#hidden-state-analysis News & Analysis

2 articles tagged with #hidden-state-analysis. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles

AIBearisharXiv – CS AI · 4d ago7/10

🧠

Plans Don't Persist: Why Context Management Is Load Bearing for LLM Agents

Researchers demonstrate that large language model agents fail to maintain plans as persistent internal state, instead relying on plans remaining in the context window. Using diagnostic techniques on Llama-3.1-70B and DeepSeek-R1, the study shows plan signal decays rapidly when compressed out of context, with practical implications for agent reliability in long-horizon tasks.

🧠 Llama

AINeutralarXiv – CS AI · May 127/10

🧠

Where Reliability Lives in Vision-Language Models: A Mechanistic Study of Attention, Hidden States, and Causal Circuits

Researchers challenge the widespread assumption that sharp attention maps in vision-language models indicate reliable outputs. Through mechanistic analysis of three VLM families (LLaVA, PaliGemma, Qwen2-VL), they find attention structure is nearly uncorrelated with correctness, while hidden-state geometry and late-layer circuits prove far more predictive of model reliability.