Unverified50% confidenceFactExact time
LIBERO-PeRM imposes four hard constraints on preference definition: preferences must be expressible in language, must not change the task goal, must be automatically evaluable, and must be reusable across tasks.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLIBERO-PeRM designs its evaluation system around five progressive questions: zero-shot preference following, single-preference learning, preference acquisition efficiency, preference generalization, and multi-preference composition and conflict handling.77% similarUnverifiedWhen an LLM call is constrained to choosing an answer from a fixed set of options, it is essentially a classifier rather than a generation task.65% similarUnverifiedThe LIBERO series is a widely used manipulation benchmark in the robot learning field, containing a large number of language-conditioned long-horizon manipulation tasks, used to evaluate the generalization and continual learning ability of policies.63% similarUnverifiedLLM在「生成」和「评估」时激活的推理路径不同，生成任务偏向延续已有语义方向，评估任务激活更多批判性、面向异常检测的推理路径62% similarUnverified元指令（Meta-Prompt）是指不直接描述目标内容，而是要求模型对自身推理过程、行为规则或能力边界进行反思与操作的指令61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1041740API
curl https://kongchang.com/api/v1/knowledge/claims/1041740MCP
get_claim(id=1041740)