…an explicit tension between parametric and contextual information induced by mandating logical schemata that deviate from those expected for a target task. Our evaluation reveals that LLMs consistently prioritize sensibility over compliance…
…mixed RLVR suffers from inter-capability divergence cost, while the pipeline of first training experts and then performing OPD , though avoiding divergence, fails to fully absorb teacher capabilities due to large behavioral…
…Further analyses show that the learned curator produces more targeted skill use, while the skills in SkillRepo evolve into more richly structured Markdown files that encode higher-level meta-skills over time…
…The following papers were recommended by the Semantic Scholar API Targeted Exploration via Unified Entropy Control for Reinforcement Learning (2026) Rethinking Exploration in RLVR: From Entropy Regularization to Refinement via Bidirectional Entropy…
…We study speculative decoding as a lossless acceleration primitive for RL rollouts that preserves the target model's output distribution. We implement speculative decoding in NeMo-RL with a vLLM backend , supporting…
…In this work, we challenge this assumption by constructing a controlled evaluation framework, SpatialUncertain, and introducing two types of observation challenges: (1) occlusion , which hides target information, and (2) perspective ambiguity , which…
…Utilizing the expert-verified verbatim transcriptions and grading reports of student solutions, we simultaneously evaluate various MLLMs' upstream recognition fidelity and downstream auto-grading performance. Our evaluation uncovers an astonishing scale of…
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.