Unverified50% confidenceFactExact time
The planner was trained via supervised fine-tuning (SFT) on outcome-selection trajectories from 140 training questions and 28 development questions.
1
Sources
50%
Confidence
Long-term
Relevance
9/24/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedLarge model training goes through three core stages: pre-training, supervised fine-tuning (SFT), and preference alignment.75% similarUnverifiedAgent Tuning is a specialized direction of supervised fine-tuning (SFT), where training samples are complete task trajectories rather than traditional question-answer pairs.74% similarUnverified后训练通常涵盖监督微调（SFT）、强化学习对齐（RLHF/RLAIF）以及领域适配微调，视觉推理模型还涉及视觉指令微调72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/946185API
curl https://kongchang.com/api/v1/knowledge/claims/946185MCP
get_claim(id=946185)