arXiv:2607. 24339v1 Announce Type: new Abstract: Large language model (LLM) agents inherit reactive failure modes: escalation under provocation, sycophantic drift under flattery, perseveration when stuck.
arXiv:2608. 04066v1 Announce Type: new Abstract: How do you verify a long-horizon agent when its own state and self-reports are exactly what you cannot trust?
arXiv:2608.22347v1 Announce Type: new Abstract: A cognitive architecture is more than the module that reasons: it must also decide how long to think and what deserves the effort. We built a minimal b...
arXiv:2609.36570v1 Announce Type: cross Abstract: Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that...
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.
arXiv:2608. 05863v1 Announce Type: new Abstract: Modern models no longer keep a plain KV cache: latent caches, learned sparse selectors and recurrent states each carry the model's memory in a different form, and each fails differently under compression.
The paper investigates how tool‑using language‑model agents can safely commit changes to infrastructure when external state may change between read and commit. By distinguishing invalidating races from predicate‑preserving and irrelevant ones, the authors evaluate three commit‑time guard granularities—global epoch, read‑set version, and semantic commit predicate—using a deterministic simulator and three quantized model families. The study finds that only the complete predicate guard consistently eliminates unsafe commits, while freshness‑based guards block a large proportion of benign races and model‑side signals fail to replace precise semantic enforcement.
arXiv:2606. 25449v1 Announce Type: cross Abstract: A language model's memory can be worse than having no memory at all.
arXiv:2606. 06460v3 Announce Type: replace-cross Abstract: Autonomous LLM agents increasingly hold real credentials and operate infrastructure with no human in the loop, yet operators have no standard way to tell an agent a resource is off-limits, or to ask a running agent to stand down: access controls either admit it or hard-fail it.
arXiv:2606. 07552v2 Announce Type: replace-cross Abstract: Large language models exhibit a risk-averse "turtle" bias as strategic agents.
arXiv:2607. 00871v1 Announce Type: new Abstract: Self-evolving agents violate the assumption behind most learning-theoretic guarantees: the data, evaluator, components, and hypothesis space are produced by the policy being updated.
arXiv:2609.36490v1 Announce Type: cross Abstract: Latent space monitors aim to detect undesired behaviors in LLM agents by inspecting an agent's internal activations rather than its outputs. However,...
The paper audits LLM-based explainers attached to an Active Inference agent that manages German grid demand, testing three large‑language‑model backends (GPT‑4o, Claude‑3‑Opus, Gemini). By injecting corrupted observations and attacker‑controlled text, the study finds that the explainers fail to flag errors, produce fluent but incorrect rationalizations for wrong actions, and can be steered to exfiltrate data. The authors propose mitigations but do not evaluate them, emphasizing that explanations are never verified for truth before operators rely on them.