DiG-Plan: Mitigating Early Commitment for Tool-Graph Planning via Diffusion Guidance
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 DiG-Plan, a framework that decouples combinatorial exploration from structural refinement. DiG-Plan employs a diffusion-based proposer to generate diverse tool sets via iterative refinement, followed by an AR refiner for dependency prediction. On TaskBench, DiG-Plan improves over AR baselines by a 10% relative margin, with the largest gains on complex compositional tasks; API-Bank results show that the propose-refine-select design remains effective across domains. Code is available at https://github.com/puddingyeah/DiG-Plan.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
What Is the Minimum Architecture for Prolepsis? Early Irrevocable Commitment Across Tasks in Small Transformers
When do transformers commit to a decision, and what prevents them from correcting it? We introduce prolepsis: a transformer commits early, task-specific attention heads sustain the commitment, and no layer corrects it. R…
The Windfall Clause: Distributing the Benefits of AI for the Common Good
As the transformative potential of AI has become increasingly salient as a matter of public and political interest, there has been growing discussion about the need to ensure that AI broadly benefits humanity. This in tu…
When to Plan, When to Polish: Noise Level as a Granularity Axis for Diffusion Language Models
Standard tokenwise diffusion LMs keep training corruption and inference commitment at token granularity throughout denoising. At high noise, this leaves scattered local fragments rather than coherent evidence, making it …
Multi-Transmission Node DER Aggregation: Chance-Constrained Unit Commitment with Bounded Hetero-Dimensional Mixture Model for Uncertain Distribution Factors
To facilitate the integration of distributed energy resources (DERs) into the wholesale market while maintaining the tractability of associated market operation tools such as unit commitment (UC), existing DER aggregatio…
Using Sub-Optimal Plan Detection to Identify Commitment Abandonment in Discrete Environments
Assessing whether an agent has abandoned a goal or is actively pursuing it is important when multiple agents are trying to achieve joint goals, or when agents commit to achieving goals for each other. Making such a deter…