The paper introduces a method to transform entire trace corpora of LLM-based agents into compact finite-state machines (FSMs) that capture shared behavioral structure. These FSMs, comprising 7–43 states, achieve near-perfect replay of held‑out data and enable accurate next‑step prediction and failure detection across twelve public datasets. The approach offers a model‑agnostic structural tool for safety auditing and runtime monitoring of agent behavior.
arXiv:2606. 09863v1 Announce Type: new Abstract: LLM agents can fail silently by asserting task completion when the environment state shows otherwise.
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:2607. 11388v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled increasingly capable digital agents for computer use.
arXiv:2607. 16247v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) have empowered embodied agents to execute complex household tasks, they struggle to proactively handle dynamically emerging hazards during closed-loop interactions.
Software engineering (SWE) agents resolve repository-level issues through long trajectories that grow increasingly expensive as context accumulates. Failed runs tend to be longer and exhibit redundant exploration or looping, suggesting that some failures may be detectable before completion.
arXiv:2607. 06503v1 Announce Type: new Abstract: Large language model (LLM) agents solving multi-step tasks frequently commit to trajectories that are doomed to fail, yet continue to consume substantial inference compute before the failure becomes observable.
The paper demonstrates that safety mechanisms for autonomous large language model agents fail to compose across iterative loops, as trajectory‑scoped monitors cannot detect attacks whose evidence is spread over multiple iterations. It introduces LoopHarness, a system that maintains a persistent, non‑decaying safety state across loops, bounding unauthorized actions with a constant that does not grow with the number of iterations. The authors provide a comprehensive evaluation protocol, including attacks that require cross‑iteration evidence, module ablations, and adaptive white‑box red‑team testing.
arXiv:2608. 02464v1 Announce Type: cross Abstract: LLM agents fail mid-episode -- they loop, cascade tool errors, drift off goal, fabricate results, or silently absorb corrupted content -- and the standard remedy, judging every step with a second LLM, costs more than the agent itself.
arXiv:2609.08589v1 Announce Type: cross Abstract: Recent large language models can emit task-progress signals that agent frameworks use to decide whether a task should continue or stop, yet whether a...
The paper introduces AOI (Autonomous Operations Intelligence), a multi‑agent framework that treats automated site reliability tasks as a structured trajectory learning problem under security constraints. It combines a trainable diagnostic system using Group Relative Policy Optimization, a read‑write separated execution architecture, and a Failure Trajectory Closed‑Loop Evolver that turns unsuccessful runs into corrective supervision. On the AIOpsLab benchmark, AOI achieves significant performance gains, including a 66.3% best@5 success rate and improved average metrics on unseen fault types.
arXiv:2605.27690v2 Announce Type: replace-cross Abstract: LLM agents increasingly operate through multi-turn tool use and environment interaction, where safety risks often emerge from intermediate st...
The paper introduces EMFA, a method for attributing failures in large language model-based multi-agent systems by identifying the decisive error—an agent–step pair whose correction would restore correct execution. EMFA builds a structured representation of the failed trajectory, models error propagation and persistent loops, and applies propagation-aware screening with counterfactual verification to pinpoint the decisive error. On the Who&When benchmark, EMFA outperforms prior methods, improving step-level attribution accuracy by 3.45 and 4.40 percentage points on two subsets.