Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Planning Commitment of LLM under Partial Observability
Cassie Huang, Zhanwei Cao, Yeawon Lee +7
LLM-based planning agents commit to plans of different lengths before interacting with a partially observable environment. Some aggressively commit to a long plan based on assumpti…
cs.AI2026
Representation Alignment as a Bottleneck in LLM-Based Retrosynthesis Planning
Hyunwoo Yoo, Cassie Huang, Haebin Shin +2
While LLMs show promise in general reasoning, symbolic planning in chemistry remains a bottleneck. Direct ''SMILES-to-PDDL'' attempts fail because they force models to juggle chemi…