Search

Few direct matches — filled in with the latest updates.

Tag: #agentic-rl3 results

MemoraX AI Raises $10M Seed Round

MemoraX AI Raises $10M Seed Round

MemoraX AI, a memory-enhanced large model, secured millions in USD seed funding led by L2F Guangyuan Entrepreneur Fund and Zhongding Capital. The capital will drive iteration and engineering of Agentic RL algorithms, plus productization of its endogenous memory modules.

ARLArena: Stable Agentic RL Framework

ARLArena: Stable Agentic RL Framework

ARLArena offers a stable training recipe and analysis framework for agentic reinforcement learning (ARL) to combat training collapse. It decomposes policy gradients into four core dimensions and introduces SAMPO, a method mitigating key instability sources. SAMPO ensures consistent stability and superior performance across diverse agentic tasks.

SELFCEST: Learned Parallel Model Clones

SELFCEST: Learned Parallel Model Clones

SELFCEST equips base language models to spawn same-weight clones in parallel contexts via agentic reinforcement learning. It trains end-to-end with global task rewards and shared-parameter rollouts to allocate budgets across branches. This improves accuracy-cost Pareto frontiers on math reasoning and long-context QA benchmarks with OOD generalization.