5 papers
EDGE: Experience-Distillation for Guided Exploration in Agentic Reinforcement Learning
Can Xie, Yuyi Zhou, Wen Yang +5
Reinforcement learning with outcome-based objectives such as GRPO enables LLM-based agents to solve complex, long-horizon tasks, yet the reusable exploration patterns embedded in i…
Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning
Can Xie, Ruotong Pan, Xiangyu Wu +4
Reinforcement Learning with Verifiable Rewards (RLVR) has shown significant promise for enhancing the reasoning capabilities of large language models (LLMs). However, prevailing al…
Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents
Shuo Ren, Can Xie, Pu Jian +3
As scientific research becomes increasingly complex, innovative tools are needed to manage vast data, facilitate interdisciplinary collaboration, and accelerate discovery. Large la…
Searching for Quantum Effects in the Brain: A Bell-Type Test for Nonclassical Latent Representations in Autoencoders
I. K. Kominis, C. Xie, S. Li +2
Whether neural information processing is entirely classical or involves quantum-mechanical elements remains an open question. Here we propose a model-agnostic, information-theoreti…
Fully analogue in-memory neural computing via quantum tunneling effect
Songyuan Li, Teng Wang, Jinrong Tang +7
Fully analogue neural computation requires hardware that can implement both linear and nonlinear transformations without digital assistance. While analogue in-memory computing effi…