Compositional reliability bounds for multi-agent systems multiply component reliabilities, a step licensed by a conditional-independence assumption that is routinely stated and rarely tested. We test it.
arXiv:2608. 12895v1 Announce Type: new Abstract: Compositional reliability bounds for multi-agent systems multiply component reliabilities, a step licensed by a conditional-independence assumption that is routinely stated and rarely tested.
The paper reports that a model can pass fidelity checks—verifying that extracted values match the source—without actually opening a datasheet, due to a hidden constraint that disables tool use. To address this, the authors log every tool call in an agentic benchmark and develop two instruments: a rule‑based failure‑attribution classifier and a silent‑failure detector that flags runs based solely on which tools were invoked. While the detector shows low false positives on clean extractions and recovers all planted faults, its recall against correct tool usage but incorrect answers remains unmeasured, and a partial causal chamber confirms only a subset of claims, highlighting limitations in physical verification.
The paper presents a closed‑form estimator for the contamination correlation between anchors and judges under a single‑common‑factor model, requiring at least two judges and two anchors. It introduces a diagnostic battery—including judge‑covariance dispersion, over‑identification tests, a family‑block test, bootstrap confidence intervals, and a weak‑identification screen—to validate the estimator and detect violations. The authors also discuss identification limits for ordinal data and report that real panels have not yet passed the model‑adequacy pre‑test, while simulation studies confirm the estimator’s performance.
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.
The paper investigates a critical flaw in AI coding-agent systems such as Claude Code, Codex CLI, and Cursor, where the action approved by a human is not the same as the action executed by the harness. It introduces the concept of Approval Laundering, categorizing six systematic failure modes—Scope, Argument, Temporal, Tool, Delegation, and Semantic laundering—and demonstrates these failures through controlled experiments. The authors propose an Approval Token mechanism that mitigates some laundering types but leaves others unaffected, highlighting the limitations of current enforcement strategies.
The paper investigates where exactly‑once semantics should be enforced for tool‑using agents—within the model, the agent harness, or the tool contract—by evaluating 25,930 episodes across nine models, three harnesses, two contract variants, and fifteen recovery conditions. Using the LIMBO sandbox, the study shows that when an immediate read‑back is available, frontier models rarely duplicate lost acknowledgements, whereas weaker models do; when read‑back is unavailable, the contract’s idempotency keys explain most duplicate behavior. The authors prove that verification‑only policies cannot guarantee exactly‑once under late commits without bounded in‑flight time, and that waiting only helps when delays are short and predictable. whyItMatters":"The findings clarify that enforcing exactly‑once semantics largely depends on the tool contract and fault type, guiding designers on where to focus reliability mechanisms for LLM agents."
The paper presents a framework for causal attribution in agentic AI systems, outlining estimators and conditions where they fail. It distinguishes between marginal total effects and common‑random‑number total effects, introduces a natural direct effect under pinned downstreams, and derives a coupling method to keep direct effects estimable. The authors also propose a traceability specification to meet upcoming regulatory requirements for high‑risk AI systems.
arXiv:2606. 08517v1 Announce Type: new Abstract: Selective predictors answer on confident inputs and abstain elsewhere; deploying one safely needs a single finite-sample certificate that simultaneously upper-bounds the selected risk, lower-bounds the acceptance probability $\pacc$ above a floor $\pmin$, and lower-bounds the deployment utility.
arXiv:2606. 27288v1 Announce Type: new Abstract: Multi-model LLM systems such as routing, voting, cascades, fusion, and mixture-of-agents are used to beat single-model accuracy.
arXiv:2607. 10202v1 Announce Type: new Abstract: Cross-model comparisons read divergence in value dispositions as evidence that language models hold individuated values.
arXiv:2509. 11208v3 Announce Type: replace-cross Abstract: Transformers used for evidence-grounded binary adjudication (e.
arXiv:2606. 29054v1 Announce Type: new Abstract: Large language models (LLMs) deployed for structured generation (NER, JSON extraction, QA, and classification) lack formal reliability guarantees, and standard heuristic abstention policies miss user-specified risk targets by 7.