Unverified50% confidenceBenchmarkExact time
At expert retention ratios of 75% and 50%, PEEP and DCEP surpass existing state-of-the-art baselines on most benchmarks and achieve the best average performance on general tasks and mathematical reasoning tasks.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/2/2026
First Seen
Valid until: 1/31/2027
Sources
Related Entities
Related Claims
UnverifiedThe strongest configuration solved 78.2% of tasks under the strict task-level criteria and achieved a pass rate of 94.8% under the standard-level evaluation.72% similarUnverified在歧义点的四类行为中,'先搜再问'成功率最高,平均通过率达93.4%,远高于'直接猜'的56.5%,'搜多次再猜'为51.5%71% similarUnverified在从50%到92%的准确率提升中,REPL贡献最大(直接从50%跳至74%),随后领域知识注入、模糊搜索、公式追踪、系统prompt优化和bug修复层层累积70% similarUnverifiedIn the 240-question test, ReAct's accuracy was 59.6%, Plan-execute's 61.7%, Supervisor's 65.0%, and Draft-verify's 63.7%.70% similarUnverifiedThis secondary scoring uses four weights: overall intelligence accounts for 60%, agent and terminal coding capability 20%, cost efficiency 10%, and output speed 10%.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1125226API
curl https://kongchang.com/api/v1/knowledge/claims/1125226MCP
get_claim(id=1125226)