This work introduces SPEAR (Symbolic Process Evaluation and Alignment Reward), a training-free and plug-and-play process reward method for sequence-level on-policy distillation that effectively bridges the reasoning gap between student and teacher models via sequence-level distillation with efficient dense process rewa...
Zhuo-Chun Li, Yuelyu Ji, Yiming Zeng et al.· 1 citation
This work proposes MoEGen, an adaptation framework that shifts MoE-based PEFT from expert selection to expert-conditioned parameter generation, and decouples expert capacity from adapter storage while enabling instance-conditioned adaptation.
Yiming Zeng, Lei Lu, Zexin Li et al.· 1 citation· ⚡1
Thinkingbox is introduced, a sandbox for tool-agent-user interaction that provides isolated MCP-compatible tool sessions, complete execution traces, and outcome evaluation over terminal backend state, and Thinkingbox-bench reveals a large gap between occasionally finding a successful trajectory and reliably completing...
Zhuo-Chun Li, Youngmin Ko, Ali Keramati et al.· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.