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.
By Vijay Erramilli
arXiv:2605. 09692v3 Announce Type: replace Abstract: Autonomous language agents increasingly expose traces, memories, plans and constraints, but existing evaluations rarely test whether these state variables are bound to final actions.
By Xiao Jia
The paper introduces a self‑healing harness that enforces admission control over language‑model agents’ self‑modifications. The harness runs a Detect‑Notice‑Heal‑Validate loop, allowing agents to propose rule changes that are only granted persistent authority after demonstrating improvement on a failure case without regressing on protected cases. Across 16 benchmark runs, the harness rejected many locally beneficial proposals that caused collateral regressions, while improving task‑completion scores and reliability.
By Sina Tayebati, Divake Kumar, Nastaran Darabi, Ranganath Krishnan, Amit Ranjan Trivedi
arXiv:2606. 04296v1 Announce Type: new Abstract: As autonomous AI agents move from conversational systems to long-horizon software execution, runtime safety layers that decide when to interrupt an agent have become essential.
By Manvendra Modgil
arXiv:2607. 08349v1 Announce Type: new Abstract: Mechanistic interpretability often evaluates explanations by intervening on a model: swapping hidden states, patching activations, ablating components, or comparing a compressed model to the original one.
By Amir Asiaee
The paper introduces a counterfactual tool ranking framework that accounts for authority, historical support, and estimation nuances. Using eleven enterprise-inspired tools, synthetic and real-world experiments on the Berkeley Function Calling Leaderboard, the study compares direct regression and doubly robust (DR) methods, finding that DR performs better in shifted environments while direct regression excels in linear settings. The authors also evaluate Qwen2.5 models on held-out tasks, analyze policy differences under missing support, and present a falsifiable evaluation method with publicly available evidence.
By Jiapeng Li
The paper introduces the concept of intervention fidelity in latent world models, measuring whether a model’s open‑loop transitions align with actual environment interventions. Experiments on TD‑MPC2, Cheetah, and DreamerV3 show that high reward fit does not guarantee fidelity, and that self‑supervised models can outperform task‑anchored ones in preserving intervention effects. The authors propose a capture‑gated audit to localize failures and argue that fidelity must be directly audited on the model’s native interface.
By Donna Vakalis
arXiv:2605. 06890v3 Announce Type: replace Abstract: AI agents are promising for high-stakes enterprise workflows, but dependable deployment remains limited because tool-use failures are difficult to diagnose and control.
By Hariom Tatsat, Ariye Shater
arXiv:2603. 28590v3 Announce Type: replace Abstract: Large language models (LLMs) can generate chains of thought (CoTs) that are not always causally responsible for their final outputs.
By Han Wang, Yifan Sun, Brian Ko, Mann Talati, Jiawen Gong, Zimeng Li, Naicheng Yu, Xucheng Yu, Wei Shen, Vedant Jolly, Huan Zhang
arXiv:2606. 11063v1 Announce Type: new Abstract: AI control protocols oversee untrusted models by monitoring their actions and modifying potentially unsafe steps, often using a trusted model.
By Joachim Schaeffer, Thomas Jiralerspong, Alexander Panfilov, Guillaume Lajoie, Jonas Geiping, Yoshua Bengio, Roland S. Zimmermann
The paper introduces a framework for evaluating AI systems that not only checks final labels but also tracks the reasoning behind them through three core sources—grounds, norms, and authority—forming an eight-cell counterfactual judgment cube. It defines minimal source replacement sets, called judgment receipts, to explain changes in verdicts and provides certification cost bounds for black-box evaluators. The authors present ReasonBench, a benchmark with 19,520 cases, and demonstrate that while high standard accuracy can mask robustness issues, receipt accuracy reveals significant gaps in reasoning consistency across different models.
By Ye Chen, Weining Zhang
arXiv:2606. 30449v1 Announce Type: new Abstract: Probes on model internals could help monitor agentic systems if they identify harmful text or tool actions before those actions are generated.
By Max Fomin, Elad David, Amit LeVi