arXiv:2608. 11154v1 Announce Type: new Abstract: Detecting or attributing a supply-chain disruption is not the same as selecting the intervention that maximizes recoverable net value.
arXiv:2608. 02685v1 Announce Type: cross Abstract: Coding-agent benchmarks increasingly cover long-horizon, end-to-end, and interactive development, but typically retain one requested outcome or a fixed change sequence.
arXiv:2606. 13884v1 Announce Type: new Abstract: Modern decision systems increasingly rely on learned components whose outputs may be confident yet wrong, exposing downstream actions to costly errors.
arXiv:2606. 06698v1 Announce Type: new Abstract: Production agentic systems routinely face evolving constraints and must comply from the very next interaction.
The paper introduces the concept of causal retention in interactive agents, examining whether a frozen learned state can correctly answer a mechanism‑probe map that is fixed independently of training. It shows that for finite structural causal models the optimal probe error is a Bayes decision risk, vanishing only when each learning‑interface fiber lies within a single probe‑answer fiber, and provides theoretical results such as a posterior‑coverage theorem and an exact edit decomposition. Experiments on finite causal systems, continuous simulators, TD‑MPC2, and Qwen2.5‑7B‑Instruct demonstrate that causal retention can be achieved with high accuracy, outperforming task‑performance‑based approaches.
arXiv:2607. 23134v1 Announce Type: new Abstract: Discovering rare safety-critical failures in autonomous and cyber-physical systems is a fundamental challenge in verification and validation.
arXiv:2609.24112v1 Announce Type: cross Abstract: Causal Bayesian Optimization (CBO) combines causal inference with Bayesian optimization to enable sample-efficient intervention selection in systems...
arXiv:2603. 16475v2 Announce Type: replace Abstract: In schema-guided reasoning (SGR) pipelines, LLMs produce explicit intermediate structures -- rubrics, checklists, or verification queries -- before committing to a final decision.
CausalArena is a new benchmark designed to evaluate causal discovery methods in the era of foundation models. It unifies synthetic structural causal models (SCMs), semantically grounded SCMs, and formula‑grounded SCMs, while also including real‑world datasets for external validation. Experiments show that performance rankings vary widely across different SCM families and protocols, indicating that strong results on one benchmark do not necessarily transfer to others.
arXiv:2608. 07809v1 Announce Type: new Abstract: A world model is only useful for physical AI if it changes what the agent does, and only safe if it declines to do so when it is wrong.
arXiv:2608.21748v1 Announce Type: new Abstract: Verifier-guided text-to-image systems increasingly use test-time search to select, refine, or stop among multiple candidates, yet release thresholds ar...
ObserverBench is a benchmark framework that evaluates whether internal mechanistic estimators—called observers—are suitable for guiding interventions, control, or safety actions in language models. It separates estimation accuracy from the loss incurred by the chosen action, showing that accurate predictions do not always lead to better decisions. Experiments on GPT‑2‑small, Qwen2.5‑7B, Gemma‑2‑9B‑it, and Qwen3.5‑9B demonstrate that observers trained on action loss can reduce deployment loss, while traditional metrics like AUROC may rank monitors differently from actual performance.
Delay-risk models are usually judged by predictive accuracy. What matters in practice is narrower: with capacity to review only a few shipments, which ones should a manager check first?