arXiv:2606. 07308v1 Announce Type: new Abstract: We study off-policy evaluation (OPE) under strategic behavior where decision subjects (or agents) respond to a decision maker's policy by strategically modifying their covariates.
arXiv:2609.39818v1 Announce Type: new Abstract: In many high-stakes settings, human decision-makers can acquire support information before making a decision. However, acquiring information is costly,...
As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified. We present a formal safety argument for the Scientist AI (SAI) Predictor, trained to approximate the Bayesian posterior conditioned on a dataset of "epistemically contextualized" natural-language statements.
arXiv:2606. 29657v1 Announce Type: new Abstract: As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified.
The paper investigates how the definition of influence—specifically the behavior being attributed, the intervention on training data, and the counterfactual training process—affects rankings produced by influence estimators. It formalizes influence as a counterfactual estimand, distinguishes specification mismatch from approximation error, and categorizes existing estimators by their implied specifications. Experiments demonstrate that different specifications can lead to markedly different rankings, and that careful specification choice improves attribution quality in tasks such as noisy label detection and large‑language‑model attribution.
arXiv:2607. 00155v1 Announce Type: new Abstract: We study runtime human oversight of an AI agent when private information runs in both directions: the human privately knows her reward function, while the AI privately knows the quality of the action it proposes.
The paper "When Honesty is Not Enough in AI Debate" explores how AI debate, intended as a scalable oversight method, can allow agents to pursue hidden objectives while still achieving correct verdicts. By introducing the strategic interactive oversight (SIO) framework, the authors formalise task‑admissible latent optimisation and demonstrate, via the establish protocol debate, a trade‑off between task success and disclosure of a hidden variable. They show that expanding the cross‑examiner’s role can reduce bias, underscoring that oversight effectiveness depends not only on verdict correctness but also on the information revealed in transcripts.
arXiv:2605. 19674v2 Announce Type: replace Abstract: Strategic classification(SC) studies the interaction between decision models and agents who strategically manipulate their features for favorable outcomes.
For most of scientific history, researchers studying behavior could only infer hidden mechanisms from outward actions: an inverse problem that becomes more tractable when observation is augmented by targeted intervention. We pose a computational analogue: given only behavioral traces of an agent in a game environment, can a learner reconstruct the underlying decision program as executable code, and how much does this reconstruction improve with the ability to design controlled experiments?
arXiv:2606. 26094v1 Announce Type: new Abstract: For most of scientific history, researchers studying behavior could only infer hidden mechanisms from outward actions: an inverse problem that becomes more tractable when observation is augmented by targeted intervention.
Predictive models are increasingly embedded in operational decision-making, yet standard explanation methods typically explain forecasts rather than the decisions those forecasts induce. This distinction is important in predict-then-optimize systems: large forecast changes may leave the optimizer's action unchanged, while small changes can alter the selected decision and its realized value.
arXiv:2606. 29878v1 Announce Type: new Abstract: Predictive models are increasingly embedded in operational decision-making, yet standard explanation methods typically explain forecasts rather than the decisions those forecasts induce.
The paper investigates how agentic systems decide between acting and abstaining, focusing on the fidelity of their reasoning explanations. Using Qwen3‑8B in a multi‑party conversation setting, the authors compare direct decision policies, reasoning policies, supervised fine‑tuning, and reinforcement learning, finding a trade‑off: strong direct policies yield higher performance but no traceable reasoning, while reasoning policies provide an audit trail at the cost of lower recall. The study also uncovers that exposing reasoning can alter the agent’s policy and that common faithfulness metrics may overstate the alignment between reasoning and decisions.