This work operationalizes constructive specification with constructive specification, which builds hierarchical capability representations from limited profiling over diverse benchmarks, using an optimism-guided profiler that prioritizes informative regions and prunes low-utility areas with guarantees, and enables plug...
Jian-Dong Liu, Zi-Chen Zhao, Hao Sun et al.· Proceedings of the 32nd ACM...· 4 citations· ⚡1
It is shown that policy entropy bounds both the policy gradient and probability update norms; consequently, entropy collapse effectively stops reward signal backpropagation, preventing further policy learning regardless of data quality.
Cong Qin, Jiaye Lin, Xiaoliang Fu et al.· Proceedings of the 32nd ACM...· 0 citations
Reinforcement Learning with Verifiable Rewards (RLVR) has become a standard approach for improving complex reasoning in Large Language Models (LLMs). However, entropy collapse remains a critical bottleneck, often leading to performance degradation. While typically attributed to reduced exploration, we identify a more s...
Cong Qin, Jiaye Lin, Xiaoliang Fu et al.· Proceedings of the 32nd ACM...· 0 citations
This work operationalizes constructive specification with constructive specification, which builds hierarchical capability representations from limited profiling over diverse benchmarks, using an optimism-guided profiler that prioritizes informative regions and prunes low-utility areas with guarantees, and enables plug...
Jian-Dong Liu, Zi-Chen Zhao, Haodong Sun et al.· Proceedings of the 32nd ACM...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
