10 papers
Scaling Self-Evolving Agents via Parametric Memory
Tao Ren, Weiyao Luo, Hui Yang +8
Existing memory-augmented LLM agents store past experience exclusively in prompt space, as textual summaries or retrieved passages, while keeping model parameters frozen throughout…
Adaptive Robust Estimator for Multi-Agent Reinforcement Learning
Zhongyi Li, Wan Tian, Jingyu Chen +8
Multi-agent collaboration has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models, yet it suffers from interaction-level ambiguity that…
Optimal low-rank stochastic gradient estimation for LLM training
Zehao Li, Tao Ren, Zishi Zhang +2
Large language model (LLM) training is often bottlenecked by memory constraints and stochastic gradient noise in extremely high-dimensional parameter spaces. Motivated by empirical…
Omni-Masked Gradient Descent: Memory-Efficient Optimization via Mask Traversal with Improved Convergence
Hui Yang, Tao Ren, Jinyang Jiang +2
Memory-efficient optimization methods have recently gained increasing attention for scaling full-parameter training of large language models under the GPU-memory bottleneck. Existi…
Nonparametric Bayesian Optimization for General Rewards
Zishi Zhang, Tao Ren, Yijie Peng
This work focuses on Bayesian optimization (BO) under reward model uncertainty. We propose the first BO algorithm that achieves no-regret guarantee in a general reward setting, req…
RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training
Tao Ren, Jinyang Jiang, Hui Yang +10
Reinforcement learning with verifiable reward has recently emerged as a central paradigm for post-training large language models (LLMs); however, prevailing mean-based methods, suc…
Half-order Fine-Tuning for Diffusion Model: A Recursive Likelihood Ratio Optimizer
Tao Ren, Zishi Zhang, Jingyang Jiang +9
The probabilistic diffusion model (DM), generating content by inferencing through a recursive chain structure, has emerged as a powerful framework for visual generation. After pre-…
FLOPS: Forward Learning with OPtimal Sampling
Tao Ren, Zishi Zhang, Jinyang Jiang +4
Given the limitations of backpropagation, perturbation-based gradient computation methods have recently gained focus for learning with only forward passes, also referred to as quer…
Deep Reinforcement Learning for Solving Management Problems: Towards A Large Management Mode
Jinyang Jiang, Xiaotian Liu, Tao Ren +5
We introduce a deep reinforcement learning (DRL) approach for solving management problems including inventory management, dynamic pricing, and recommendation. This DRL approach has…
RiskMiner: Discovering Formulaic Alphas via Risk Seeking Monte Carlo Tree Search
Tao Ren, Ruihan Zhou, Jinyang Jiang +3
The formulaic alphas are mathematical formulas that transform raw stock data into indicated signals. In the industry, a collection of formulaic alphas is combined to enhance modeli…