Building on the analysis of Bonanno (Artificial Intelligence, 2025) we introduce a simple modal logic containing three modal operators: a unimodal belief operator, a bimodal conditional operator and the unimodal global operator. For each AGM axiom for belief revision, we provide a corresponding modal axiom. The correspondence is as follows: each AGM axiom is characterized by a property of the Kripke-Lewis frames considered in Bonanno (Artificial Intelligence, 2025) and, in turn, that property characterizes the proposed modal axiom.

We show how the AGM framework for belief change (expansion, revision, contraction) can be extended to deal with conditioning in the so-called Desirability-Indifference framework, based on abstract notions of accepting and rejecting options, as well as on abstract notions of events. This level of abstraction allows us to deal simultaneously with classical and quantum probability theory.

Bayes-adaptive planning offers a principled solution to the explorationexploitation trade-off under model uncertainty. It finds the optimal policy in belief space, which explicitly accounts for the expected effect on future rewards of reductions in uncertainty. However, the Bayes-adaptive solution is typically intractable in domains with large or continuous state spaces. We present a tractable method for approximating the Bayes-adaptive solution by combining simulationbased search with a novel value function approximation technique that generalises appropriately over belief space. Our method outperforms prior approaches in both discrete bandit tasks and simple continuous navigation and control tasks.

Weaknesses: - Presentation: I think the space that the paper spends on the BP background is more than necessary since the BP algorithm is just the standard one. The paper would be more compelling if the BP background is compressed and a more complete explanation of their algorithm is presented, for example some visual illustration that comes with the explanation of their implementation in Section 3.3. Moreover, since there are not many notations used in the paper, it is better not to use the same notation for different meanings to avoid confusion. For example, k is used for the number of top elements throughout the paper and also index of variable at Line 285; at Line 301 the parameter H is used without definition, and later on at Line 302 it denotes the tree height while at Line 334 a parameter in the Splash algorithm. Could the authors provide some conceptual or empirical comparison of them with the proposed one? Distributed Parallel Inference on Large Factor Graphs.

Reviewers agreed, in reviews and discussion, that this paper presents a nice, simple idea very clearly. The author feedback included new experiments and a new baseline, with positive results. I enjoyed reading the paper too.

Partially Observable Markov Decision Processes (POMDPs) provide a robust framework for decision-making under uncertainty in applications such as autonomous driving and robotic exploration. Their extension, $\rho$POMDPs, introduces belief-dependent rewards, enabling explicit reasoning about uncertainty. Existing online $\rho$POMDP solvers for continuous spaces rely on fixed belief representations, limiting adaptability and refinement - critical for tasks such as information-gathering. We present $\rho$POMCPOW, an anytime solver that dynamically refines belief representations, with formal guarantees of improvement over time. To mitigate the high computational cost of updating belief-dependent rewards, we propose a novel incremental computation approach. We demonstrate its effectiveness for common entropy estimators, reducing computational cost by orders of magnitude. Experimental results show that $\rho$POMCPOW outperforms state-of-the-art solvers in both efficiency and solution quality.

We would like a robot to navigate to a goal location while minimizing state uncertainty. To aid the robot in this endeavor, maps provide a prior belief over the location of objects and regions of interest. To localize itself within the map, a robot identifies mapped landmarks using its sensors. However, as the time between map creation and robot deployment increases, portions of the map can become stale, and landmarks, once believed to be permanent, may disappear. We refer to the propensity of a landmark to disappear as landmark evanescence. Reasoning about landmark evanescence during path planning, and the associated impact on localization accuracy, requires analyzing the presence or absence of each landmark, leading to an exponential number of possible outcomes of a given motion plan. To address this complexity, we develop BRULE, an extension of the Belief Roadmap. During planning, we replace the belief over future robot poses with a Gaussian mixture which is able to capture the effects of landmark evanescence. Furthermore, we show that belief updates can be made efficient, and that maintaining a random subset of mixture components is sufficient to find high quality solutions. We demonstrate performance in simulated and real-world experiments. Software is available at https://bit.ly/BRULE.

The major contributions of this paper are that it proves the global convergence of BP(Theorem 1.3) and VI(Theorem 1.2) on ferromagnetic Ising model with a specific initialization, i.e., to initialize variables to be 1. The proof of Theorem 1.2 is based on the fact that the mean-field free energy function, i.e., \Phi(x) is concave on the set S obtained by the update rule, and then we can use Holder's inequality to expand the \Phi(x*) - Phi(x_t) and get the upper bounds. The proof of Theorem 1.3 is based on the fact that the norm of \Phi(v)'s gradient is less than 1(Lemma 3.2), and the properties of variable \mu sandwiched between v 0 and final v T(Lemma 3.5 and Lemma F.1). Other minor contributions include that it provides examples to empirically show the convergence(appendix G) and it shows how to use ellipsoid method to optimize the beliefs(appendix H). I have to admit that I am not familiar with this area, so can only go through a part of the proof, and I am not able to evaluate the originality and quality of this work.

The reviewers liked the results on convergence of belief propagation algorithms for Ising models under certain settings. As a presentational suggestion, they suggest providing more extensive proof sketches in the main section of the paper.

This submission drew a great deal of discussion -- primarily on the point of the role of learning. All reviewers agreed that the approach had the potential to learn interesting, non-trivial things but did not feel the the current experiments demonstrated these effectively -- despite strong performance on the task. Some examples of questions that were not answered by the main draft but came up in the discussion: [Training Data] The training data provides edges in the dependency graph, subgoals, and predicate value -- image pairs. One question was whether the union of the seen dependency graph constituted the entire true underlying graph. Similarly, do all predicate-object pairs occur?