arXiv subjects

Bart Selman

Publications and source records attributed to Bart Selman.

At least 19 recordsLinked to original sources

arXiv2026

Agentic Neurosymbolic Collaboration for Mathematical Discovery: A Case Study in Combinatorial Design

We study mathematical discovery through the lens of neurosymbolic reasoning, where an AI agent powered by a large language model (LLM), coupled with symbolic computation tools, and human strategic direction, jointly produced a new result in combinatorial design theory. The main result of this human-AI collaboration is a tight lower bound on the imbalance of Latin squares for the notoriously difficult case $n \equiv 1 \pmod{3}$. We reconstruct the discovery process from detailed interaction logs spanning multiple sessions over several days and identify the distinct cognitive contributions of each component. The AI agent proved effective at uncovering hidden structure and generating hypotheses. The symbolic component consists of computer algebra, constraint solvers, and simulated annealing, which provides rigorous verification and exhaustive enumeration. Human steering supplied the critical research pivot that transformed a dead end into a productive inquiry. Our analysis reveals that multi-model deliberation among frontier LLMs proved reliable for criticism and error detection but unreliable for constructive claims. The resulting human-AI mathematical contribution, a tight lower bound of $4n(n{-}1)/9$, is achieved via a novel class of near-perfect permutations. The bound was formally verified in Lean 4. Our experiments show that neurosymbolic systems can indeed produce genuine discoveries in pure mathematics.

cs.AI↗

arXiv2025

LocalEscaper: A Weakly-supervised Framework with Regional Reconstruction for Scalable Neural TSP Solvers

Neural solvers have shown significant potential in solving the Traveling Salesman Problem (TSP), yet current approaches face significant challenges. Supervised learning (SL)-based solvers require large amounts of high-quality labeled data, while reinforcement learning (RL)-based solvers, though less dependent on such data, often suffer from inefficiencies. To address these limitations, we propose LocalEscaper, a novel weakly-supervised learning framework for large-scale TSP. LocalEscaper effectively combines the advantages of both SL and RL, enabling effective training on datasets with low-quality labels. To further enhance solution quality, we introduce a regional reconstruction strategy, which is the key technique of this paper and mitigates the local-optima problem common in existing local reconstruction methods. Experimental results on both synthetic and real-world datasets demonstrate that LocalEscaper outperforms existing neural solvers, achieving remarkable results.

cs.LG↗

arXiv2025

Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning

Scientific reasoning, the process through which humans apply logic, evidence, and critical thinking to explore and interpret scientific phenomena, is essential in advancing knowledge reasoning across diverse fields. However, despite significant progress, current scientific reasoning models still struggle with generalization across domains and often fall short of multimodal perception. Multimodal Large Language Models (MLLMs), which integrate text, images, and other modalities, present an exciting opportunity to overcome these limitations and enhance scientific reasoning. Therefore, this position paper argues that MLLMs can significantly advance scientific reasoning across disciplines such as mathematics, physics, chemistry, and biology. First, we propose a four-stage research roadmap of scientific reasoning capabilities, and highlight the current state of MLLM applications in scientific reasoning, noting their ability to integrate and reason over diverse data types. Second, we summarize the key challenges that remain obstacles to achieving MLLM's full potential. To address these challenges, we propose actionable insights and suggestions for the future. Overall, our work offers a novel perspective on MLLM integration with scientific reasoning, providing the LLM community with a valuable vision for achieving Artificial General Intelligence (AGI).

cs.CL↗

arXiv2024

SKI-SAT: A CMOS-compatible Hardware for Solving SAT Problems

Nature-inspired computation is receiving increasing attention. Various Ising machine implementations have recently been proven to be effective in solving numerous combinatorial optimization problems including maximum cut, low density parity check (LDPC) decoding, and Boolean satisfiability (SAT) problems. In this paper, a novel method is presented to solve SAT or MAX-SAT problems with a CMOS circuit implementation. The technique solves a SAT problem by mapping the SAT variables onto quantized capacitor voltages generated by an array of nodes that interact through a network of coupling units. The nodal interaction is achieved through coupling currents produced by the coupling units, which charge or discharge capacitor voltages, implementing a gradient descent along the SAT problem's cost function to minimize the number of unsatisfied clauses. The system also incorporates a unique low-complexity perturbation scheme to avoid settling in local minima, greatly enhancing the performance of the system. The simulation results demonstrate that the proposed SKI-SAT is a high-performance and low-energy alternative that surpasses existing solvers by significant margins, achieving more than 10 times faster solution and 300 times less power.

cs.IT↗

arXiv2023

Policy-Value Alignment and Robustness in Search-based Multi-Agent Learning

Large-scale AI systems that combine search and learning have reached super-human levels of performance in game-playing, but have also been shown to fail in surprising ways. The brittleness of such models limits their efficacy and trustworthiness in real-world deployments. In this work, we systematically study one such algorithm, AlphaZero, and identify two phenomena related to the nature of exploration. First, we find evidence of policy-value misalignment -- for many states, AlphaZero's policy and value predictions contradict each other, revealing a tension between accurate move-selection and value estimation in AlphaZero's objective. Further, we find inconsistency within AlphaZero's value function, which causes it to generalize poorly, despite its policy playing an optimal strategy. From these insights we derive VISA-VIS: a novel method that improves policy-value alignment and value robustness in AlphaZero. Experimentally, we show that our method reduces policy-value misalignment by up to 76%, reduces value generalization error by up to 50%, and reduces average value error by up to 55%.

cs.AI↗

arXiv2022

Graph Value Iteration

In recent years, deep Reinforcement Learning (RL) has been successful in various combinatorial search domains, such as two-player games and scientific discovery. However, directly applying deep RL in planning domains is still challenging. One major difficulty is that without a human-crafted heuristic function, reward signals remain zero unless the learning framework discovers any solution plan. Search space becomes \emph{exponentially larger} as the minimum length of plans grows, which is a serious limitation for planning instances with a minimum plan length of hundreds to thousands of steps. Previous learning frameworks that augment graph search with deep neural networks and extra generated subgoals have achieved success in various challenging planning domains. However, generating useful subgoals requires extensive domain knowledge. We propose a domain-independent method that augments graph search with graph value iteration to solve hard planning instances that are out of reach for domain-specialized solvers. In particular, instead of receiving learning signals only from discovered plans, our approach also learns from failed search attempts where no goal state has been reached. The graph value iteration component can exploit the graph structure of local search space and provide more informative learning signals. We also show how we use a curriculum strategy to smooth the learning process and perform a full analysis of how graph value iteration scales and enables learning.

cs.AI↗

arXiv2022

Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning

Despite the success of practical solvers in various NP-complete domains such as SAT and CSP as well as using deep reinforcement learning to tackle two-player games such as Go, certain classes of PSPACE-hard planning problems have remained out of reach. Even carefully designed domain-specialized solvers can fail quickly due to the exponential search space on hard instances. Recent works that combine traditional search methods, such as best-first search and Monte Carlo tree search, with Deep Neural Networks' (DNN) heuristics have shown promising progress and can solve a significant number of hard planning instances beyond specialized solvers. To better understand why these approaches work, we studied the interplay of the policy and value networks of DNN-based best-first search on Sokoban and show the surprising effectiveness of the policy network, further enhanced by the value network, as a guiding heuristic for the search. To further understand the phenomena, we studied the cost distribution of the search algorithms and found that Sokoban instances can have heavy-tailed runtime distributions, with tails both on the left and right-hand sides. In particular, for the first time, we show the existence of \textit{left heavy tails} and propose an abstract tree model that can empirically explain the appearance of these tails. The experiments show the critical role of the policy network as a powerful heuristic guiding the search, which can lead to left heavy tails with polynomial scaling by avoiding exploring exponentially sized subtrees. Our results also demonstrate the importance of random restarts, as are widely used in traditional combinatorial solvers, for DNN-based search methods to avoid left and right heavy tails.

cs.AI↗

arXiv2021

A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances

In recent years, we have witnessed tremendous progress in deep reinforcement learning (RL) for tasks such as Go, Chess, video games, and robot control. Nevertheless, other combinatorial domains, such as AI planning, still pose considerable challenges for RL approaches. The key difficulty in those domains is that a positive reward signal becomes {\em exponentially rare} as the minimal solution length increases. So, an RL approach loses its training signal. There has been promising recent progress by using a curriculum-driven learning approach that is designed to solve a single hard instance. We present a novel {\em automated} curriculum approach that dynamically selects from a pool of unlabeled training instances of varying task complexity guided by our {\em difficulty quantum momentum} strategy. We show how the smoothness of the task hardness impacts the final learning results. In particular, as the size of the instance pool increases, the ``hardness gap'' decreases, which facilitates a smoother automated curriculum based learning process. Our automated curriculum approach dramatically improves upon the previous approaches. We show our results on Sokoban, which is a traditional PSPACE-complete planning problem and presents a great challenge even for specialized solvers. Our RL agent can solve hard instances that are far out of reach for any previous state-of-the-art Sokoban solver. In particular, our approach can uncover plans that require hundreds of steps, while the best previous search methods would take many years of computing time to solve such instances. In addition, we show that we can further boost the RL performance with an intricate coupling of our automated curriculum approach with a curiosity-driven search strategy and a graph neural net representation.

cs.AI↗

arXiv2021

Automating Crystal-Structure Phase Mapping: Combining Deep Learning with Constraint Reasoning

Crystal-structure phase mapping is a core, long-standing challenge in materials science that requires identifying crystal structures, or mixtures thereof, in synthesized materials. Materials science experts excel at solving simple systems but cannot solve complex systems, creating a major bottleneck in high-throughput materials discovery. Herein we show how to automate crystal-structure phase mapping. We formulate phase mapping as an unsupervised pattern demixing problem and describe how to solve it using Deep Reasoning Networks (DRNets). DRNets combine deep learning with constraint reasoning for incorporating scientific prior knowledge and consequently require only a modest amount of (unlabeled) data. DRNets compensate for the limited data by exploiting and magnifying the rich prior knowledge about the thermodynamic rules governing the mixtures of crystals with constraint reasoning seamlessly integrated into neural network optimization. DRNets are designed with an interpretable latent space for encoding prior-knowledge domain constraints and seamlessly integrate constraint reasoning into neural network optimization. DRNets surpass previous approaches on crystal-structure phase mapping, unraveling the Bi-Cu-V oxide phase diagram, and aiding the discovery of solar-fuels materials.

cs.LG↗

arXiv2021

Structure Amplification on Multi-layer Stochastic Block Models

Much of the complexity of social, biological, and engineered systems arises from a network of complex interactions connecting many basic components. Network analysis tools have been successful at uncovering latent structure termed communities in such networks. However, some of the most interesting structure can be difficult to uncover because it is obscured by the more dominant structure. Our previous work proposes a general structure amplification technique called HICODE that uncovers many layers of functional hidden structure in complex networks. HICODE incrementally weakens dominant structure through randomization allowing the hidden functionality to emerge, and uncovers these hidden structure in real-world networks that previous methods rarely uncover. In this work, we conduct a comprehensive and systematic theoretical analysis on the hidden community structure. In what follows, we define multi-layer stochastic block model, and provide theoretical support using the model on why the existence of hidden structure will make the detection of dominant structure harder compared with equivalent random noise. We then provide theoretical proofs that the iterative reducing methods could help promote the uncovering of hidden structure as well as boosting the detection quality of dominant structure.

cs.SI↗

arXiv2021

Multi-Agent Curricula and Emergent Implicit Signaling

Emergent communication has made strides towards learning communication from scratch, but has focused primarily on protocols that resemble human language. In nature, multi-agent cooperation gives rise to a wide range of communication that varies in structure and complexity. In this work, we recognize the full spectrum of communication that exists in nature and propose studying lower-level communication. Specifically, we study emergent implicit signaling in the context of decentralized multi-agent learning in difficult, sparse reward environments. However, learning to coordinate in such environments is challenging. We propose a curriculum-driven strategy that combines: (i) velocity-based environment shaping, tailored to the skill level of the multi-agent team; and (ii) a behavioral curriculum that helps agents learn successful single-agent behaviors as a precursor to learning multi-agent behaviors. Pursuit-evasion experiments show that our approach learns effective coordination, significantly outperforming sophisticated analytical and learned policies. Our method completes the pursuit-evasion task even when pursuers move at half of the evader's speed, whereas the highest-performing baseline fails at 80% of the evader's speed. Moreover, we examine the use of implicit signals in coordination through position-based social influence. We show that pursuers trained with our strategy exchange more than twice as much information (in bits) than baseline methods, indicating that our method has learned, and relies heavily on, the exchange of implicit signals.

cs.MA↗

arXiv2021

Cooperative Multi-Agent Fairness and Equivariant Policies

We study fairness through the lens of cooperative multi-agent learning. Our work is motivated by empirical evidence that naive maximization of team reward yields unfair outcomes for individual team members. To address fairness in multi-agent contexts, we introduce team fairness, a group-based fairness measure for multi-agent learning. We then prove that it is possible to enforce team fairness during policy optimization by transforming the team's joint policy into an equivariant map. We refer to our multi-agent learning strategy as Fairness through Equivariance (Fair-E) and demonstrate its effectiveness empirically. We then introduce Fairness through Equivariance Regularization (Fair-ER) as a soft-constraint version of Fair-E and show that it reaches higher levels of utility than Fair-E and fairer outcomes than non-equivariant policies. Finally, we present novel findings regarding the fairness-utility trade-off in multi-agent settings; showing that the magnitude of the trade-off is dependent on agent skill.

cs.AI↗

arXiv2020

Low-Bandwidth Communication Emerges Naturally in Multi-Agent Learning Systems

In this work, we study emergent communication through the lens of cooperative multi-agent behavior in nature. Using insights from animal communication, we propose a spectrum from low-bandwidth (e.g. pheromone trails) to high-bandwidth (e.g. compositional language) communication that is based on the cognitive, perceptual, and behavioral capabilities of social agents. Through a series of experiments with pursuit-evasion games, we identify multi-agent reinforcement learning algorithms as a computational model for the low-bandwidth end of the communication spectrum.

cs.MA↗

arXiv2020

Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning

Despite significant progress in general AI planning, certain domains remain out of reach of current AI planning systems. Sokoban is a PSPACE-complete planning task and represents one of the hardest domains for current AI planners. Even domain-specific specialized search methods fail quickly due to the exponential search complexity on hard instances. Our approach based on deep reinforcement learning augmented with a curriculum-driven method is the first one to solve hard instances within one day of training while other modern solvers cannot solve these instances within any reasonable time limit. In contrast to prior efforts, which use carefully handcrafted pruning techniques, our approach automatically uncovers domain structure. Our results reveal that deep RL provides a promising framework for solving previously unsolved AI planning problems, provided a proper training curriculum can be devised.

cs.AI↗

arXiv2020

Hidden Community Detection on Two-layer Stochastic Models: a Theoretical Perspective

Hidden community is a new graph-theoretical concept recently proposed [4], in which the authors also propose a meta-approach called HICODE (Hidden Community Detection) for detecting hidden communities. HICODE is demonstrated through experiments that it is able to uncover previously overshadowed weak layers and uncover both weak and strong layers at a higher accuracy. However, the authors provide no theoretical guarantee for the performance. In this work, we focus on the theoretical analysis of HICODE on synthetic two-layer networks, where layers are independent of each other and each layer is generated by stochastic block model. We bridge their gap through two-layer stochastic block model networks in the following aspects: 1) we show that partitions that locally optimize modularity correspond to grounded layers, indicating modularity-optimizing algorithms can detect strong layers; 2) we prove that when reducing found layers, HICODE increases absolute modularities of all unreduced layers, showing its layer reduction step makes weak layers more detectable. Our work builds a solid theoretical base for HICODE, demonstrating that it is promising in uncovering both weak and strong layers of communities in two-layer networks.

cs.SI↗

arXiv2019

A 20-Year Community Roadmap for Artificial Intelligence Research in the US

Decades of research in artificial intelligence (AI) have produced formidable technologies that are providing immense benefit to industry, government, and society. AI systems can now translate across multiple languages, identify objects in images and video, streamline manufacturing processes, and control cars. The deployment of AI systems has not only created a trillion-dollar industry that is projected to quadruple in three years, but has also exposed the need to make AI systems fair, explainable, trustworthy, and secure. Future AI systems will rightfully be expected to reason effectively about the world in which they (and people) operate, handling complex tasks and responsibilities effectively and ethically, engaging in meaningful communication, and improving their awareness through experience. Achieving the full potential of AI technologies poses research challenges that require a radical transformation of the AI research enterprise, facilitated by significant and sustained investment. These are the major recommendations of a recent community effort coordinated by the Computing Community Consortium and the Association for the Advancement of Artificial Intelligence to formulate a Roadmap for AI research and development over the next two decades.

cs.CY↗

arXiv2018

Understanding Batch Normalization

Batch normalization (BN) is a technique to normalize activations in intermediate layers of deep neural networks. Its tendency to improve accuracy and speed up training have established BN as a favorite technique in deep learning. Yet, despite its enormous success, there remains little consensus on the exact reason and mechanism behind these improvements. In this paper we take a step towards a better understanding of BN, following an empirical approach. We conduct several experiments, and show that BN primarily enables training with larger learning rates, which is the cause for faster convergence and better generalization. For networks without BN we demonstrate how large gradient updates can result in diverging loss and activations growing uncontrollably with network depth, which limits possible learning rates. BN avoids this problem by constantly correcting activations to be zero-mean and of unit standard deviation, which enables larger gradient steps, yields faster convergence and may help bypass sharp local minima. We further show various ways in which gradients and activations of deep unnormalized networks are ill-behaved. We contrast our results against recent findings in random matrix theory, shedding new light on classical initialization schemes and their consequences.

cs.LG↗

arXiv2017

XOR-Sampling for Network Design with Correlated Stochastic Events

Many network optimization problems can be formulated as stochastic network design problems in which edges are present or absent stochastically. Furthermore, protective actions can guarantee that edges will remain present. We consider the problem of finding the optimal protection strategy under a budget limit in order to maximize some connectivity measurements of the network. Previous approaches rely on the assumption that edges are independent. In this paper, we consider a more realistic setting where multiple edges are not independent due to natural disasters or regional events that make the states of multiple edges stochastically correlated. We use Markov Random Fields to model the correlation and define a new stochastic network design framework. We provide a novel algorithm based on Sample Average Approximation (SAA) coupled with a Gibbs or XOR sampler. The experimental results on real road network data show that the policies produced by SAA with the XOR sampler have higher quality and lower variance compared to SAA with Gibbs sampler.

cs.AI↗