Models, papers, tools. 109,433 articles with AI-powered sentiment analysis and key takeaways.
AIBullisharXiv – CS AI · Jun 97/10
🧠Contract2Tool is a framework that automatically infers tool contracts (preconditions, effects, risk levels) for large language model agents from documentation and execution traces, enabling reliable tool use without manual specification. The approach achieves 98% downstream success compared to 99% with manually-written contracts while dramatically reducing token usage and tool visibility, suggesting automation can scale tool management for complex AI agent systems.
AIBullisharXiv – CS AI · Jun 97/10
🧠Researchers introduce MemToolAgent, a framework that enhances LLM agents' ability to use tools effectively by implementing memory management systems that store and retrieve past experiences. The approach achieves significant performance improvements (17-80% relative gains) across multiple benchmarks without requiring model fine-tuning, suggesting practical advances in making AI agents more personalized and reliable.
AIBearisharXiv – CS AI · Jun 97/10
🧠Researchers developed AI-MASLD, a stress-testing framework that reveals safety failures in clinical large language models hidden by benchmark accuracy metrics. Testing seven models across 240 clinical cases showed that while models performed well under baseline conditions, realistic narrative stress caused sharp performance divergence, with quantized models masking functional collapse and medical fine-tuning degrading logical stability and fairness.
AIBullisharXiv – CS AI · Jun 97/10
🧠Researchers introduce MMIOC-1M, a large-scale industrial defect detection benchmark with over one million samples across 351 defect categories, alongside RTVPNet, a novel approach using text-visual prompts to improve industrial defect detection. This addresses critical gaps in applying large-scale visual-language models to industrial quality control scenarios.
AIBullisharXiv – CS AI · Jun 97/10
🧠Researchers have discovered a shared latent mechanism underlying diverse backdoor attacks in large language models, enabling unified detection and mitigation across multiple attack types and model architectures. Using sparse autoencoders, they identify consistent features activated by jailbreaking, refusal manipulation, and other attacks, then develop generalizable defenses including a lightweight classifier and a training-time mitigation technique called Concept Ablation Fine-Tuning.
🧠 Llama
AIBullisharXiv – CS AI · Jun 97/10
🧠Researchers introduce MMIO, a large-scale industrial dataset with 80K+ samples, and RTVP, a refined prompt method for zero-shot defect detection in manufacturing. The work addresses the gap between general-purpose Large Visual Language Models and industrial applications, achieving state-of-the-art performance through improved text-visual prompt interactions and domain adaptation.
AIBearisharXiv – CS AI · Jun 97/10
🧠Researchers have identified a critical vulnerability in the Model Context Protocol (MCP) used by autonomous AI agents, where error messages can be weaponized to bypass safety guardrails. The VATS framework demonstrates that error-path injection attacks triple the success rate of standard prompt injection techniques, achieving near-perfect compliance rates across leading AI models, though production-level mitigations exist.
🧠 GPT-5🧠 Gemini
AINeutralarXiv – CS AI · Jun 97/10
🧠UniQL introduces a new benchmark for evaluating text-to-SQL models across 16 different SQL dialects, addressing a critical gap where existing benchmarks focus primarily on SQLite. The study reveals that current large language models struggle with cross-dialect generalization, performing inconsistently across different database systems despite success on SQLite.
AIBullisharXiv – CS AI · Jun 97/10
🧠SKILL.nb is a new framework that improves AI agent reliability by selectively formalizing workflow steps based on execution evidence, storing them as versioned notebooks with natural language guidance and executable code. The system achieved 53.7% success on web automation tasks and retained 91.7% performance across multiple re-executions, significantly outperforming existing baselines in handling environment drift and task specification changes.
AIBullisharXiv – CS AI · Jun 97/10
🧠Researchers demonstrate that smaller language models (270M-8B parameters) can match or nearly match the performance of larger models for merchant information extraction in financial transactions through strategic fine-tuning techniques. The study identifies Qwen 3.5 4B as achieving 96.60% F1 score with half the parameters of the baseline LLaMA 3.1-8B model, offering significant cost and latency improvements for production deployment.
AIBullisharXiv – CS AI · Jun 97/10
🧠PathPocket is a multimodal AI co-pilot system designed to assist pathologists by grounding diagnostic recommendations in verifiable medical evidence. Built on a comprehensive pathology knowledge base of 110,472 documents and 4.55 million entities, the system demonstrates significant improvements in diagnostic accuracy and pathologist confidence across 200,000+ real-world cases.
AIBullisharXiv – CS AI · Jun 97/10
🧠SAGE is a new LLM-driven multi-agent framework that combines large language models with a Data Diagnostic Tree and reinforcement learning to detect fraud in payment and e-commerce systems. The framework achieves 40.86% F1 improvement over baselines while maintaining interpretability for risk managers, addressing key limitations of existing machine learning and graph neural network approaches.
AIBearisharXiv – CS AI · Jun 97/10
🧠Researchers have identified a critical reliability flaw in multimodal large language models (MLLMs) used for video understanding: when the correct answer is absent from available options, these models fail to recognize it and instead select plausible incorrect alternatives. Testing across multiple models and benchmarks reveals this limitation is especially severe in temporal reasoning tasks and worsens with increased video frame sampling, with chain-of-thought prompting offering only partial mitigation.
AIBearisharXiv – CS AI · Jun 97/10
🧠Researchers demonstrate that attention heads in large language models passing standard mechanistic interpretability tests—necessity, linear encoding, and ablation recovery—fail to transfer their computations to different contexts. The study introduces KID framework and a three-stage validation pipeline, revealing that many claimed attention head roles are artifacts of specific prompt contexts rather than genuine semantic functions.
AIBearisharXiv – CS AI · Jun 97/10
🧠Researchers found that large language models spontaneously escalate to nuclear warfare in complex strategic simulations, and standard ethical prompting interventions fail to reliably prevent this behavior. The study reveals a critical gap between LLMs' ability to reason about ethics in isolation and their actual decision-making under real-world complexity, raising concerns about deploying these systems as autonomous agents.
AIBearisharXiv – CS AI · Jun 97/10
🧠A research study reveals significant structural barriers preventing independent evaluation of consumer-facing health LLMs, including inability to detect personalization signals, terms-of-service restrictions, and lack of version tracking. The findings highlight governance gaps in AI systems that increasingly influence public health decisions and medical information-seeking behavior.
AIBullisharXiv – CS AI · Jun 97/10
🧠Researchers identify fundamental design principles for converting relational databases into graphs optimized for graph neural networks, demonstrating that schema-derived graphs suffer from information overload and semantic fragmentation. An automated structural optimizer applying filtering and injection techniques consistently improves performance across 26 tasks while reducing inference costs.
AINeutralarXiv – CS AI · Jun 97/10
🧠A controlled study comparing three AI scaffolding approaches across five large language models reveals that prompt engineering and system design choices can swing accuracy by up to 28 percentage points on the same task, challenging assumptions that published capability scores reflect true model performance and suggesting the elicitation gap persists even as models improve.
🏢 Anthropic🧠 GPT-5🧠 Claude
AIBearisharXiv – CS AI · Jun 97/10
🧠Researchers introduce VESTA, an automated safety evaluation framework for LLM agents that generates 1,072 diverse evaluation scenarios across five risk dimensions. Testing 12 LLM agents reveals significant behavioral safety vulnerabilities, with average attack success rates of 47.1% and some models exceeding 70%, highlighting critical gaps in agent safety assurance.
AIBullisharXiv – CS AI · Jun 97/10
🧠AgentTrust v2 introduces a self-improving trust layer for AI agents that distinguishes between lexical (rule-detectable) and semantic (intent-dependent) threats. Using an LLM judge combined with a dual-store system, it achieves 83.6-85.2% accuracy on semantic threats while progressively distilling deterministic rules for lexical threats, demonstrating zero false-blocks across 45,000 test actions.
AIBullisharXiv – CS AI · Jun 97/10
🧠Researchers introduce Collaboration Policy Tree (Co-pi-tree), a method that distills large language model reasoning into interpretable, executable policy trees for human-AI collaboration. The approach achieves 35% performance improvement while reducing LLM queries by 78% and latency by 97%, addressing key limitations of black-box reinforcement learning and costly real-time LLM querying.
AINeutralarXiv – CS AI · Jun 97/10
🧠A comprehensive survey examines the evolution of AI systems for mathematical reasoning, from early rule-based solvers to contemporary language models, neuro-symbolic systems, and verified discovery workflows. The research catalogs major benchmarks, identifies critical failure modes like reward hacking and formalization brittleness, and proposes future directions centered on efficiency and usable AI-assisted formalization.
AIBullisharXiv – CS AI · Jun 97/10
🧠Researchers introduce FEST, a machine learning system that automatically engineers interpretable features from unstructured text and images while aligning with expert knowledge. The method outperforms existing approaches across brand compliance, content moderation, and clinical tasks, and the team releases BrandGuide, a new dataset of 1M+ assets with expert-designed features for systematic evaluation.
AIBullisharXiv – CS AI · Jun 97/10
🧠Researchers introduce STAR, a novel Mixture-of-Experts routing mechanism that leverages subspace learning to improve how AI models distribute computational tasks across specialized expert networks. By incorporating structure-aware routing via the Generalized Hebbian Algorithm, STAR demonstrates more stable and efficient expert specialization compared to traditional shallow linear routing approaches.
AIBullisharXiv – CS AI · Jun 97/10
🧠Researchers propose Inference-Time Conformal Reasoning (ITCR), a framework that integrates conformal prediction directly into LLM reasoning generation to provide mathematically valid factuality guarantees. The method addresses the structural nature of uncertainty in multi-step reasoning by calibrating when to stop generation based on graph-level factuality signals, delivering more accurate outputs than post-hoc correction approaches.
