AINeutralarXiv – CS AI · May 127/10
🧠Researchers introduced MathConstraint, an adaptive benchmark for testing large language models' combinatorial reasoning abilities using constraint satisfaction problems with automated verification. The benchmark reveals significant performance gaps between frontier models, with accuracy dropping from 72-87% on easier instances to 18-66% on harder ones, while tool access via Python solvers roughly doubles performance.
🧠 GPT-5
AIBullisharXiv – CS AI · Apr 147/10
🧠CircuitSynth is a neuro-symbolic framework that addresses hallucinations and logical inconsistencies in LLM-generated synthetic data by combining probabilistic decision diagrams with optimization mechanisms to enforce hard constraints and distributional guarantees. The approach achieves 100% schema validity across complex benchmarks while outperforming existing methods in coverage, representing a significant advancement in reliable synthetic data generation for machine learning applications.
AIBullisharXiv – CS AI · Mar 97/10
🧠Researchers developed Localized In-Context Learning (L-ICL), a technique that significantly improves large language model performance on symbolic planning tasks by targeting specific constraint violations with minimal corrections. The method achieves 89% valid plan generation compared to 59% for best baselines, representing a major advancement in LLM reasoning capabilities.
AIBullisharXiv – CS AI · Mar 56/10
🧠Researchers introduce JANUS, a new AI framework that solves the 'Quadrilemma' in synthetic data generation by achieving high fidelity, logical constraint control, reliable uncertainty estimation, and computational efficiency simultaneously. The system uses Bayesian Decision Trees and a novel Reverse-Topological Back-filling algorithm to guarantee 100% constraint satisfaction while being 128x faster than existing methods.
AIBullisharXiv – CS AI · 2d ago6/10
🧠Researchers introduce LsrIF, a training framework that improves how large language models follow complex instructions by recognizing logical structures like sequential dependencies and conditional branching. The method uses structure-aware reward aggregation instead of simple averaging, demonstrating improved instruction-following performance both within and across domains.
AINeutralarXiv – CS AI · 4d ago5/10
🧠BrickAnything is a new AI framework that generates physically buildable brick structures from 3D shapes by combining geometric reconstruction with structural constraints. The method uses structure-aware tokenization to model how bricks attach to each other, improving the feasibility and stability of generated designs compared to existing heuristic approaches.
AINeutralarXiv – CS AI · 4d ago5/10
🧠Researchers present 2-ASP(Q)^w, a fragment of Answer Set Programming extended with quantifiers and weak constraints, proving its theoretical complexity bounds and introducing practical computation strategies using CEGAR techniques. The work bridges theoretical computer science with implementable solutions for optimization problems, offering both formal completeness results and experimental validation on real-world benchmarks.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers introduce DSAT, a native SAT solver designed to work directly with discrete variables rather than converting them to binary Boolean variables. The solver applies traditional SAT techniques like unit resolution and clause learning to discrete logic, offering potential computational and semantic advantages over existing binarization approaches for applications in probabilistic reasoning, planning, and explainable AI.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers introduce primal-dual guided decoding, an inference-time method for discrete diffusion models that enforces global constraints during token generation through adaptive Lagrangian multipliers and KL-regularized optimization. The approach requires no model retraining, supports multiple simultaneous constraints, and demonstrates effectiveness across text generation, molecular design, and music applications.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers propose SMER-Opt, a novel approach to molecular optimization that combines a single-step edit response predictor with multi-step planning via tree search. The method addresses the challenge of editing molecules for desired properties by treating molecular edits as discrete actions guided by chemical feasibility rules, reducing dependence on external oracles and improving data efficiency.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers introduce Neural CFRS, a non-autoregressive neural network framework that solves the Capacitated Vehicle Routing Problem by clustering nodes first, then routing—departing from sequential autoregressive methods. The approach uses differentiable optimal transport to enforce capacity constraints and achieves competitive results on benchmarks while scaling robustly to large, out-of-distribution instances.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers propose an adaptive data harvesting approach using reinforcement learning to dynamically select training samples for neural networks constrained by universal conditions. The method improves upon fixed heuristics for training Lyapunov Neural Networks and Physics-Informed Neural Networks, demonstrating faster convergence and better solution quality across test problems.
AINeutralarXiv – CS AI · May 115/10
🧠Researchers present CM-Tabu, a composite-move Tabu search algorithm that solves spatial redistricting optimization problems more effectively by expanding the feasible solution space while maintaining district contiguity constraints. The method uses graph analysis to identify minimal unit movements or swaps that preserve connectivity, achieving superior solution quality and computational efficiency compared to traditional approaches.
AINeutralarXiv – CS AI · May 115/10
🧠Researchers present a novel computational method for generating sequences constrained by regular automata using variable-order Markov models. The advancement eliminates the need to expand full K-tuple state spaces while maintaining exact inference, achieving linear complexity for fixed models and enabling efficient constrained sequence generation across applications.
AINeutralarXiv – CS AI · Apr 156/10
🧠Researchers introduce Text2Model and Text2Zinc, frameworks that use large language models to translate natural language descriptions into formal optimization and satisfaction models. The work represents the first unified approach combining both problem types with a solver-agnostic architecture, though experiments reveal LLMs remain imperfect at this task despite showing competitive performance.
AINeutralarXiv – CS AI · Apr 136/10
🧠Researchers introduce CONDESION-BENCH, a new benchmark for evaluating how large language models make decisions in complex, real-world scenarios with compositional actions and conditional constraints. The benchmark addresses limitations in existing decision-making frameworks by incorporating variable-level, contextual, and allocation-level restrictions that better reflect actual decision-making environments.
AINeutralarXiv – CS AI · Apr 136/10
🧠Researchers introduced NLCO, a benchmark for evaluating large language models on natural-language combinatorial optimization problems without external solvers or code generation. Testing across modern LLMs reveals that while high-performing models handle small instances well, performance degrades significantly as problem complexity increases, with graph-structured and bottleneck-objective problems proving particularly challenging.
AINeutralarXiv – CS AI · Mar 36/107
🧠Researchers introduced Pencil Puzzle Bench, a new framework for evaluating large language model reasoning capabilities using constraint-satisfaction problems. The benchmark tested 51 models across 300 puzzles, revealing significant performance improvements through increased reasoning effort and iterative verification processes.
AIBullisharXiv – CS AI · Mar 27/1019
🧠Researchers have developed a safety filtering framework that ensures AI generative models like diffusion models produce outputs that satisfy hard constraints without requiring model retraining. The approach uses Control Barrier Functions to create a 'constricting safety tube' that progressively tightens constraints during the generation process, achieving 100% constraint satisfaction across image generation, trajectory sampling, and robotic manipulation tasks.
