TangramPuzzle is introduced, a benchmark comprising 668 validated configurations and 1,336 instances for evaluating compositional spatial reasoning under geometric constraints, and the Tangram Construction Expression is formulated to encode tangram configurations with machine-verifiable geometric specifications.
Daixian Liu, Jiayi Kuang, Ying-Hui Li et al.· arXiv.org· 4 citations
This work introduces Dream2Reward, which learns a language-conditioned successful latent transition field from positive demonstrations that provides stronger success-failure separation and more informative feedback on low-quality behavior than progress-based alternatives.
Hao-Yu Zhang, Ze-Cui Zeng, Bin Wang et al.· 3 citations
INSPIRE is an Internalize-Then-Improve approach combining Reference-Guided Student Internalization (RGSI), which produces high-quality preference candidates under the policy model's own distribution, with a stage-wise rubric preference training strategy that decomposes learning into method-oriented and correctness-orie...
Shuai Wang, Jiayi Kuang, Ying-Hui Li et al.· 0 citations
Experiments reveal that models with similar end-to-end accuracy can exhibit markedly different agentic capability profiles, demonstrating that process-level evaluation is crucial for interpreting the true potential of LLMs and guiding the development of next-generation mathematical agents.
Jiayi Kuang, Ying-Hui Li, Yun-Ze Song et al.· 0 citations
JOP-VLN is introduced, a novel VLN framework that synergistically combines off-policy imitation learning and on-policy exploration within a three-stage training pipeline, featuring high-entropy trajectory sampling to enhance RL training efficiency and an error-correction-prioritized trajectory sorting strategy for effe...
Qin He, Lingqing Zhao, Kevin Zheng et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
