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.
arXiv:2607. 09510v1 Announce Type: cross Abstract: Large language model (LLM) coding agents are increasingly deployed to autonomously perform software engineering tasks in terminal-based environments, making their reliability a growing concern.
arXiv:2606. 01365v1 Announce Type: new Abstract: Tool-using multi-agent large language model (LLM) systems spend computation through model tokens, tool calls, retries, and code execution before producing an answer.
arXiv:2608. 02645v1 Announce Type: cross Abstract: Large Language Model (LLM) agents rely on external tools to perform multistage tasks.
arXiv:2607. 11098v1 Announce Type: cross Abstract: Tool-using LLM agents are mostly evaluated assuming all tools work.
arXiv:2606. 09863v1 Announce Type: new Abstract: LLM agents can fail silently by asserting task completion when the environment state shows otherwise.
The paper introduces rebuild‑dossier, an open‑source tool that locks an application’s real interface before code is written and enforces one‑test‑at‑a‑time building through automated checks. In experiments, a compliant agent failed a held‑back test while a rule‑breaking agent passed, showing that a passing test suite can be gamed. The study also demonstrates that the automated check mechanism, rather than interface‑locking alone, is crucial for reliable rebuilds, and that multi‑level verification catches errors that single‑level checks miss.
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.
arXiv:2608. 13867v1 Announce Type: cross Abstract: AI coding agents are commonly evaluated as models but deployed as systems.
The paper introduces a pre‑action verification framework for large language model agents that emit shell commands or code edits. By running deterministic checks before execution, the system can catch invalid commands (95.8% success with a 10.0% false‑positive rate) and prevent silent failures in code edits, achieving high recall while minimizing false positives. The authors provide benchmarks, verifiers, and guards for both action modalities.
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.
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.
arXiv:2609.13672v1 Announce Type: new Abstract: AI agents can be interrupted while editing files, calling tools, or carrying out multi-step tasks. Restarting repeats completed work, but continuing fr...