Unverified50% confidenceFactExact time
Existing embodied instruction-following planners fall mainly into two categories: supervised learning based on large-scale annotated trajectories, and single-pass serial reasoning that leverages LLM few-shot/zero-shot capabilities.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/30/2026
First Seen
Valid until: 1/28/2027
Sources
Related Entities
Related Claims
UnverifiedThe LLM routing space already has precedents in RouteLLM, Martian, and others; the core idea is to train lightweight classifiers to predict task difficulty and type before inference, then map the results to a model selection strategy.79% similarUnverifiedUsing a small classifier or an LLM to determine the question type and thereby decide whether to trigger retrieval is a common routing strategy.77% similarUnverifiedZero-shot learning is typically achieved via two pathways: meta-learning and generalization based on structural priors.77% similarUnverifiedThe method's procedure is: starting from a baseline reasoning program, each round uses an LLM as a judge, showing it the current program's code and failure cases on training problems and asking it to provide improvement evolution actions; candidate programs are kept in a small program pool ranked by training accuracy, and the next round of editing is performed on the highest-scoring program in the pool.76% similarUnverifiedΨ-0.6 acquires through reinforcement learning a scheduling policy that adaptively selects among different representations, and the model learns during training to judge which reasoning path suits the current task.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1114282API
curl https://kongchang.com/api/v1/knowledge/claims/1114282MCP
get_claim(id=1114282)