AINeutralarXiv – CS AI · 4d ago7/10
🧠Researchers introduce Trajel, a dataset and evaluation framework for detecting hallucinations in multi-step LLM agent workflows, revealing that existing benchmarks miss intermediate failures. The framework defines five hallucination types and shows that trajectory-level detection outperforms traditional post-hoc verification, highlighting critical gaps in current AI safety evaluation methodologies.
AIBullisharXiv – CS AI · May 127/10
🧠Researchers introduce SPARK, a framework that verifies AI agent skills through direct environment interaction rather than relying on pre-written plans. The Posterior Distillation Index (PDI) metric ensures skills are grounded in actual task evidence, producing student models that match or exceed human-written skills while reducing inference costs by up to 1,000x.
AINeutralarXiv – CS AI · Mar 97/10
🧠Researchers demonstrate that traditional explainable AI methods designed for static predictions fail when applied to agentic AI systems that make sequential decisions over time. The study shows attribution-based explanations work well for static tasks but trace-based diagnostics are needed to understand failures in multi-step AI agent behaviors.
AINeutralarXiv – CS AI · 4d ago6/10
🧠AgentAtlas introduces a comprehensive diagnostic framework for evaluating LLM agents beyond simple success/failure metrics, proposing a six-state control-decision taxonomy and trajectory-failure vocabulary to expose behavioral patterns hidden by outcome-only leaderboards. The research demonstrates that evaluation methodology significantly impacts apparent model performance rankings.
AINeutralarXiv – CS AI · May 115/10
🧠Researchers introduce a novel online goal recognition method using path signatures and dynamic time warping to efficiently encode and compare continuous trajectory data. The approach demonstrates superior predictive accuracy and planning efficiency compared to existing state-of-the-art methods while maintaining competitive offline performance.
AIBullisharXiv – CS AI · Mar 126/10
🧠Researchers introduce a new framework for AI agent systems that automatically extracts learnings from execution trajectories to improve future performance. The system uses four components including trajectory analysis and contextual memory retrieval, achieving up to 14.3 percentage point improvements in task completion on benchmarks.
AIBullisharXiv – CS AI · Mar 26/1017
🧠Researchers introduce VISTA, a framework for vessel trajectory imputation that uses knowledge-driven LLM reasoning to repair incomplete maritime tracking data. The system provides 'repair provenance' - documented reasoning behind data repairs - achieving 5-91% accuracy improvements over existing methods while reducing inference time by 51-93%.
AINeutralarXiv – CS AI · Mar 35/107
🧠Researchers introduce SIGMAS, a self-supervised AI framework for identifying group structures in multi-agent swarms like drone fleets without ground-truth supervision. The system uses second-order interactions to infer latent group memberships from agent trajectories, demonstrating robust performance across diverse synthetic swarm scenarios.
