[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

@dair_ai "Top AI Papers of The Week (October 13-19): - Kimi-Dev - Elastic-Cache - Hybrid Reinforcement - Cell2Sentence-Scale 27B - Holistic Agent Leaderboard - Dynamic Layer Routing in LLMs - The Art of Scaling RL Compute for LLMs Read on for more:"
X Link @dair_ai 2025-10-19T12:54Z 80.6K followers, 18.7K engagements

"2. Emergent Misalignment In controlled multi-agent sims models fine-tuned to maximize conversions votes or engagement also increased deception disinformation and harmful rhetoric even when instructed to stay truthful"
X Link @dair_ai 2025-10-12T15:00Z 80.5K followers, 1735 engagements

"3. Agentic Context Engineering (ACE) Presents a modular context-engineering framework that grows and refines an LLMs working context like a playbook not a terse prompt"
X Link @dair_ai 2025-10-12T15:00Z 80.5K followers, 1427 engagements

"2. The Art of Scaling RL Compute for LLMs A 400k+ GPU-hour study introduces a simple predictive way to scale RL for LLMs"
X Link @dair_ai 2025-10-19T12:54Z 80.5K followers, XXX engagements

"3. Demystifying RL in Agentic Reasoning This paper studies what actually works when using RL to improve tool-using LLM agents across three axes: data algorithm and reasoning mode"
X Link @dair_ai 2025-10-19T12:54Z 80.6K followers, XXX engagements

"8. Hybrid Reinforcement Hybrid Ensemble Reward Optimization is a reinforcement learning framework that combines binary verifier feedback with continuous reward-model signals to improve LLM reasoning"
X Link @dair_ai 2025-10-19T12:54Z 80.5K followers, XXX engagements

"1. Cell2Sentence-Scale 27B C2S-Scale extends Cell2Sentence by converting gene expression into cell sentences and training LLMs on 50M+ cells plus biological text"
X Link @dair_ai 2025-10-19T12:54Z 80.6K followers, 1240 engagements

"Top AI Papers of The Week (October 6-12): - Webscale-RL - Tiny Recursive Model - The Markovian Thinker - Emergent Misalignment - Agentic Context Engineering - Abstract Reasoning Composition - Reasoning over Longer Horizons via RL Read on for more:"
X Link @dair_ai 2025-10-12T15:00Z 80.6K followers, 35.6K engagements

"9. Kimi-Dev Kimi-Dev introduces agentless training as a skill prior to software engineering LLMs bridging workflow-style and agentic paradigms"
X Link @dair_ai 2025-10-19T12:54Z 80.6K followers, 3908 engagements