Author
University of Illinois Urbana-Champaign
We have 6 of 40 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Reinforcement learning with verifiable rewards (RLVR) has been shown to improve the reasoning capability of large language models (LLMs) across diverse reasoning tasks. However, group-based RLVR methods, such as GRPO, assign a uniform advantage to all tokens within rollouts of the same outcome. While existing works ref...
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.
The proposed Mixture of Roles (MoRe), which adaptively composes multiple specializations into a single steering vector for single-turn inference, enables multi-perspective specialization in a single-agent, single-turn inference process.
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 work constructs and releases SETA-Env, the largest open-source verifiable terminal RL dataset to date, containing over 4,500 environments, and demonstrates that SETA- Env provides high-quality training environments for terminal agents and serves as a valuable resource for advancing research on terminal-based agent...
This work proposes a principled VLM TTA method called \algname, and theoretically reveals that the InfoNCE loss can be neatly reformulated as a Wasserstein OT formulation, thereby unifying the objectives of the inference and adaptation of VLMs to achieve their mutual benefits.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
