This survey synthesizes agentic reasoning methods into a unified roadmap bridging thought and action, and outlines open challenges and future directions, including personalization, long-horizon interaction, world modeling, scalable multi-agent training, and governance for real-world deployment.
Tian-Xin Wei, Ting-Wei Li, Zhining Liu et al.· 39 citations· ⚡6
CoFiRec is proposed, a novel generative recommendation framework that explicitly incorporates the Coarse-to-Fine nature of item semantics into the tokenization process, and it is proved that structured tokenization leads to lower dissimilarity between generated and ground truth items, supporting its effectiveness in ge...
CoReflect is introduced, which unifies dialogue simulation and evaluation into an adaptive, iterative process that allows evaluation protocols to adapt alongside the rapidly advancing capabilities of dialogue models.
AdaFuse is an adaptive ensemble decoding framework that dynamically selects semantically appropriate fusion units during generation that establishes a synergistic interaction between adaptive ensembling and test-time scaling, where ensemble decisions guide targeted exploration, and the resulting diversity in turn stren...
This formulation enables a systematic study of key self-improvement factors through the proposed Evo-Harness, and provides a principled understanding of how LLM agents can effectively learn on the fly.
Tian-Xin Wei, Zhan Shi, Min-hua Lin et al.· 10 citations
EvoHarness-RL is introduced, which exposes Belief, Progress, and Experience (BPE) as policy-facing harness state and reveals two key dynamics: harness annealing, where training internalizes recurring harness-use patterns into the model policy and shifts the agent from frequent harness calls toward selective external-st...
Xuying Ning, Dongqi Fu, Tianxin Wei 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.
