Unverified50% confidenceFactExact time
WANDR is a benchmark that evaluates both broad information retrieval and deep investigation, aimed at comprehensive evaluation of research agents.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSLR要求研究者事先定义严格的检索协议，包括研究问题、数据源、检索字符串、纳入/排除标准、质量评估准则和数据提取表格64% similarUnverifiedPromptSR provides three capabilities — prompt experimentation, experiment management, and result analysis — to support LLM-based screening experiments.63% similarUnverifiedTraser is a local debugging tool for multi-step AI systems that narrows the investigation scope to a small number of evidence-supported locations worth focusing on by analyzing suspicious execution traces.62% similarUnverifiedTest-time search refers to the AI running a search process in real time during the inference phase of actual gameplay (such as Monte Carlo Tree Search) to find better moves, which in hidden-information scenarios requires simultaneously traversing multiple possible opponent state combinations62% similarUnverified系统文献综述（SLR）源于循证医学领域，最初由Cochrane协作网推广，用于汇总临床试验的证据以指导医疗决策61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1054401API
curl https://kongchang.com/api/v1/knowledge/claims/1054401MCP
get_claim(id=1054401)