Reasoning models excel in complex problem solving but exhibit a concerning trade off between reasoning capabilities and instruction following abilities. Existing approaches for improving instruction following rely on stronger external models, creating methodological bottlenecks and practical limitations including increased costs and accessibility constraints. We propose a self-supervised RL framework that leverages reasoning models' own internal signals to improve instruction following capabilities without external supervision. Extensive experiments demonstrate that our framework significantly improves instruction following capabilities while maintaining reasoning performance, offering a scalable and cost-effective approach to enhance instruction following in reasoning models. The data and code are publicly available at https://github.com/Rainier-rq/verl-if.

A core challenge in program synthesis is taming the large space of possible programs. Since program synthesis is essentially a combinatorial search, the community has sought to leverage powerful combinatorial constraint solvers. Here, constraints are used to express the program semantics, but not as a potentially potent tool to remove unwanted programs. Recent inductive logic programming approaches introduce constraints on the program's syntax to be synthesized. These syntactic constraints allow for checking and propagating a constraint without executing the program, and thus for arbitrary operators. In this work, we leverage syntactic constraints to model program spaces, defining not just solutions that are feasible, but also ones that are likely useful. To demonstrate this idea, we introduce BART, a solver that efficiently propagates and solves these constraints. We evaluate BART on program space enumeration tasks, finding that the constraints eliminate up to 99 percent of the program space, and that modeling program spaces significantly reduces enumeration time.

Sampling Boltzmann probability distributions plays a key role in machine learning and optimization, motivating the design of hardware accelerators such as Ising machines. While the Ising model can in principle encode arbitrary optimization problems, practical implementations are often hindered by soft constraints that either slow down mixing when too strong, or fail to enforce feasibility when too weak. We introduce a two-dimensional extension of the powerful parallel tempering algorithm (PT) that addresses this challenge by adding a second dimension of replicas interpolating the penalty strengths. This scheme ensures constraint satisfaction in the final replicas, analogous to low-energy states at low temperature. The resulting two-dimensional parallel tempering algorithm (2D-PT) improves mixing in heavily constrained replicas and eliminates the need to explicitly tune the penalty strength. In a representative example of graph sparsification with copy constraints, 2D-PT achieves near-ideal mixing, with Kullback-Leibler divergence decaying as O(1/t). When applied to sparsified Wishart instances, 2D-PT yields orders of magnitude speedup over conventional PT with the same number of replicas. The method applies broadly to constrained Ising problems and can be deployed on existing Ising machines.

We present a systematic approach for evaluating the quality of knowledge graph repairs with respect to constraint violations defined in shapes constraint language (SHACL). Current evaluation methods rely on \emph{ad hoc} datasets, which limits the rigorous analysis of repair systems in more general settings. Our method addresses this gap by systematically generating violations using a novel mechanism, termed violation-inducing operations (VIOs). We use the proposed evaluation framework to assess a range of repair systems which we build using large language models. We analyze the performance of these systems across different prompting strategies. Results indicate that concise prompts containing both the relevant violated SHACL constraints and key contextual information from the knowledge graph yield the best performance.

-- Panoramic RGB-D cameras are known for their ability to produce high-quality 3D scene reconstructions. However, operating these cameras involves manually selecting viewpoints and physically transporting the camera, making the generation of a 3D model time-consuming and tedious. Additionally, the process can be challenging for novice users due to spatial constraints, such as ensuring sufficient feature overlap between viewpoint frames. T o address these challenges, we propose a fully autonomous scan planning system that generates an efficient tour plan for environment scanning, ensuring collision-free navigation and adequate overlap between viewpoints within the plan. Extensive experiments conducted in both synthetic and real-world environments validate our planner's performance against state-of-the-art view planners. In particular, our method achieved an average scan coverage of 99% in the real-world experiment, with our approach being up to 3 faster than state-of-the-art planners in total scan time. The increasing advancements in mobile robotics research have enhanced robots' ability to improve the efficiency and completeness of outcomes in various active trajectory planning tasks.

--T o gain deeper insights into a complex sensor system through the lens of causality, we present common and individual causal mechanism estimation (CICME), a novel three-step approach to inferring causal mechanisms from heterogeneous data collected across multiple domains. By leveraging the principle of Causal Transfer Learning (CTL), CICME is able to reliably detect domain-invariant causal mechanisms when provided with sufficient samples. The identified common causal mechanisms are further used to guide the estimation of the remaining causal mechanisms in each domain individually. The performance of CICME is evaluated on linear Gaussian models under scenarios inspired from a manufacturing process. Building upon existing continuous optimization-based causal discovery methods, we show that CICME leverages the benefits of applying causal discovery on the pooled data and repeatedly on data from individual domains, and it even outperforms both baseline methods under certain scenarios. In manufacturing systems, sensors are widely deployed to monitor machines, components, and environmental conditions.

Qualitative timeline-based planning models domains as sets of independent, but interacting, components whose behaviors over time, the timelines, are governed by sets of qualitative temporal constraints (ordering relations), called synchronization rules. Its plan-existence problem has been shown to be PSPACE-complete; in particular, PSPACE-membership has been proved via reduction to the nonemptiness problem for nondeterministic finite automata. However, nondeterministic automata cannot be directly used to synthesize planning strategies as a costly determinization step is needed. In this paper, we identify a fragment of qualitative timeline-based planning whose plan-existence problem can be directly mapped into the nonemptiness problem of deterministic finite automata, which can then synthesize strategies. In addition, we identify a maximal subset of Allen's relations that fits into such a deterministic fragment.

Neuro-symbolic artificial intelligence aims to combine neural architectures with symbolic approaches that can represent knowledge in a human-interpretable formalism. Continual learning concerns with agents that expand their knowledge over time, improving their skills while avoiding to forget previously learned concepts. Most of the existing approaches for neuro-symbolic artificial intelligence are applied to static scenarios only, and the challenging setting where reasoning along the temporal dimension is necessary has been seldom explored. In this work we introduce LTLZinc, a benchmarking framework that can be used to generate datasets covering a variety of different problems, against which neuro-symbolic and continual learning methods can be evaluated along the temporal and constraint-driven dimensions. Our framework generates expressive temporal reasoning and continual learning tasks from a linear temporal logic specification over MiniZinc constraints, and arbitrary image classification datasets. Fine-grained annotations allow multiple neural and neuro-symbolic training settings on the same generated datasets. Experiments on six neuro-symbolic sequence classification and four class-continual learning tasks generated by LTLZinc, demonstrate the challenging nature of temporal learning and reasoning, and highlight limitations of current state-of-the-art methods. We release the LTLZinc generator and ten ready-to-use tasks to the neuro-symbolic and continual learning communities, in the hope of fostering research towards unified temporal learning and reasoning frameworks.

Constraint Logic Programming (CLP) is a logic programming formalism used to solve problems requiring the consideration of constraints, like resource allocation and automated planning and scheduling. It has previously been extended in various directions, for example to support fuzzy constraint satisfaction, uncertainty, or negation, with different notions of semiring being used as a unifying abstraction for these generalizations. None of these extensions have studied clauses with negation allowed in the body. We investigate an extension of CLP which unifies many of these extensions and allows negation in the body. We provide semantics for such programs, using the framework of approximation fixpoint theory, and give a detailed overview of the impacts of properties of the semirings on the resulting semantics. As such, we provide a unifying framework that captures existing approaches and allows extending them with a more expressive language.

Many critical decision-making tasks are now delegated to machine-learned models, and it is imperative that their decisions are trustworthy and reliable, and their outputs are consistent across similar inputs. We identify a new source of unreliable behaviors-called glitches-which may significantly impair the reliability of AI models having steep decision boundaries. Roughly speaking, glitches are small neighborhoods in the input space where the model's output abruptly oscillates with respect to small changes in the input. We provide a formal definition of glitches, and use well-known models and datasets from the literature to demonstrate that they have widespread existence and argue they usually indicate potential model inconsistencies in the neighborhood of where they are found. We proceed to the algorithmic search of glitches for widely used gradient-boosted decision tree (GBDT) models. We prove that the problem of detecting glitches is NP-complete for tree ensembles, already for trees of depth 4. Our glitch-search algorithm for GBDT models uses an MILP encoding of the problem, and its effectiveness and computational feasibility are demonstrated on a set of widely used GBDT benchmarks taken from the literature.