Unverified50% confidenceBenchmarkExact time
Skill-Uni was tested on five skill-related benchmarks, improving on average by 66.59% over Qwen3-4B and by 34.82% on average over LLaMA3.1-8B.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/30/2026
First Seen
Valid until: 11/13/2026
Sources
Related Entities
Related Claims
UnverifiedAfter the second round of distilling 3 newly selected skills, all four models reach or exceed the level of the complete skill library, while at this point the size of the complete skill library is at most 11 times that of the skills selected by SGUID.73% similarUnverified3,189 successful rollouts were collected from Qwen3.8-27B for supervised fine-tuning (imitation learning), and performance stagnated at 47.5%, below the results of two rounds of RL training.71% similarUnverifiedAcross six configurations covering five groups of heterogeneous agent combinations, HMA improved the any-medal rate by an average of 6.4 percentage points over its constituent baseline agents.71% similarUnverifiedThe paper conducted RL experiments on Qwen3-8B, and after 40 training steps, EnvSched achieved an average score of 48.81 on the three benchmarks BFCL-v3, tau-Bench, and ACEBench-Agent.69% similarUnverifiedOn Qwen3-8B, after the second round of the loop selected 3 new skills, model performance improved from 64.3% to 66.3%.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1114755API
curl https://kongchang.com/api/v1/knowledge/claims/1114755MCP
get_claim(id=1114755)