English
Related papers

Related papers: MOA: Multi-Objective Alignment for Role-Playing Ag…

200 papers

Policy gradient (PG) methods are popular reinforcement learning (RL) methods where a baseline is often applied to reduce the variance of gradient estimates. In multi-agent RL (MARL), although the PG theorem can be naturally extended, the…

Machine Learning · Computer Science 2022-04-05 Jakub Grudzien Kuba , Muning Wen , Yaodong Yang , Linghui Meng , Shangding Gu , Haifeng Zhang , David Henry Mguni , Jun Wang

Multi-Agent Reinforcement Learning (MARL) has become a powerful framework for numerous real-world applications, modeling distributed decision-making and learning from interactions with complex environments. Resource Allocation Optimization…

Multiagent Systems · Computer Science 2025-05-01 Mohamad A. Hady , Siyi Hu , Mahardhika Pratama , Jimmy Cao , Ryszard Kowalczyk

Mathematical reasoning is a fundamental capability for large language models (LLMs), yet achieving high performance in this domain remains a significant challenge. The auto-regressive generation process often makes LLMs susceptible to…

Artificial Intelligence · Computer Science 2024-12-02 Xiaoxuan Lou , Chaojie Wang , Bo An

While reasoning has become a central capability of large language models (LLMs), the reasoning patterns required for different scenarios are often misaligned. Mathematical reasoning typically relies on intrinsic logic to solve closed-world…

Artificial Intelligence · Computer Science 2026-05-12 Junjian Wang , Xin Zhou , Qiran Xu , Kun Zhan

Post-training of LLMs with RLHF, and subsequently preference optimization algorithms such as DPO, IPO, etc., made a big difference in improving human alignment. However, all such techniques can only work with a single (human) objective. In…

Machine Learning · Computer Science 2025-05-19 Akhil Agnihotri , Rahul Jain , Deepak Ramachandran , Zheng Wen

Reward shaping (RS) is a powerful method in reinforcement learning (RL) for overcoming the problem of sparse or uninformative rewards. However, RS typically relies on manually engineered shaping-reward functions whose construction is…

Memory systems are critical for LLMs, mitigating context window limitations and supporting long-horizon user-LLM interactions. Such systems typically comprise multiple agents responsible for memory construction and retrieval. Existing…

Multiagent Systems · Computer Science 2026-04-28 Wenyu Mao , Haoyang Liu , Haosong Tan , Yaorui Shi , Jiancan Wu , An Zhang , Xiang Wang

Current role-playing agents (RPAs) are typically constructed by imitating surface-level behaviors, but this approach lacks internal cognitive consistency, often causing out-of-character errors in complex situations. To address this, we…

Computation and Language · Computer Science 2026-01-09 Yihong Tang , Kehai Chen , Xuefeng Bai , Benyou Wang , Zeming Liu , Haifeng Wang , Min Zhang

Prompt optimization has become a practical way to improve the performance of Large Language Models (LLMs) without retraining. However, most existing frameworks treat evaluation as a black box, relying solely on outcome scores without…

Multiagent Systems · Computer Science 2026-04-01 Wonduk Seo , Juhyeon Lee , Junseo Koh , Wonseok Choi , Hyunjin An , Jian Park , Seunghyun lee , Haihua Chen , Yi Bu

Achieving mission objectives in a realistic simulation of aerial combat is highly challenging due to imperfect situational awareness and nonlinear flight dynamics. In this work, we introduce a novel 3D multi-agent air combat environment and…

Robotics · Computer Science 2025-10-23 Ardian Selmonaj , Giacomo Del Rio , Adrian Schneider , Alessandro Antonucci

Multi-Agent Reinforcement Learning can lead to the development of collaborative agent behaviors that show similarities with organizational concepts. Pushing forward this perspective, we introduce a novel framework that explicitly…

Artificial Intelligence · Computer Science 2025-04-01 Julien Soulé , Jean-Paul Jamont , Michel Occello , Louis-Marie Traonouez , Paul Théron

The advancement of Large Language Models (LLMs) has spurred significant interest in Role-Playing Agents (RPAs) for applications such as emotional companionship and virtual interaction. However, recent RPAs are often built on explicit…

Computation and Language · Computer Science 2025-06-03 Yihong Tang , Kehai Chen , Muyun Yang , Zhengyu Niu , Jing Li , Tiejun Zhao , Min Zhang

Recently, there has been an increasing interest in automated prompt optimization based on reinforcement learning (RL). This approach offers important advantages, such as generating interpretable prompts and being compatible with black-box…

Machine Learning · Computer Science 2023-10-26 Dong-Ki Kim , Sungryull Sohn , Lajanugen Logeswaran , Dongsub Shim , Honglak Lee

Sliding-window attention offers a hardware-efficient solution to the memory and throughput challenges of Large Language Models (LLMs) in long-context scenarios. Existing methods typically employ a single window length across all attention…

The performance of the reward model (RM) is a critical factor in improving the effectiveness of the large language model (LLM) during alignment fine-tuning. There remain two challenges in RM training: 1) training the same RM using various…

Computation and Language · Computer Science 2024-04-30 Shanghaoran Quan

We introduce MMaDA, a novel class of multimodal diffusion foundation models designed to achieve superior performance across diverse domains such as textual reasoning, multimodal understanding, and text-to-image generation. The approach is…

Computer Vision and Pattern Recognition · Computer Science 2025-09-26 Ling Yang , Ye Tian , Bowen Li , Xinchen Zhang , Ke Shen , Yunhai Tong , Mengdi Wang

Natural language processing (NLP) has seen remarkable advancements with the development of large language models (LLMs). Despite these advancements, LLMs often produce socially biased outputs. Recent studies have mainly addressed this…

Computation and Language · Computer Science 2025-02-13 Zhenjie Xu , Wenqing Chen , Yi Tang , Xuanying Li , Cheng Hu , Zhixuan Chu , Kui Ren , Zibin Zheng , Zhichao Lu

Recent advancements in Reinforcement Learning (RL), particularly Group Relative Policy Optimization (GRPO), have significantly enhanced the reasoning capabilities of Large Language Models. However, applying these problem-centric…

Computation and Language · Computer Science 2026-05-26 Yihong Tang , Kehai Chen , Liang Yue , Benyou Wang , Min Zhang

The Mixture-of-Agents (MoA) framework has shown promise in improving large language model (LLM) performance by aggregating outputs from multiple agents. However, existing MoA systems often rely on static routers that do not fully capture…

Computation and Language · Computer Science 2026-05-20 Rui Chu

This paper introduces a reinforcement learning framework that enables controllable and diverse player behaviors without relying on human gameplay data. Existing approaches often require large-scale player trajectories, train separate models…

Machine Learning · Computer Science 2025-12-12 Atahan Cilan , Atay Özgövde