https://www.friendlypaperreview.com/archivedailyhttps://www.friendlypaperreview.com/aboutweeklyhttps://www.friendlypaperreview.com/p/reinforcement-learning-via-self-distillation2026-07-27monthlyhttps://www.friendlypaperreview.com/p/edgebench-unveiling-scaling-laws2026-07-22monthlyhttps://www.friendlypaperreview.com/p/rlanything-forge-environment-policy2026-07-20monthlyhttps://www.friendlypaperreview.com/p/dspark-confidence-scheduled-speculative2026-07-17monthlyhttps://www.friendlypaperreview.com/p/mhc-vs-attention-residuals2026-07-13monthlyhttps://www.friendlypaperreview.com/p/osworld-20-benchmarking-computer2026-07-08monthlyhttps://www.friendlypaperreview.com/p/deepseek-v4-towards-highly-efficient2026-07-06monthlyhttps://www.friendlypaperreview.com/p/qwen-agentworld-language-world-models2026-07-01monthlyhttps://www.friendlypaperreview.com/p/zaya1-8b-technical-report2026-06-29monthlyhttps://www.friendlypaperreview.com/p/agents-last-exam2026-06-24monthlyhttps://www.friendlypaperreview.com/p/rewarding-the-rare-uniqueness-aware2026-06-22monthlyhttps://www.friendlypaperreview.com/p/nemotron-3-ultra2026-06-18monthlyhttps://www.friendlypaperreview.com/p/world-action-models-are-zero-shot2026-06-15monthlyhttps://www.friendlypaperreview.com/p/mai-thinking-1-building-a-hill-climbing2026-06-11monthlyhttps://www.friendlypaperreview.com/p/conditional-memory-via-scalable-lookup2026-06-08monthlyhttps://www.friendlypaperreview.com/p/code-as-agent-harness2026-06-03monthlyhttps://www.friendlypaperreview.com/p/speculative-speculative-decoding2026-06-02monthlyhttps://www.friendlypaperreview.com/p/embarrassingly-simple-self-distillation2026-06-02monthly