AIBullisharXiv – CS AI · May 97/10
🧠Researchers present a layered security architecture for multitenant enterprise AI systems that isolates data and controls access in retrieval-augmented generation (RAG) and agentic AI deployments. The approach separates security-critical operations to the server while preventing cross-tenant data leakage, validated through an open-source OGX framework with negligible performance overhead.
🏢 OpenAI
AIBullisharXiv – CS AI · May 17/10
🧠Researchers introduce ObjectGraph (.og), a new file format designed specifically for how AI agents consume documents through retrieval rather than linear reading. The format reduces token consumption by up to 95.3% while maintaining task accuracy, addressing a fundamental architectural mismatch between traditional documents and LLM agent workflows.
AIBullisharXiv – CS AI · Apr 207/10
🧠Researchers introduce DeepER-Med, an agentic AI framework designed to advance evidence-based medical research with explicit transparency and trustworthiness mechanisms. The system outperforms existing production-grade platforms on complex medical questions and demonstrates clinical alignment in real-world case evaluations, addressing critical gaps in AI reliability for healthcare adoption.
AIBullisharXiv – CS AI · Apr 207/10
🧠Researchers introduce EvoTest, an evolutionary framework enabling AI agents to improve performance across consecutive test episodes without fine-tuning or gradients. The method outperforms existing adaptation techniques on a new Jericho Test-Time Learning benchmark, successfully winning games that all baseline methods failed to complete.
AIBullisharXiv – CS AI · Apr 147/10
🧠Researchers introduce ExecTune, a training methodology for optimizing black-box LLM systems where a guide model generates strategies executed by a core model. The approach improves accuracy by up to 9.2% while reducing inference costs by 22.4%, enabling smaller models like Claude Haiku to match larger competitors at significantly lower computational expense.
🧠 Claude🧠 Haiku🧠 Sonnet
AIBullisharXiv – CS AI · Mar 117/10
🧠AlphaApollo is a new AI reasoning system that addresses limitations in foundation models through multi-turn agentic reasoning, learning, and evolution components. The system demonstrates significant performance improvements across math reasoning benchmarks, with success rates exceeding 85% for tool calls and substantial gains from reinforcement learning across different model scales.
AINeutralarXiv – CS AI · Mar 97/10
🧠Researchers evaluated 34 large language models on radiology questions, finding that agentic retrieval-augmented reasoning systems improve consensus and reliability across different AI models. The study shows these systems reduce decision variability between models and increase robust correctness, though 72% of incorrect outputs still carried moderate to high clinical severity.
AI × CryptoNeutralBankless · Mar 67/10
🤖The article discusses three key developments in the intersection of AI and cryptocurrency, highlighting both problematic applications like criminal use cases and positive developments such as AI-powered smart contract auditing. These developments signal the emergence of an 'agentic frontier' where AI agents operate autonomously within crypto ecosystems.
AIBearisharXiv – CS AI · Mar 67/10
🧠Research reveals that AI language models exhibit self-attribution bias when monitoring their own behavior, evaluating their own actions as more correct and less risky than identical actions presented by others. This bias causes AI monitors to fail at detecting high-risk or incorrect actions more frequently when evaluating their own outputs, potentially leading to inadequate monitoring systems in deployed AI agents.
AINeutralarXiv – CS AI · Jun 256/10
🧠Researchers propose measuring agentic AI system intelligence through information compression, demonstrating that components like tools, retrieval, and verification reduce the bits needed to reconstruct outputs across five task domains. This analytical framework provides a quantitative method for evaluating multi-turn AI agents beyond traditional performance metrics.
AINeutralAI News · Jun 116/10
🧠Xebia's global CTO Niels Zeilemaker emphasizes that organizations implementing AI agents must prioritize building a strong data foundation first, as agentic AI performance scales directly with data quality and availability. The article argues that without proper data infrastructure and accessibility for AI consumption, organizations cannot effectively accelerate their processes using AI agents.
AINeutralarXiv – CS AI · Jun 106/10
🧠Researchers provide a formal operational definition of 'agent harness' in AI software engineering, establishing necessary and sufficient conditions to distinguish harnesses from related tools like frameworks and SDKs. The work analyzes six real-world implementations and proposes a shared vocabulary to standardize how the industry discusses and compares agentic systems built on language models.
🧠 Claude
AIBullisharXiv – CS AI · Jun 86/10
🧠Researchers developed an agentic LLM framework that automates structural analysis of complex 3D frame systems by decomposing tasks across specialized AI agents. The system converts natural language descriptions into executable engineering simulations with 90% accuracy, advancing AI applications in domain-specific professional workflows.
AIBullishGoogle Research Blog · Jun 56/10
🧠Google has introduced Agentic RAG capabilities within its Gemini Enterprise Agent Platform, designed to improve the reliability of AI-generated responses through retrieval-augmented generation techniques. This advancement addresses a critical challenge in enterprise AI deployment: reducing hallucinations and ensuring responses are grounded in accurate, up-to-date data sources.
🧠 Gemini
AIBullishAI News · Jun 46/10
🧠Amazon is launching an Agentic Shopping Assistant built on AWS, enabling third-party retailers like Kate Spade to deploy customized AI shopping assistants on their websites and apps. This move signals Amazon's strategy to monetize its AI infrastructure by licensing it to competitors, expanding the commercial applications of enterprise AI beyond its own retail operations.
AINeutralarXiv – CS AI · Jun 46/10
🧠Researchers introduce Deontic Agentic Reasoning (DAR), a new framework that enables large language models to better tackle complex rule-based reasoning tasks by dynamically querying statutes and policies. Testing on DeonticBench shows agentic approaches improve performance on hard cases, though weaker models struggle with numerical reasoning and consume significantly more tokens.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce MOSAIC, a structured agentic framework that automates data science model selection by combining LLM flexibility with systematic verification. Unlike traditional AutoML systems or unstructured LLM agents, MOSAIC creates intermediate 'blueprints' that ground decisions in retrieved evidence and execution feedback, improving task performance and decision traceability.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce MobEvolve, an AI framework that generates realistic human mobility patterns by combining interpretable heuristics with LLM agents that self-evolve through iterative learning. The system outperforms existing deep learning and LLM approaches while maintaining computational efficiency and behavioral plausibility across Singapore and Montreal datasets.
AINeutralarXiv – CS AI · Jun 26/10
🧠Merkle has developed BADGER, a unified evaluation framework that combines text-to-SQL assessment with agentic behavior evaluation for enterprise AI systems. The framework achieves substantial agreement with human expert judgment (Cohen's kappa=0.717) and outperforms six competing evaluation approaches, addressing a critical gap in production-grade AI system assessment.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers propose a practical framework for building LLM-based agentic systems that prioritizes simplicity, cost predictability, and controllability over maximum optimization. The framework uses modular "pseudo-tools" and fixed workflows, demonstrating that hand-engineered agents often outperform dynamically-planned systems in production environments.
AINeutralarXiv – CS AI · Jun 26/10
🧠Atomix is a new runtime system that enables LLM agents to execute multi-step workflows with transactional guarantees, preventing partial effects and state corruption from faults or concurrent execution. By explicitly tracking which effects must settle together and when conflicting work is exhausted, Atomix provides reliable settlement semantics for agentic systems with minimal overhead.
AIBullisharXiv – CS AI · Jun 16/10
🧠Researchers introduce GLIDE, an open-source Python library that standardizes prediction-powered inference (PPI) methods for evaluating AI systems and language models. The library combines human annotation with LLM evaluations to produce unbiased estimates with valid confidence intervals, potentially reducing annotation costs while maintaining accuracy.
AINeutralarXiv – CS AI · Jun 16/10
🧠Researchers introduce AutoSci, an AI-driven system designed to automate the full scientific research lifecycle by managing literature review, experiments, manuscript writing, and peer review responses. The system uses a memory-centric architecture with four specialized modules to maintain structured knowledge, execute research workflows, and continuously improve its procedures through feedback.
AIBullisharXiv – CS AI · Jun 16/10
🧠Researchers propose symbolic intermediaries—compact mathematical expressions derived from symbolic regression—to bridge the gap between Large Language Models and physics simulators by converting continuous numerical outputs into interpretable symbolic forms. LLM-based agents using this interface outperformed genetic algorithms by 19-53% on mechanism synthesis tasks, demonstrating that translating simulator behavior into symbolic language enables grounded geometric reasoning without model retraining.
AIBullisharXiv – CS AI · May 296/10
🧠Researchers introduce KairosAgent, an agentic framework combining large language models with time series foundation models to improve multimodal forecasting across domains. The system uses semantic reasoning from LLMs fused with numerical forecasting capabilities, achieving superior zero-shot performance through reinforcement learning and structured tool integration.
