AIBearisharXiv – CS AI · 5d ago7/10
🧠A study of a deployed food-and-beverage ordering chatbot reveals that LLM-based quality judges catch fewer than 25% of genuine defects, missing systematic failures in state-tracking and multi-turn consistency while excelling only at single-turn issues. The research demonstrates that automated evaluation metrics are fundamentally insufficient for production multi-agent systems and should not replace human review.
AIBullisharXiv – CS AI · Jun 57/10
🧠Researchers propose PACT, a new protocol for multi-agent AI systems that compresses inter-agent communication into compact action-state records, reducing token usage by up to 50% while maintaining or improving task performance. The approach addresses a critical efficiency bottleneck in large language model-based multi-agent systems, with demonstrated improvements in production coding applications.
AIBullisharXiv – CS AI · Jun 57/10
🧠Researchers introduced PRECISE, a method combining human annotations with LLM judgments to produce statistically reliable ranking evaluation metrics. The approach reduces computational complexity for hierarchical metrics like Precision@K and demonstrated 21% error reduction on benchmarks, with real-world validation showing a +407 basis points sales lift in production systems.
🧠 Claude
AIBullisharXiv – CS AI · Jun 47/10
🧠MapAgent is an AI framework that automates lane-level map generation for autonomous driving at city scale, combining vision-language models with constraint verification to produce specification-compliant maps. Already deployed by Baidu Maps across 360+ Chinese cities, the system achieves over 95% production automation while reducing manual editing overhead in complex scenarios.
AIBullisharXiv – CS AI · Jun 47/10
🧠Researchers introduce SSSD, a training-free method for accelerating Large Language Model inference that reduces latency by up to 2.9x through n-gram matching and hardware-aware speculation. The approach matches performance of existing trained methods while eliminating deployment complexity, data preparation, and maintenance overhead.
AINeutralarXiv – CS AI · May 117/10
🧠Researchers propose a geometric framework for detecting hallucinations in large language models by analyzing embedding space structure, categorizing three types of errors with different detectability profiles. The approach outperforms standard NLI baselines on expert-annotated datasets, providing interpretable diagnostics for production systems operating under black-box constraints.
AIBullisharXiv – CS AI · Apr 107/10
🧠AgentOpt v0.1, a new Python framework, addresses client-side optimization for AI agents by intelligently allocating models, tools, and API budgets across pipeline stages. Using search algorithms like Arm Elimination and Bayesian Optimization, the tool reduces evaluation costs by 24-67% while achieving near-optimal accuracy, with cost differences between model combinations reaching up to 32x at matched performance levels.
AINeutralarXiv – CS AI · 4d ago6/10
🧠Researchers propose a five-plane reference architecture for governing production AI agents in enterprise environments, addressing security gaps where traditional data-boundary controls fail. The system uses composite principals, capability attenuation, and structured audit trails to manage delegated agent actions that could otherwise transform business processes without proper authorization.
AIBullisharXiv – CS AI · 6d ago6/10
🧠Researchers introduce FAME, a sparse mixture-of-experts framework that dynamically routes time series forecasting tasks to specialized models based on data characteristics. Tested on a production retail dataset with 5,000+ vending machines, the system achieves 12.4% MSE improvement over single-model baselines while using only 1.92 experts per series, demonstrating practical advantages for large-scale commercial forecasting systems.
AINeutralarXiv – CS AI · 6d ago6/10
🧠Researchers present a cost-aware method for optimizing speculative execution in LLM-agent workflows, addressing the challenge of reducing idle time while managing per-token billing costs. The approach combines five design decisions—including predictive execution, dual-rate pricing, Bayesian probability estimation, and a configurable latency-cost tradeoff—with safeguards ensuring only side-effect-free operations proceed speculatively.
AINeutralarXiv – CS AI · Jun 46/10
🧠Researchers present a hybrid content moderation system for livestreams that combines supervised classification with multimodal similarity matching, achieving 67-76% recall at 80% precision. The production-deployed framework reduces user views of unwanted content by 6-8%, demonstrating scalable AI-driven moderation for user-generated video platforms.
AINeutralarXiv – CS AI · May 16/10
🧠Researchers present a Bayesian statistical framework for migrating production LLM systems when models reach end-of-life, enabling organizations to confidently compare and select replacement models using limited human evaluation data. The framework was validated on a commercial question-answering system processing 5.3M monthly interactions, addressing a critical operational challenge as the LLM ecosystem rapidly evolves.
AIBullisharXiv – CS AI · Feb 276/105
🧠Researchers developed improved neural retriever-reranker pipelines for Retrieval-Augmented Generation (RAG) systems over knowledge graphs in e-commerce applications. The study achieved 20.4% higher Hit@1 and 14.5% higher Mean Reciprocal Rank compared to existing benchmarks, providing a framework for production-ready RAG systems.
