Preprint
Jul 2026
WildTrace: Benchmarking Natural Evidence Trails in Long-Context Reasoning
WILDTRACE is introduced, a benchmark of 481 tasks over 214 naturally occurring long-form sources such as technical incident reports and lesser-known literary narratives, where all evidence trails arise from the document's own causal, temporal, and narrative logic.
Zixin Chen, Peng Liu, Haobo Li et al.
· 0 citations