AIBullisharXiv – CS AI · Jun 257/10
🧠Researchers developed a multi-agent AI system that autonomously designs hardware-compatible computing systems using an Evolutionary Knowledge Graph, successfully compressing a 235-billion-parameter foundation model onto constrained dual-A100 servers with 75% memory reduction. The framework evolved two novel compression techniques (Q-Enhance and MoE-Salient-AQ) that outperform manually-engineered alternatives, establishing a scalable paradigm for hardware-software co-design in AI deployment.
AIBullisharXiv – CS AI · Jun 237/10
🧠Researchers propose a hierarchical reinforcement learning method that combines learned world models with dual-level policies to enable safe exploration in long-horizon tasks. The approach uses high-level subgoals to guide exploration toward safe regions and low-level imagined rollouts to minimize unsafe behaviors, demonstrating significant improvements over existing Safe RL baselines on complex navigation and manipulation tasks.
AIBullisharXiv – CS AI · Jun 197/10
🧠Researchers introduce the Rule Violation Score (RVS), a new evaluation metric that measures whether predictive models respect logical and domain-specific constraints independently of accuracy. Unlike traditional metrics focused on prediction performance, RVS distinguishes between hard rules (strict constraints) and soft rules (statistical regularities), enabling assessment of logical consistency in high-stakes applications like finance and healthcare.
AIBearisharXiv – CS AI · Jun 107/10
🧠Researchers introduce τ-Rec, a new benchmark for evaluating conversational AI recommender systems that replaces subjective LLM-based judging with verifiable, measurable rewards. Testing across nine model configurations reveals a critical reliability gap, with even top-performing models achieving only ~57% accuracy on single-attempt tasks, exposing significant limitations in current agentic AI deployment.
🧠 GPT-5🧠 Claude🧠 Sonnet
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.
AINeutralarXiv – CS AI · Jun 196/10
🧠Researchers introduce PCBSchemaGen, a training-free framework that enables large language models to generate verified PCB schematics by combining datasheet-derived domain schemas with deterministic verification and Thompson Sampling refinement. The approach achieves 81.3% task success on real IC designs without requiring unit tests or golden references, establishing a general method for LLM code synthesis in domains lacking traditional test oracles.
AIBullisharXiv – CS AI · Jun 116/10
🧠Researchers demonstrate a multi-agent AI framework using AutoGen that automates reinforced concrete barrier design with 98% accuracy while requiring significantly fewer computational resources than larger language models. The lightweight 8B-parameter model outperforms 631B-parameter flagship models, suggesting AI-assisted engineering tools can achieve production-grade performance at substantially lower cost.
AIBullisharXiv – CS AI · Jun 96/10
🧠Researchers introduce Projected Consistency Inference (PCI), a neural optimization method that solves the Traveling Salesman Problem more efficiently than gradient-based approaches by using structure-aware projections and local search instead of computationally expensive refinement. PCI achieves better optimality gaps (0.17% for 500 cities, 0.31% for 1000 cities) while reducing inference time by 30-40% compared to state-of-the-art FT2T methods.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers introduce Q-RACL, a quantum-enhanced machine learning framework that uses quantum computing to solve a critical constraint satisfaction problem: determining which repairs can restore feasibility to rejected candidates. The system demonstrates quantum advantage in accessing hidden discrete logarithm features that classical algorithms cannot efficiently process, achieving false-veto rates below 1.1% where classical approaches fail.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers introduce a neuro-symbolic framework that integrates Linear Temporal Logic constraints into transformer-based reinforcement learning policies, enabling AI systems to satisfy high-level temporal requirements while maintaining competitive performance. The method compiles logical specifications into deterministic finite automata and uses differentiable signals to regularize training, demonstrating improved constraint satisfaction in navigation tasks.
AINeutralarXiv – CS AI · Jun 86/10
🧠DiBS introduces a diffusion model-guided approach to optimize branch selection in Sudoku solving, combining symbolic solver completeness with learned global guidance. The method substantially reduces search costs on hard instances while maintaining correctness guarantees, demonstrating how neural models can enhance traditional constraint satisfaction algorithms.
AINeutralarXiv – CS AI · Jun 86/10
🧠Researchers have developed AFSAT, a GPU-accelerated solver for pseudo-Boolean satisfiability problems that builds on continuous local search principles. The fully-engineered system uses JAX compilation techniques to achieve substantial improvements in numerical stability, runtime performance, and memory efficiency while scaling efficiently across multiple accelerators.
AINeutralarXiv – CS AI · Jun 85/10
🧠Researchers present an empirical study of parallel Continuous Local Search (CLS) as a method for solving Boolean satisfiability problems with pseudo-Boolean constraints. Key findings reveal that redundant constraints can slow convergence, CLS shows promise as a hybrid solver component, and local search quickly plateaus due to saddle-dense optimization landscapes.
AINeutralarXiv – CS AI · Jun 55/10
🧠Researchers propose BiXDFBnB, a bidirectional depth-first branch-and-bound algorithm that efficiently applies front-to-front heuristics to longest-path problems by adapting the Single-Frontier Bidirectional Search framework. The method reduces computational overhead typically associated with bidirectional frontier management, achieving both fewer node expansions and improved runtime performance on several problem variants.
AINeutralarXiv – CS AI · Jun 56/10
🧠Researchers propose MDP-GRPO, an improved reinforcement learning method that stabilizes group relative policy optimization for instruction-following tasks by addressing three fundamental instabilities in reward normalization. The technique achieves up to 5% improvement in constraint satisfaction on language models while maintaining general performance capabilities.
🧠 Llama
AINeutralarXiv – CS AI · Jun 46/10
🧠Researchers introduce a framework for training neural networks to solve combinatorial puzzles optimally by enforcing admissibility constraints—ensuring heuristics never overestimate remaining costs. The method combines an underestimating Bellman operator with asymmetric loss functions and post-hoc calibration, achieving significant reductions in search node expansions while maintaining solution optimality.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers propose a framework for generating physically consistent structural engineering code using large language models, introducing CivilInstruct dataset and MBEval benchmark to reduce hallucinations and ensure simulation-ready outputs. The approach combines domain knowledge, constraint-oriented alignment, and verification-driven evaluation to overcome current limitations in automated building modeling.
AIBullisharXiv – CS AI · Jun 16/10
🧠PhyDrawGen is a neuro-symbolic AI system that generates physics diagrams from natural language text while maintaining strict physical accuracy. By combining large language models, deterministic solvers, and vision-language models in a pipeline, it overcomes the hallucination problems of current generative models and outperforms GPT-4, Gemini 2.5, and Gemini 3 Pro on physics problems spanning mechanics, optics, and electromagnetism.
🧠 GPT-5🧠 Gemini
AIBullisharXiv – CS AI · Jun 16/10
🧠Researchers present a distributed multi-agent reinforcement learning method that uses state augmentation and consensus algorithms to enforce global constraints while maintaining linear scalability. The approach enables thousands of agents to coordinate through local communication alone, outperforming centralized training methods that scale quadratically and fail on real-world constraint satisfaction problems like smart grid management.
AINeutralarXiv – CS AI · Jun 16/10
🧠Researchers introduce PlanningBench, a framework for generating scalable and verifiable planning datasets to evaluate and train large language models on complex task coordination. The system uses a constraint-driven synthesis pipeline with adaptive difficulty control and finds that current frontier LLMs struggle with coupled constraints, though reinforcement learning on verified data improves performance across planning and instruction-following tasks.
AIBullisharXiv – CS AI · May 296/10
🧠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 · May 275/10
🧠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.
