Models, papers, tools. 62,023 articles with AI-powered sentiment analysis and key takeaways.
AIBullisharXiv – CS AI · Jun 237/10
🧠Researchers present ExecTimeNet, a learned world model that bridges the gap between discrete multi-agent path finding (MAPF) planning and real-world robot execution by predicting how planned paths perform on physical systems with realistic dynamics and delays. The framework includes REMAP, which integrates execution-time estimation into planning, and ESADG, a post-planning optimizer that achieves up to 40% improvement in execution efficiency while maintaining path feasibility.
AIBullisharXiv – CS AI · Jun 237/10
🧠Over-the-Air Federated Learning (AirFL) integrates wireless signal processing with distributed machine learning to enable efficient edge AI by using wireless superposition to aggregate model updates directly at the receiver. The approach reduces latency, bandwidth, and energy consumption compared to traditional federated learning architectures.
AINeutralarXiv – CS AI · Jun 237/10
🧠Researchers introduce Hierarchical Attribution Graph Decomposition (HAGD), a novel method for extracting sparse circuits from billion-parameter language models that reduces computational complexity from exponential to polynomial time. The approach successfully identifies interpretable pathways in models ranging from GPT-2 to Llama-70B, achieving 91% behavioral preservation on modular arithmetic tasks while existing methods like ACDC become memory-prohibitive at 1.4B parameters.
🧠 Llama
AIBullisharXiv – CS AI · Jun 237/10
🧠Researchers introduce PEAR, a new multi-agent debate protocol for large language models that dynamically reassigns agent roles across debate rounds to eliminate positional biases. By using permutation-equivariant routing, PEAR improves reasoning accuracy across multiple benchmarks while reducing the sensitivity of LLM outputs to arbitrary role assignments.
AIBearisharXiv – CS AI · Jun 237/10
🧠Researchers introduced HardSecBench, a comprehensive security benchmark for evaluating large language models used in hardware and firmware code generation. The study of 924 tasks reveals that LLMs frequently produce functionally correct code while embedding critical security vulnerabilities, highlighting a significant gap in current AI safety evaluation practices.
AIBearisharXiv – CS AI · Jun 237/10
🧠Researchers introduce TrojanGYM, an LLM-driven framework that automatically generates hardware Trojans to expose vulnerabilities in detection systems. The system demonstrates that existing detectors can be evaded at rates up to 83.33%, revealing critical gaps in hardware security testing methodologies.
🧠 GPT-4🧠 Gemini
AIBullisharXiv – CS AI · Jun 237/10
🧠Researchers introduce Darwin Mobile Agent, an open-source infrastructure enabling autonomous reinforcement learning agents to interact with mobile GUIs at scale. The framework addresses data collection bottlenecks through parallel cloud-phone instances and proposes a roadmap to remove human priors from AI agent design, advancing toward truly self-evolving autonomous systems.
AIBullisharXiv – CS AI · Jun 237/10
🧠OGD4All is a Large Language Model framework that enables citizens to interact with geospatial open government data through natural language queries, achieving 98% analytical correctness and 94% recall while minimizing hallucinations. The system combines semantic retrieval, agentic reasoning, and sandboxed execution to provide transparent, auditable access to public datasets, representing a significant advance in making government data democratically accessible.
AIBearisharXiv – CS AI · Jun 237/10
🧠Researchers audited eight text-to-image models and found that emotionally conditioned prompts systematically amplify demographic biases, with negatively valenced emotions consistently shifting outputs toward White, middle-aged, male-coded faces while underrepresenting younger women and Black individuals. The study reveals that intersectional demographic combinations face near-erasure in synthetic face generation, highlighting critical gaps in current bias evaluation practices.
AINeutralarXiv – CS AI · Jun 237/10
🧠Researchers identify 'rational value risk' in large language models, showing that even well-aligned LLMs fail to consistently maximize their intended values during reasoning tasks. The study across major models (Llama, GPT, DeepSeek) reveals that value alignment training alone cannot eliminate this reasoning gap, with performance highly dependent on inference-time strategies.
🧠 GPT-5🧠 Llama
AIBullisharXiv – CS AI · Jun 237/10
🧠Researchers propose Optimal Token Baseline (OTB), a new variance reduction technique for reinforcement learning in large language models that addresses training instability in long-horizon tasks. The method reduces token consumption by over 65% while maintaining performance equivalent to models using 8x larger batch sizes, offering significant efficiency gains for LLM-RL training.
AIBullisharXiv – CS AI · Jun 237/10
🧠Researchers introduce ALOE, an off-policy evaluation framework designed to improve vision-language-action (VLA) models through better value function estimation from heterogeneous real-world data. The method addresses a critical challenge in robotic learning by enabling more accurate credit assignment and stable policy improvement across complex manipulation tasks.
AINeutralarXiv – CS AI · Jun 237/10
🧠Researchers introduce WikiProfile, a benchmark that reframes LLM factuality failures as either missing knowledge or poor recall of encoded information. Analysis of 13 models shows frontier models encode 95-98% of facts but struggle significantly with recall, suggesting future improvements depend less on scaling and more on better knowledge access mechanisms.
🧠 GPT-5🧠 Gemini
AIBullisharXiv – CS AI · Jun 237/10
🧠Researchers introduce SkillHarness, a framework enabling computer-use agents to safely learn and reuse skills in dynamic environments by constraining skill learning against adversarial attacks and environmental disruptions. The system reduces unsafe skill rates by 57.1% compared to existing approaches, addressing a critical vulnerability in AI agents deployed in interactive settings.
AIBullisharXiv – CS AI · Jun 237/10
🧠Researchers developed a framework combining deep reinforcement learning (DRL) with large language models (LLMs) to make autonomous vehicles safer and more trustworthy by explaining driving decisions to passengers. The system was trained to handle three driving modes—fast, comfort, and stop—while generating safety-focused explanations for its actions, demonstrating effective mode switching and rule compliance.
AIBullisharXiv – CS AI · Jun 237/10
🧠Researchers propose a retrieval-augmented approach for generating CT scans from radiology reports that combines semantic control with anatomical consistency by retrieving structurally similar clinical cases and using their annotations as guidance. The method improves image fidelity and clinical consistency compared to text-only baselines while enabling spatial controllability without requiring ground-truth annotations at inference time.
AIBullisharXiv – CS AI · Jun 237/10
🧠Researchers introduce SPARC, a multi-agent AI system that answers electrical circuit diagram questions by grounding reasoning in executable physics simulations rather than relying solely on language models. The system achieves 83% accuracy with up to 58% improvement over existing baselines, demonstrating how hybrid AI approaches combining LLMs with domain-specific simulation tools can enhance reasoning reliability.
AIBearisharXiv – CS AI · Jun 237/10
🧠Researchers demonstrate that large language models exhibit brittle instruction-following when faced with competing behavioral patterns, with compliance rates ranging from 1% to 99% across 13 models. The study reveals that output diversity and format—rather than reasoning ability—are the primary determinants of robustness against induction pressure, highlighting fundamental vulnerabilities in current LLM training.
AIBearisharXiv – CS AI · Jun 237/10
🧠A research paper challenges the credibility of unsupervised feature selection methods by demonstrating that many state-of-the-art approaches perform no better than random selection. The study calls for establishing random feature selection as a mandatory baseline in future research to ensure genuine methodological improvements.
AIBullisharXiv – CS AI · Jun 237/10
🧠Researchers demonstrated an autonomous AI system that successfully post-trained NVIDIA's 30B Nemotron model over multiple weeks without human intervention, achieving competitive results (0.86 score vs. 0.87 human baseline) on a public leaderboard. The system notably detected and corrected its own measurement failures by recognizing when its optimization proxy diverged from actual performance, representing a significant step toward autonomous machine learning research at frontier model scale.
🏢 Nvidia
AIBullisharXiv – CS AI · Jun 237/10
🧠FoMoE introduces a distributed training system that breaks the full-model replication requirement in Mixture-of-Experts (MoE) architectures by partitioning experts across workers. The approach achieves up to 1.42x communication cost reduction and 45x improvement over traditional distributed training, enabling efficient LLM pre-training across geographically dispersed commodity hardware.
AINeutralarXiv – CS AI · Jun 237/10
🧠Researchers introduce DrugBench, a benchmark for evaluating AI safety protocols in medical LLM applications, combining 3,671 medical conversations with FDA drug data to test systems against medication-related harms. The study reveals that existing AI control mechanisms can be circumvented and proposes severity-based monitoring to better account for the potential consequences of unsafe outputs in clinical contexts.
AINeutralarXiv – CS AI · Jun 237/10
🧠Researchers introduce Agent Behavior Mining, a governance framework that applies process mining techniques to make generative AI agent decision-making observable and traceable within business processes. The approach translates agent activities into standardized process logs, enabling organizations to detect policy deviations and quantify operational variability while addressing the control challenges posed by non-deterministic AI systems.
AINeutralarXiv – CS AI · Jun 237/10
🧠A comprehensive survey examines LLM-based agent systems through a model-harness lens, arguing that agent performance depends on the interaction between foundation models, execution infrastructure, and task structure rather than model capabilities alone. The research identifies six core runtime responsibilities and maps how different harness configurations affect long-horizon task completion, efficiency, and reliability.
AIBearisharXiv – CS AI · Jun 237/10
🧠Researchers demonstrate a critical flaw in using large language models as user simulators for training conversational AI: LLM simulators systematically misrepresent how real customers disengage from purchases, showing excessive deliberation and muted resistance compared to actual users. This bias could lead developers to overestimate the effectiveness of sales agents trained on synthetic user interactions.
