Large language models (LLMs), especially recent reasoning-oriented models trained with reinforcement learning, achieve near-saturating accuracy on many reasoning benchmarks. However, it remains unclear whether these models truly reason over semantic structure or rely on superficial symbol patterns and familiar language...
Jing-Hao Zhang, Shi-Song Chen, Zhi-Xu Li et al.· Proceedings of the 35th ACM...· 0 citations
Large language models (LLMs), especially recent reasoning-oriented models trained with reinforcement learning, achieve near-saturating accuracy on many reasoning benchmarks. However, it remains unclear whether these models truly reason over semantic structure or rely on superficial symbol patterns and familiar language...
Jing-Hao Zhang, Shi-Song Chen, Zhi-Xu Li et al.· Proceedings of the 35th ACM...· 0 citations
Retrieval-Augmented Generation (RAG) effectively grounds large language models (LLMs) in external knowledge but struggles with
exploratory reasoning problems (ERPs)
that are the complex queries involving high uncertainty and ambiguity. Resolving ERPs requires complex reasoning with unclear paths, tending to result...
Gan-Lin Xu, Ling-Hao Zhang, Zhi-Tao Yin et al.· Proceedings of the ACM on Ma...· 0 citations
A novel policy gradient method is introduced, Hindsight Policy Optimization (HPO), that projects both the current policy distribution and the hindsight distribution into an intent space and extracts low-variance learning signals from the Wasserstein distance between them.
Zishang Jiang, Tingyun Li, Jinyi Han et al.· 0 citations
A multi-layer taxonomy of 14 capability domains and 91 subskills across Primitive, Constructed, and Integrative layers is introduced and supports research organization, coverage audits, evaluation interpretation, and testable hypotheses for diagnosis, training, and transfer.