Unverified50% confidenceFactExact time
AREX-2 is based on a core assumption that reflection and long-horizon execution capabilities are domain-agnostic and can be transferred from scenarios suitable for supervised training to different task domains
1
Sources
50%
Confidence
Long-term
Relevance
10/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAREX-2 synthesizes long-horizon improvement trajectories from two domains—machine learning tasks and algorithmic programming tasks—as training data68% similarUnverified任何先优化表示再训练分类器的两阶段方法都需要仔细验证其代理目标与下游任务的对齐程度67% similarUnverified大模型的工程落地分为训练和推理两个核心环节65% similarUnverifiedTraining thinking-length preferences into the model weights is more stable than using system prompts at deployment time to request concise answers, as the latter is an external constraint that is unstable while the former becomes the model's default behavior.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/963921API
curl https://kongchang.com/api/v1/knowledge/claims/963921MCP
get_claim(id=963921)