The paper defines accidental meltdowns as unsafe agent behavior triggered by benign errors and reports that such meltdowns occur in 64.7% of evaluated rollouts across GPT, Grok, and Gemini agents.
hub
Title resolution pending
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
years
2026 10roles
background 3polarities
background 3representative citing papers
PocketAgents introduces a manifest-driven library for LLM-based autonomous defense agents, evaluated in 18 closed-loop trials against a DarkSide-inspired attack where 13 trials produced validated blocking actions.
Open-world evaluations using qualitative review of real-world tasks can give earlier warnings of frontier AI capabilities than automated benchmarks, as demonstrated by an AI agent publishing a simple iOS app with one minor human fix.
Pilot study shows agent decision reconstructability varies by vendor SDK regime, with completeness scores from 42.9% to 85.7% and consistent gaps in reasoning traces.
LLMs need metacognition to align expressed uncertainty with their actual knowledge boundaries, moving beyond knowledge expansion to reduce confident errors.
LLMs show poor calibration in predicting task success and token use on software engineering benchmarks, causing market auctions to underperform compared to perfect information scenarios, with limited improvement from added context.
RemoteShield improves robustness of Earth observation MLLMs by training on semantic equivalence clusters of clean and perturbed inputs via preference learning to maintain consistent reasoning under noise.
NAUTILUS is a prompt-driven harness that automates plug-and-play adapters, typed contracts, and validation for policies, benchmarks, and robots in learning research.
A framework with U-statistics and kernel-based metrics quantifies AI agent consistency and robustness, showing trajectory metrics outperform pass@1 rates in diagnosing failures.
The paper analyzes security, privacy, and ethical risks in the OpenClaw AI agent system arising from its architecture, storage, tool use, and integrations, arguing these form major barriers to trustworthy adoption.
citing papers explorer
-
Nautilus: From One Prompt to Plug-and-Play Robot Learning
NAUTILUS is a prompt-driven harness that automates plug-and-play adapters, typed contracts, and validation for policies, benchmarks, and robots in learning research.