home.social

#llmreasoning — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #llmreasoning, aggregated by home.social.

  1. New research shows AI agents can map an entire plan, execute each step, then pause to reflect and re‑plan if needed. This iterative loop boosts LLM reasoning and autonomous problem solving, bringing us closer to truly self‑directed agents. Dive into the details of this planning‑reflection pattern and its open‑source implications. #AIAgents #IterativeLearning #LLMReasoning #AutonomousAgents

    🔗 aidailypost.com/news/ai-agents

  2. New research shows AI agents can map an entire plan, execute each step, then pause to reflect and re‑plan if needed. This iterative loop boosts LLM reasoning and autonomous problem solving, bringing us closer to truly self‑directed agents. Dive into the details of this planning‑reflection pattern and its open‑source implications. #AIAgents #IterativeLearning #LLMReasoning #AutonomousAgents

    🔗 aidailypost.com/news/ai-agents

  3. New research shows AI agents can map an entire plan, execute each step, then pause to reflect and re‑plan if needed. This iterative loop boosts LLM reasoning and autonomous problem solving, bringing us closer to truly self‑directed agents. Dive into the details of this planning‑reflection pattern and its open‑source implications. #AIAgents #IterativeLearning #LLMReasoning #AutonomousAgents

    🔗 aidailypost.com/news/ai-agents

  4. RLVR promises faster sampling but leaves reasoning untouched—base LLMs still carry the heavy‑lifting of trajectories. The paper (NeurIPS 2025) shows that gains come from smarter teacher‑distillation and minor architectural tweaks, not a new reasoning engine. Curious how sampling efficiency separates from true understanding? Dive into the details. #RLVR #SamplingEfficiency #LLMReasoning #NeurIPS2025

    🔗 aidailypost.com/news/rlvr-lift

  5. Quoting Andrej Karpathy In 2025, Reinforcement Learning from Verifiable Rewards (RLVR) emerged as the de facto new major stage to add to this mix. By training LLMs against automatically verifiable ...

    #andrej-karpathy #llm #generative-ai #llm-reasoning #definitions #ai #llms #deepseek

    Origin | Interest | Match
  6. deepseek-ai/DeepSeek-Math-V2 deepseek-ai/DeepSeek-Math-V2 New on Hugging Face, a specialist mathematical reasoning LLM from DeepSeek. This is their entry in the space previously dominated by propri...

    #mathematics #ai #generative-ai #llms #llm-reasoning #deepseek #llm-release #ai-in-china

    Origin | Interest | Match
  7. Kimi K2 Thinking Kimi K2 Thinking Chinese AI lab Moonshot's Kimi K2 established itself as one of the largest open weight models - 1 trillion parameters - back in July . They've now released...

    #ai #generative-ai #llms #llm #mlx #pelican-riding-a-bicycle #llm-reasoning #llm-release #openrouter #ai-in-china #artificial-analysis

    Origin | Interest | Match
  8. Kimi K2 Thinking Kimi K2 Thinking Chinese AI lab Moonshot's Kimi K2 established itself as one of the largest open weight models - 1 trillion parameters - back in July . They've now released...

    #ai #generative-ai #llms #llm #mlx #pelican-riding-a-bicycle #llm-reasoning #llm-release #openrouter #ai-in-china #artificial-analysis

    Origin | Interest | Match
  9. Kimi K2 Thinking Kimi K2 Thinking Chinese AI lab Moonshot's Kimi K2 established itself as one of the largest open weight models - 1 trillion parameters - back in July . They've now released...

    #ai #generative-ai #llms #llm #pelican-riding-a-bicycle #llm-reasoning #llm-release #openrouter #ai-in-china #artificial-analysis #moonshot

    Origin | Interest | Match
  10. Simple Prompt Tweaks Derail LLM Reasoning - MarkTechPost

    ➡️ MIT researchers analyzed how input changes impact the response quality of 13 prominent LLMs.
    ➡️Prompt perturbations included irrelevant contexts, misleading (pathological) instructions, and a mix of additional yet unnecessary details.
    ➡️Quality dropped substantially, with average declines of up to 55.89% for irrelevant contexts.

    marktechpost.com/2025/04/15/fr

    #AI #PropmtEngineering #LLMReasoning

  11. Simple Prompt Tweaks Derail LLM Reasoning - MarkTechPost

    ➡️ MIT researchers analyzed how input changes impact the response quality of 13 prominent LLMs.
    ➡️Prompt perturbations included irrelevant contexts, misleading (pathological) instructions, and a mix of additional yet unnecessary details.
    ➡️Quality dropped substantially, with average declines of up to 55.89% for irrelevant contexts.

    marktechpost.com/2025/04/15/fr

  12. Simple Prompt Tweaks Derail LLM Reasoning - MarkTechPost

    ➡️ MIT researchers analyzed how input changes impact the response quality of 13 prominent LLMs.
    ➡️Prompt perturbations included irrelevant contexts, misleading (pathological) instructions, and a mix of additional yet unnecessary details.
    ➡️Quality dropped substantially, with average declines of up to 55.89% for irrelevant contexts.

    marktechpost.com/2025/04/15/fr

    #AI #PropmtEngineering #LLMReasoning

  13. Simple Prompt Tweaks Derail LLM Reasoning - MarkTechPost

    ➡️ MIT researchers analyzed how input changes impact the response quality of 13 prominent LLMs.
    ➡️Prompt perturbations included irrelevant contexts, misleading (pathological) instructions, and a mix of additional yet unnecessary details.
    ➡️Quality dropped substantially, with average declines of up to 55.89% for irrelevant contexts.

    marktechpost.com/2025/04/15/fr

    #AI #PropmtEngineering #LLMReasoning

  14. Simple Prompt Tweaks Derail LLM Reasoning - MarkTechPost

    ➡️ MIT researchers analyzed how input changes impact the response quality of 13 prominent LLMs.
    ➡️Prompt perturbations included irrelevant contexts, misleading (pathological) instructions, and a mix of additional yet unnecessary details.
    ➡️Quality dropped substantially, with average declines of up to 55.89% for irrelevant contexts.

    marktechpost.com/2025/04/15/fr

    #AI #PropmtEngineering #LLMReasoning

  15. Unlocking Human-like Reasoning in AI: The Meta Chain-of-Thought Breakthrough

    In an ambitious leap forward, researchers introduce the Meta Chain-of-Thought framework, aiming to enhance reasoning capabilities in large language models (LLMs). This innovative approach not only bui...

    news.lavx.hu/article/unlocking

    #news #tech #MetaChainOfThought #LLMReasoning #AIAdvancements

  16. Unlocking Human-like Reasoning in AI: The Meta Chain-of-Thought Breakthrough

    In an ambitious leap forward, researchers introduce the Meta Chain-of-Thought framework, aiming to enhance reasoning capabilities in large language models (LLMs). This innovative approach not only bui...

    news.lavx.hu/article/unlocking

    #news #tech #MetaChainOfThought #LLMReasoning #AIAdvancements

  17. Unlocking Human-like Reasoning in AI: The Meta Chain-of-Thought Breakthrough

    In an ambitious leap forward, researchers introduce the Meta Chain-of-Thought framework, aiming to enhance reasoning capabilities in large language models (LLMs). This innovative approach not only bui...

    news.lavx.hu/article/unlocking

    #news #tech #MetaChainOfThought #LLMReasoning #AIAdvancements

  18. Unlocking Human-like Reasoning in AI: The Meta Chain-of-Thought Breakthrough

    In an ambitious leap forward, researchers introduce the Meta Chain-of-Thought framework, aiming to enhance reasoning capabilities in large language models (LLMs). This innovative approach not only bui...

    news.lavx.hu/article/unlocking

    #news #tech #MetaChainOfThought #LLMReasoning #AIAdvancements

  19. Unlocking Human-like Reasoning in AI: The Meta Chain-of-Thought Breakthrough

    In an ambitious leap forward, researchers introduce the Meta Chain-of-Thought framework, aiming to enhance reasoning capabilities in large language models (LLMs). This innovative approach not only bui...

    news.lavx.hu/article/unlocking

    #news #tech #MetaChainOfThought #LLMReasoning #AIAdvancements

  20. Four papers on LLM reasoning summarized by @melaniemitchell aiguide.substack.com/p/the-llm along with the background in her latest. Of these, the chain of thought prompting paper's attempt to identify sources of predictions (memorization vs reasoning] is very interesting, although chaotic. Stats people might hate the conclusions. #LLMReasoning #LLMResearch

  21. Four papers on LLM reasoning summarized by @melaniemitchell aiguide.substack.com/p/the-llm along with the background in her latest. Of these, the chain of thought prompting paper's attempt to identify sources of predictions (memorization vs reasoning] is very interesting, although chaotic. Stats people might hate the conclusions. #LLMReasoning #LLMResearch

  22. Four papers on LLM reasoning summarized by @melaniemitchell aiguide.substack.com/p/the-llm along with the background in her latest. Of these, the chain of thought prompting paper's attempt to identify sources of predictions (memorization vs reasoning] is very interesting, although chaotic. Stats people might hate the conclusions. #LLMReasoning #LLMResearch

  23. Four papers on LLM reasoning summarized by @melaniemitchell aiguide.substack.com/p/the-llm along with the background in her latest. Of these, the chain of thought prompting paper's attempt to identify sources of predictions (memorization vs reasoning] is very interesting, although chaotic. Stats people might hate the conclusions. #LLMReasoning #LLMResearch

  24. Four papers on LLM reasoning summarized by @melaniemitchell aiguide.substack.com/p/the-llm along with the background in her latest. Of these, the chain of thought prompting paper's attempt to identify sources of predictions (memorization vs reasoning] is very interesting, although chaotic. Stats people might hate the conclusions. #LLMReasoning #LLMResearch