Paper

DiG-Plan: Mitigating Early Commitment for Tool-Graph Planning via Diffusion Guidance

arXiv:2606.05728v1 Announce Type: cross Abstract: Generating executable tool plans requires selecting appropriate subsets from tool libraries, a combinatorial search problem with an exponentially large solution space. However, we identify a critical misalignment in predominant approaches: standard autoregressive (AR) decoding suffers from early commitment, where initial token choices rigidly constrain the search trajectory. A controlled study shows that masked denoising raises Pass@10 solution coverage from 0.320 to 0.943 over AR sampling under matched compute. Motivated by this, we propose D…

Authors:

Related discussions