一作ACL 2026Poster· Natural Language Processing
D eep P lanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints
Yinger Zhang · Shutong Jiang · Renhao Li · Jianhong Tu · Yang Su · Lianghao Deng · Xudong Guo · ChenXu Lv · Junyang Lin
摘要
While agent evaluation has shifted toward long-horizon tasks, most benchmarks still emphasize local, step-level reasoning rather than the global constrained optimization (e.g., time and financial budgets) that demands genuine planning ability. Meanwhile, existing LLM planning benchmarks underrepr...