Tag: AI reasoning models
Browse our exclusive articles!
Mitigating Self-Jailbreak in Large Reasoning Models Safely
Discover how Chain-of-Guardrail (CoG) improves safety in large reasoning models by preventing self-jailbreak without sacrificing reasoning power.
Enhancing Safety Alignment in Large Reasoning Models
Discover how modifying reasoning structures with AltTrain improves safety alignment in large reasoning models, reducing harmful AI outputs effectively.
Solver-Sampler Mismatch in Multi-Agent LLM Negotiation
Explore how reasoning models affect behavioral simulation in multi-agent LLM negotiation, revealing solver-sampler mismatches and their impact on outcomes.
Emergent Attention Heads in Post-Training Reasoning Models
Discover how post-training sparks emergent attention heads that enhance reasoning models' performance and reveal key trade-offs in AI computation.
Contrastive Reasoning Path Synthesis for Efficient MCTS
Discover how Contrastive Reasoning Path Synthesis (CRPS) improves MCTS by synthesizing insights from diverse search paths, boosting reasoning model efficie...