High-Entropy Token Selection in Reinforcement Learning with Verifiable Rewards (RLVR) Improves Accuracy and Reduces Training Cost for LLMs
junio 9, 2025admin NUAI,Committee,Noticias,Uncategorized(0)Large Language Models (LLMs) generate step-by-step responses known as Chain-of-Thoughts (CoTs), where each token contributes...
High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning
junio 5, 2025admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2506.04051v1 Announce Type: new Abstract: Large Language Models (LLMs) currently respond to every prompt. However...
Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents
agosto 1, 2025admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2507.22925v1 Announce Type: new Abstract: Long-term memory is one of the key factors influencing the...
Hierarchical Chain-of-Thought Prompting: Enhancing LLM Reasoning Performance and Efficiency
abril 3, 2026admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2604.00130v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has significantly improved the reasoning capabilities of...
HFS: Holistic Query-Aware Frame Selection for Efficient Video Reasoning
diciembre 15, 2025admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2512.11534v1 Announce Type: cross Abstract: Key frame selection in video understanding presents significant challenges. Traditional...
HeuriGym: An Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization
enero 29, 2026admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2506.07972v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) have demonstrated significant advancements in...
Hermes Agent Ships Tool Search for MCP: Anthropic Evals Show 49% to 74% Accuracy Gain on Opus 4
mayo 30, 2026admin NUAI,Committee,Noticias,Uncategorized(0)Nous Research’s open-source Hermes Agent now ships a Tool Search feature. It directly addresses a...
Here’s why some people choose cryonics to store their bodies and brains after death
marzo 27, 2026admin NUAI,Committee,Noticias,Uncategorized(0)This week I reported on some rather unusual research that focuses on the brain of...
Here’s why AI agents lie and cheat to reach their goals
agosto 3, 2026admin NUAI,Committee,Noticias,Uncategorized(0)MIT Technology Review Explains: Let our writers untangle the complex, messy world of technology to...
