Xiaohan Shan

Yuan Wei, Xiaohan Shan, Jianmin Li

Multi-agent reinforcement learning (MARL) faces two critical bottlenecks distinct from single-agent RL: credit assignment in cooperative tasks and partial observability of environmental states. We propose LERO, a framework integrating Large language models (LLMs) with evolutionary optimization to address these MARL-specific challenges. The solution centers on two LLM-generated components: a hybrid reward function that dynamically allocates individual credit through reward decomposition, and an observation enhancement function that augments partial observations with inferred environmental context. An evolutionary algorithm optimizes these components through iterative MARL training cycles, where top-performing candidates guide subsequent LLM generations. Evaluations in Multi-Agent Particle Environments (MPE) demonstrate LERO's superiority over baseline methods, with improved task performance and training efficiency.

Yuan Wei, Xiaohan Shan, Ran Miao et al.

Reinforcement learning (RL) agent development traditionally requires substantial expertise and iterative effort, often leading to high failure rates and limited accessibility. This paper introduces Agent$^2$, an LLM-driven agent-generates-agent framework for fully automated RL agent design. Agent$^2$ autonomously translates natural language task descriptions and environment code into executable RL solutions without human intervention. The framework adopts a dual-agent architecture: a Generator Agent that analyzes tasks and designs agents, and a Target Agent that is automatically generated and executed. To better support automation, RL development is decomposed into two stages, MDP modeling and algorithmic optimization, facilitating targeted and effective agent generation. Built on the Model Context Protocol, Agent$^2$ provides a unified framework for standardized agent creation across diverse environments and algorithms, incorporating adaptive training management and intelligent feedback analysis for continuous refinement. Extensive experiments on benchmarks including MuJoCo, MetaDrive, MPE, and SMAC show that Agent$^2$ outperforms manually designed baselines across all tasks, achieving up to 55\% performance improvement with consistent average gains. By enabling a closed-loop, end-to-end automation pipeline, this work advances a new paradigm in which agents can design and optimize other agents, underscoring the potential of agent-generates-agent systems for automated AI development.

Zhihuai Chen, Bo Li, Xiaohan Shan et al.

The arisen of Bitcoin has led to much enthusiasm for blockchain research and block mining, and the extensive existence of mining pools helps its participants (i.e., miners) gain reward more frequently. Recently, the mining pools are proved to be vulnerable for several possible attacks, and pool block withholding attack is one of them: one strategic pool manager sends some of her miners to other pools and these miners pretend to work on the puzzles but actually do nothing. And these miners still get reward since the pool manager can not recognize these malicious miners. In this work, we revisit the game-theoretic model for pool block withholding attacks and propose a revised approach to reallocate the reward to the miners. Fortunately, in the new model, the pool managers have strong incentive to not launch such attacks. We show that for any number of mining pools, no-pool-attacks is always a Nash equilibrium. Moreover, with only two minority mining pools participating, no-pool-attacks is actually the unique Nash equilibrium.