arXiv Machine Learning
The Value of Mechanistic Priors in Sequential Decision Making
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Aug 28
Safety by Design: Realized-Cost Constraints for Contextual Bandits with Continuous Actions
The paper introduces a new approach to safety in contextual bandits with continuous actions, focusing on high‑probability constraints on the realized cost rather than expected cost. It presents the High‑Probability Constrained UCB algorithm, which balances reward exploration with conservative safety estimation, and provides theoretical regret guarantees for linear models and extensions to general function classes. Experiments demonstrate that this realized‑cost safety framework significantly reduces safety violations compared to expected‑cost constrained methods.
arXiv AI
Jun 16
Free Energy Heuristics: Fast-And-Frugal Cognition as Active Inference Under Uncertain Precision
arXiv:2606. 15877v1 Announce Type: cross Abstract: Chain-of-thought (CoT) improves large language models' performance in math and symbolic reasoning.
Hugging Face Trending Papers
Aug 27
Safety by Design: Realized-Cost Constraints for Contextual Bandits with Continuous Actions
The paper introduces a new approach to safety in contextual bandits with continuous actions by enforcing high‑probability constraints on the realized cost rather than on its expectation. It proposes the High‑Probability Constrained UCB algorithm, which balances optimistic reward exploration with pessimistic safety estimation. The authors provide theoretical regret guarantees for linear models and extend the analysis to general function classes, demonstrating experimentally that realized‑cost constraints significantly reduce safety violations compared to expected‑cost baselines.
arXiv AI
Aug 26
Knowing When to Ask for Help: Bayesian Self-Escalation in Hierarchical LLM Agents
The paper introduces a Bayesian self‑escalation strategy for hierarchical large‑language‑model agents, allowing an agent to detect during its own reasoning that it is unlikely to succeed and hand control over to a stronger model. The authors formalise this as an optimal‑stopping problem over a learned competence posterior, derive a myopic escalation threshold, and prove that the optimal policy is a time‑varying threshold without assumptions on the raw signal. They provide theoretical guarantees—including a 1/√n regret decay with n calibration trajectories—and validate the approach in simulations and a real‑model code‑generation cascade, showing that the escalation frontier outperforms post‑hoc routing at equal cost. whyItMatters":"The study offers a principled, theoretically grounded method for agents to dynamically decide when to seek stronger models, potentially improving efficiency and reliability in hierarchical LLM systems."
arXiv Machine Learning
Jul 3
Prediction Sets for Counterfactual Decisions: Coverage, Optimality, and Conformal Prediction
arXiv:2607. 02206v1 Announce Type: cross Abstract: Predictions are increasingly used to guide high-stakes decisions, from treatment selection to policy making.
arXiv AI
1d ago
Satisficing as competitive Bayesian weighting: a minimal model of goal-directed choice under an unattained target
The paper introduces Risk‑Sensitive Satisficing (RS), a bandit learning rule that evaluates actions based on their past frequency and their surplus or shortfall relative to an aspiration level. RS can be reformulated as Attention Competitive Bayes (ACB), a Bayesian‑like estimator where the aspiration level serves as a prior mean and the limited number of trials limits how strongly evidence can override this prior. ACB predicts that unchosen actions gradually revert toward the aspiration level (pseudo‑forgetting) and that when the aspiration is unattainable, exploration never fully settles, reducing regret in simulations.