack of a retirement stage—and proposes a seven‑principle operating discipline centered on an error loop. The paper includes three real‑world cases, one of which illustrates how a control mechanism can inadvertently cause the harm it was meant to prevent, and concludes with a suggested measurement framework and a lab study to validate the approach.
arXiv:2607. 11098v1 Announce Type: cross Abstract: Tool-using LLM agents are mostly evaluated assuming all tools work.
By Aritra Mazumder, Nusrat jahan Lia
arXiv:2607. 13071v1 Announce Type: cross Abstract: Agentic LLM coding tools compress long session histories into compaction summaries that subsequent sessions inherit as ground truth.
By Hiroki Tamba
Everyone is talking about loop engineering, but most discussions assume an LLM sits at the center of the loop. I wanted to isolate the architecture itself.
By Emmimal P Alexander
arXiv:2606. 14589v1 Announce Type: cross Abstract: LLM agent systems increasingly run as long-lived autonomous runtimes: scheduling jobs, calling tools, maintaining memory, and pushing results to humans.
By Wei Wu
arXiv:2606. 01416v1 Announce Type: new Abstract: Tool-augmented large language model (LLM) agents rely on orchestration layers that coordinate planning, retrieval, tool invocation, validation, memory, and recovery.
By Rahul Suresh Babu, Adarsh Agrawal
The study investigates why small language model agents tend to repeat a tool call that just failed. By recording the failed call and its error message in the transcript, the authors measure a negative corrective gain—agents are more likely to repeat the failed action, with a drop of about 1.03 nats per token. The problem is traced to the harness design rather than the model’s understanding of errors, and the authors show that replacing the verbatim call with a runtime-generated description of the failure can reduce this backfiring effect by 76%.
By Esmail Gumaan
arXiv:2608.25920v2 Announce Type: replace
Abstract: As large language model (LLM)-based multi-agent systems (MASs) are increasingly applied to long-horizon complex tasks, their reliability has emerge...
By Zhongwen Luan, Xiaoyu Zhang, Ming Hu, Yue Yang, Jiongchi Yu, Xiaohong Chen
arXiv:2605. 16309v2 Announce Type: replace Abstract: LLM-based agents can recover from individual execution errors, yet they repeatedly fail on the same fault when the underlying process knowledge--operator schemas, preconditions, and constraints--remains unrepaired.
By Safayat Bin Hakim, Keyan Guo, Wenkai Tan, Alvaro Velasquez, Shouhuai Xu, Houbing Herbert Song
The paper investigates the reliability of language‑model judges used as measurement instruments on shared endpoints. Through two preregistered audits of 52,988 requests, the authors found that repeat rankings and byte‑identical replays fell far short of required thresholds, revealing significant instability. They identify three mechanisms—label‑to‑meaning bias, candidate gaps below the noise floor, and input permutation noise—that explain the gap, and propose a snapshot‑identity ladder, design rules, and a reporting checklist to mitigate such failures.
The paper reports a failure study of a production agentic software‑delivery platform, analyzing 147 incidents across 81 runs. It shows that the standard reliability primitives—retry, timeout, and error‑rate circuit breaking—fail in practice, leading to costly loops, false trips, and blocked work. The authors identify two cross‑cutting causes—identity adequacy and evidence adequacy—and propose seven new reliability primitives that enforce reliability at the delegation level.
By Mazhar Shaikh, Anurag Rajkumar Bombarde, Harshal Pathak
arXiv:2606. 05806v1 Announce Type: new Abstract: Existing benchmarks evaluate Tool-Integrated Reasoning (TIR) in LLMs on idealized ''happy paths'', largely overlooking real-world tool failures.
By Dongsheng Zhu, Xuchen Ma, Yucheng Shen, Xiang Li, Yukun Zhao, Shuaiqiang Wang, Lingyong Yan, Dawei Yin