Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

COMPANY · ENTITY #3060

CISPO

Related event timeline, sources and context from the news index.

EVENT TIMELINE

3

COMPANIES · 1 SOURCE · AWS Machine Learning

Amazon SageMaker AI demonstrates multi-turn reinforcement learning (MTRL) fine-tuning for search agents with Qwen3.6-27B

Amazon’s blog post describes using Amazon SageMaker AI’s multi-turn reinforcement learning (MTRL) capability to fine-tune a Qwen3.6-27B model for an LLM-powered search agent. The write-up details MTRL features—serverless execution, modular agent-environment interfaces, asynchronous rollouts, built-in algorithms (PPO, CISPO, IS), trajectory observability via MLflow, and evaluation jobs—and shows an enterprise search use case combining BM25 and vector search tools.

6.0

MODELS · 1 SOURCE · Mistral AI

Robostral debuts Robostral Navigate, an 8B single-RGB navigation model

Robostral introduced Robostral Navigate, an 8B embodied navigation model that uses only a single RGB camera and plain-language instructions to move robots. The company reports 76.6% success on R2R-CE validation unseen (79.4% validation seen), claims to outperform prior single-camera and multi-sensor systems, and says the model was trained entirely in simulation on ~2.4M trajectories across 350k scenes using token-efficient prefix-caching and online RL (CISPO).

8.0

MODELS · 1 SOURCE · Mistral AI

Leanstral 1.5: open-source 6B-active-parameter model advances formal verification

Leanstral 1.5 is an Apache-2.0 open-source model (119B total, 6B active parameters) released for Lean 4 proof engineering; it uses mid-training, supervised fine-tuning, and reinforcement learning with CISPO and is available via Hugging Face and a free API. The model saturates miniF2F, solves 587/672 PutnamBench problems, achieves 87% on FATE-H and 34% on FATE-X, scales strongly with token budget, improves FLTEval pass rates, and found 5 previously unknown bugs across 57 tested repositories.

8.0