Ministral-3-3B
PulseAugur coverage of Ministral-3-3B — every cluster mentioning Ministral-3-3B across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New benchmark evaluates AI agents' multi-domain self-improvement
Researchers have introduced ParetoRSI-Gym, a new benchmark designed to evaluate recursive self-improvement (RSI) in AI agents across multiple domains. Unlike previous single-benchmark evaluations, ParetoRSI-Gym fixes th…
-
New framework uses LLM-generated knowledge for efficient zero-shot text classification
Researchers have developed SLKR (Semantic Label Knowledge Retrieval), a novel framework for zero-shot text classification that leverages a flagship LLM to generate label definitions and retrieval keywords. This offline …
-
New self-distillation methods improve LLM performance without external teachers · 4 sources tracked
Researchers have introduced several novel self-distillation techniques for language models, aiming to improve performance without requiring external teachers or ground-truth labels. Activation-Conditioned Self-Distillat…
-
Liquid AI releases compact agent model; Mistral launches safety classifier
Liquid AI has released LFM2.5-2.6B, a compact text-only model optimized for agent harnesses and tool interaction, featuring a large context window and multilingual support. While not recommended for complex coding, its …
-
Personas shape LLM agent behavior in strategic games
Researchers investigated how persona prompts influence the strategic behavior of large language model agents in a "Split or Steal" game. Using four open-source models (Ministral-3-3B, phi4:14b, Gemma3:12b, and Gemma4:e4…
-
New research identifies actionable directions to mitigate AI model misalignment
Researchers have identified a method to detect and mitigate emergent misalignment in language models by analyzing activation directions. This approach, tested across four model families including Qwen2.5-1.5B, Gemma-2-2…