Related papers: MEMO: Memory-Augmented Model Context Optimization …

Advancements in deep multi-agent reinforcement learning (MARL) have positioned it as a promising approach for decision-making in cooperative games. However, it still remains challenging for MARL agents to learn cooperative strategies for…

Proficient game agents with diverse play styles enrich the gaming experience and enhance the replay value of games. However, recent advancements in game AI based on reinforcement learning have predominantly focused on improving proficiency,…

Making sophisticated, robust, and safe sequential decisions is at the heart of intelligent systems. This is especially critical for planning in complex multi-agent environments, where agents need to anticipate other agents' intentions and…

Large Language Model (LLM) has exhibited strong reasoning ability in text-based contexts across various domains, yet the limitation of context window poses challenges for the model on long-range inference tasks and necessitates a memory…

In Natural Language Processing (NLP), the Elo rating system, originally designed for ranking players in dynamic games such as chess, is increasingly being used to evaluate Large Language Models (LLMs) through "A vs B" paired comparisons.…

Recent memory agents improve LLMs by extracting experiences and conversation history into an external storage. This enables low-overhead context assembly and online memory update without expensive LLM training. However, existing solutions…

Understanding decision-making in multi-AI-agent frameworks is crucial for analyzing strategic interactions in network-effect-driven contexts. This study investigates how AI agents navigate network-effect games, where individual payoffs…

LLM-driven multi-agent-based simulations have been gaining traction with applications in game-theoretic and social simulations. While most implementations seek to exploit or evaluate LLM-agentic reasoning, they often do so with a weak…

Context window expansion is often treated as a straightforward capability upgrade for LLMs, but we find it systematically fails in multi-agent social dilemmas. Across 7 LLMs and 4 games over 500 rounds, expanding accessible history degrades…

Human preference alignment is essential to improve the interaction quality of large language models (LLMs). Existing alignment methods depend on manually annotated preference data to guide the LLM optimization directions. However,…

Large language models (LLMs) excel at many NLP tasks but struggle to sustain long-term interactions due to limited attention over extended dialogue histories. Retrieval-augmented generation (RAG) mitigates this issue but lacks reliable…

Stochastic games have become a prevalent framework for studying long-term multi-agent interactions, especially in the context of multi-agent reinforcement learning. In this work, we comprehensively investigate the concept of constant-memory…

Memory-augmented LLM agents enable interactions that extend beyond finite context windows by storing, updating, and reusing information across sessions. However, training such agents with reinforcement learning in multi-session environments…

As the performance of larger, newer Large Language Models continues to improve for strategic Theory of Mind (ToM) tasks, the demand for these state-of-the-art models increases commensurately. However, their deployment is costly both in…

Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when…

Statefulness is essential for large language model (LLM) agents to perform long-term planning and problem-solving. This makes memory a critical component, yet its management and evolution remain largely underexplored. Existing evaluations…

Optimizing artificial intelligence (AI) for dynamic environments remains a fundamental challenge in machine learning research. In this paper, we examine evolutionary training methods for optimizing AI to solve the game 2048, a 2D sliding…

Reinforcement learning (RL) has re-emerged as a natural approach for training interactive LLM agents in real-world environments. However, directly applying the widely used Group Relative Policy Optimization (GRPO) algorithm to multi-turn…

Memory-augmented LLM agents maintain external memory banks to support long-horizon interaction, yet most existing systems treat construction, retrieval, and utilization as isolated subroutines. This creates two coupled challenges: strategic…

Reinforcement Learning (RL) has shown great potential for autonomous decision-making in the cybersecurity domain, enabling agents to learn through direct environment interaction. However, RL agents in Autonomous Cyber Operations (ACO)…