AIBearisharXiv – CS AI · May 127/10
🧠Researchers demonstrate 'Oracle Poisoning,' a novel attack where adversaries corrupt knowledge graphs used by AI agents, causing them to reach incorrect conclusions through valid reasoning. Testing across nine models from three providers shows all models accept fabricated data at 100% under moderate attack sophistication, revealing a critical vulnerability in production-scale agentic systems that differs fundamentally from prompt injection attacks.
🧠 GPT-5
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 · May 17/10
🧠Researchers introduce Intern-Atlas, a methodological evolution graph built from over 1 million AI papers that automatically maps how research methods develop and relate to one another. The infrastructure captures explicit causal relationships between methodologies and enables AI-driven research agents to reconstruct innovation timelines, addressing a critical gap in existing document-centric research systems.
AIBullisharXiv – CS AI · Apr 157/10
🧠Researchers introduce reasoning graphs, a persistent knowledge structure that improves language model reasoning accuracy by storing and reusing chains of thought tied to evidence items. The system achieves 47% error reduction on multi-hop questions and maintains deterministic outputs without model retraining, using only context engineering.
AINeutralarXiv – CS AI · Apr 157/10
🧠Researchers identified a critical failure mode in LLM-based agents called policy-invisible violations, where agents execute actions that appear compliant but breach organizational policies due to missing contextual information. They introduced PhantomPolicy, a benchmark with 600 test cases, and Sentinel, an enforcement framework using counterfactual graph simulation that achieved 93% accuracy in detecting violations compared to 68.8% for baseline approaches.
AINeutralarXiv – CS AI · Apr 147/10
🧠Researchers introduce PaperScope, a comprehensive benchmark for evaluating multi-modal AI systems on complex scientific research tasks across multiple documents. The benchmark reveals that even advanced systems like OpenAI Deep Research and Tongyi Deep Research struggle with long-context retrieval and cross-document reasoning, exposing significant gaps in current AI capabilities for scientific workflows.
🏢 OpenAI
AIBullisharXiv – CS AI · Apr 147/10
🧠Researchers introduce AtlasKV, a parametric knowledge integration method that enables large language models to leverage billion-scale knowledge graphs while consuming less than 20GB of VRAM. Unlike traditional retrieval-augmented generation (RAG) approaches, AtlasKV integrates knowledge directly into LLM parameters without requiring external retrievers or extended context windows, reducing inference latency and computational overhead.
AIBullisharXiv – CS AI · Apr 137/10
🧠Researchers introduce LOM-action, an enterprise AI system that grounds LLM-based decisions in business ontologies and event-driven simulations rather than unrestricted knowledge spaces. The approach achieves 93.82% accuracy with 98.74% F1 scores on decision chains, vastly outperforming larger models like DeepSeek-V3.2, while maintaining complete audit trails for enterprise compliance.
AIBullisharXiv – CS AI · Mar 267/10
🧠Researchers have developed AI-Supervisor, a multi-agent framework that maintains a persistent Research World Model to autonomously conduct end-to-end AI research supervision. Unlike traditional linear pipelines, the system uses specialized agents with structured gap discovery, self-correcting loops, and consensus mechanisms to continuously evolve research understanding.
AINeutralarXiv – CS AI · Mar 267/10
🧠Researchers developed a graph-based evaluation framework that transforms clinical guidelines into dynamic benchmarks for testing domain-specific language models. The system addresses key evaluation challenges by providing contamination resistance, comprehensive coverage, and maintainable assessment tools that reveal systematic capability gaps in current AI models.
AIBullisharXiv – CS AI · Mar 117/10
🧠Researchers introduce MMGraphRAG, a new AI framework that addresses hallucination issues in large language models by integrating visual scene graphs with text knowledge graphs through cross-modal fusion. The system uses SpecLink for entity linking and demonstrates superior performance in multimodal information processing across multiple benchmarks.
AIBullisharXiv – CS AI · Mar 56/10
🧠Researchers propose PlugMem, a task-agnostic plugin memory module for LLM agents that structures episodic memories into knowledge-centric graphs for efficient retrieval. The system consistently outperforms existing memory designs across multiple benchmarks while maintaining transferability between different tasks.
AIBullisharXiv – CS AI · Mar 56/10
🧠Researchers propose a dual-helix governance framework to address AI agent reliability issues in WebGIS development, implementing a 3-track architecture that achieved 51% reduction in code complexity. The framework uses knowledge graphs and self-learning cycles to overcome LLM limitations like context constraints and instruction failures.
AIBullisharXiv – CS AI · Mar 57/10
🧠Researchers developed a new AI training method using knowledge graphs as reward models to improve compositional reasoning in specialized domains. The approach enables smaller 14B parameter models to outperform much larger frontier systems like GPT-5.2 and Gemini 3 Pro on complex multi-hop reasoning tasks in medicine.
🧠 Gemini
AIBullisharXiv – CS AI · Mar 57/10
🧠Researchers introduce GraphMERT, an 80M-parameter AI model that efficiently extracts reliable knowledge graphs from unstructured text data. The system outperforms much larger language models like Qwen3-32B in generating factually accurate and semantically valid knowledge graphs, achieving 69.8% FActScore versus 40.2% for the baseline.
AIBullisharXiv – CS AI · Mar 47/103
🧠Researchers introduce MIRAGE, a novel AI framework that uses knowledge graphs and electronic health records to predict Alzheimer's disease when MRI scans are unavailable. The system improves AD classification rates by 13% compared to single-modality approaches by creating synthetic representations without expensive 3D brain scan reconstruction.
AIBullisharXiv – CS AI · Mar 47/103
🧠Researchers present Odin, the first production-deployed graph intelligence engine that autonomously discovers patterns in knowledge graphs without predefined queries. The system uses a novel COMPASS scoring metric combining structural, semantic, temporal, and community-aware signals, and has been successfully deployed in regulated healthcare and insurance environments.
AINeutralarXiv – CS AI · Jun 256/10
🧠Researchers propose a multi-LLM system with hybrid retrieval-augmented generation to automate German IT-Grundschutz security certifications, addressing NIS2 compliance demands and specialist shortages. The architecture combines large language models with knowledge graphs to streamline certification phases while maintaining security quality standards.
AINeutralarXiv – CS AI · Jun 256/10
🧠Researchers demonstrate that Holographic Reduced Representations (HRR), a theoretically promising approach for multi-hop reasoning in knowledge graphs, fail at zero-shot compositional queries despite competitive single-hop performance. The core bottleneck is not the mathematical binding mechanism but rather reduced retrieval capacity under superposition, a finding with implications for neural-symbolic AI systems.
AIBullisharXiv – CS AI · Jun 256/10
🧠Researchers introduce CausalRAG2, a framework that improves retrieval-augmented generation (RAG) systems by incorporating causal reasoning into knowledge graph design, addressing limitations in current entity-centric approaches. The framework uses hierarchical modules with causal gating to reduce spurious correlations and enable scalable reasoning, accompanied by a new HolisQA benchmark for comprehensive evaluation.
AINeutralarXiv – CS AI · Jun 256/10
🧠Researchers have developed a framework for evaluating fuzzy quantification queries over OWL ontologies and knowledge graphs, enabling retrieval of individuals matching Type I or Type II fuzzy quantified expressions. The system is agnostic to quantifier types and data sources, with Q2S2 released as an open implementation for future research.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers present ThermoLLM, a Large Language Model-based framework for multi-zone HVAC control that integrates thermodynamic physics and spatial building semantics through a knowledge graph. The system outperforms standard baselines and competing LLM approaches by reasoning about zone coupling and thermal interactions, achieving superior energy-comfort trade-offs in building simulations.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers present a human-in-the-loop framework combining fine-tuned small language models with knowledge graphs to automatically detect and repair semantic errors in SysML v2 models that bypass traditional compiler validation. The approach achieves over 91% repair accuracy using domain-specific training data and generates practical repair suggestions for engineer review.
AINeutralarXiv – CS AI · Jun 235/10
🧠Researchers propose a novel graph alignment framework using dual-pass spectral encoding and geometry-aware functional mapping to improve node correspondence identification across multiple graphs. The method addresses critical limitations in existing unsupervised approaches by combating oversmoothing in embeddings and latent space misalignment, demonstrating superior performance on graph benchmarks.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers compare four neural network architectures for factual knowledge propagation in question-answering systems, finding that repeated shared memory access enables out-of-distribution generalization ('grokking'), but only architectures with fine-grained addressable memory can effectively propagate edited facts. The study dissociates learning capability from editing affordance, revealing that looped computation and explicit memory mechanisms serve different functional purposes.
