English
Related papers

Related papers: Epistemic Gain, Aleatoric Cost: Uncertainty Decomp…

200 papers

Exploration in environments with sparse rewards is difficult for artificial agents. Curiosity driven learning -- using feed-forward prediction errors as intrinsic rewards -- has achieved some success in these scenarios, but fails when faced…

Machine Learning · Computer Science 2024-07-08 Augustine N. Mavor-Parker , Kimberly A. Young , Caswell Barry , Lewis D. Griffin

Multi-agent reinforcement learning (MARL) has witnessed significant progress with the development of value function factorization methods. It allows optimizing a joint action-value function through the maximization of factorized per-agent…

Multiagent Systems · Computer Science 2023-05-05 Hanhan Zhou , Tian Lan , Vaneet Aggarwal

Multi-agent systems built on large language models have shown strong performance on complex reasoning tasks, yet most work focuses on agent roles and orchestration while treating inter-agent communication as a fixed interface. Latent…

Artificial Intelligence · Computer Science 2026-04-24 Ye Yu , Heming Liu , Haibo Jin , Xiaopeng Yuan , Peng Kuang , Haohan Wang

The overall predictive uncertainty of a trained predictor can be decomposed into separate contributions due to epistemic and aleatoric uncertainty. Under a Bayesian formulation, assuming a well-specified model, the two contributions can be…

Machine Learning · Computer Science 2021-10-22 Sharu Theresa Jose , Sangwoo Park , Osvaldo Simeone

Multi-agent systems (MAS) often achieve higher reasoning accuracy than single models, but their reliance on repeated debates across agents makes them computationally expensive. We introduce SMAGDi, a distillation framework that transfers…

Artificial Intelligence · Computer Science 2025-11-11 Aayush Aluru , Myra Malik , Samarth Patankar , Spencer Kim , Kevin Zhu , Sean O'Brien , Vasu Sharma

Understanding the internal thinking process of Large Language Models (LLMs) and the cause of hallucinations remains a key challenge. To this end, we introduce latent debate, a novel framework for interpreting model predictions through the…

Computation and Language · Computer Science 2026-02-03 Lihu Chen , Xiang Yin , Francesca Toni

Large Reasoning Models (LRMs) face two fundamental limitations: excessive token consumption when overanalyzing simple information processing tasks, and inability to access up-to-date knowledge beyond their training data. We introduce MARS…

Artificial Intelligence · Computer Science 2026-02-03 Guoxin Chen , Zile Qiao , Wenqing Wang , Donglei Yu , Xuanzhong Chen , Hao Sun , Minpeng Liao , Kai Fan , Yong Jiang , Penguin Xie , Wayne Xin Zhao , Ruihua Song , Fei Huang

LLM-as-Judge has emerged as a scalable alternative to human evaluation, enabling large language models (LLMs) to provide reward signals in trainings. While recent work has explored multi-agent extensions such as multi-agent debate and…

Artificial Intelligence · Computer Science 2025-09-19 Chiyu Ma , Enpei Zhang , Yilun Zhao , Wenjun Liu , Yaning Jia , Peijun Qing , Lin Shi , Arman Cohan , Yujun Yan , Soroush Vosoughi

Large Language Models (LLMs) are being increasingly used as autonomous agents in complex reasoning tasks, opening the niche for dialectical interactions. However, Multi-Agent systems implemented with systematically unconstrained systems…

Artificial Intelligence · Computer Science 2026-03-31 Jakub Masłowski , Jarosław A. Chudziak

Multi-agent reinforcement learning (MARL) provides a promising paradigm for coordinating multi-agent systems (MAS). However, most existing methods rely on restrictive assumptions, such as a fixed number of agents and fully synchronous…

Multiagent Systems · Computer Science 2026-02-17 Yexin Li , Jinjin Guo , Haoyu Zhang , Yuhan Zhao , Yiwen Sun , Zihao Jiao

In multi-agent debate (MAD) systems, performance gains are often reported; however, because the debate protocol (e.g., number of agents, rounds, and aggregation rule) is typically held fixed while model-related factors vary, it is difficult…

Multiagent Systems · Computer Science 2026-04-01 Ramtin Zargari Marandi

When people reason about cause and effect, they often consider many competing "what if" scenarios before deciding which explanation fits best. Analogously, advanced language models capable of causal inference can consider multiple…

Machine Learning · Computer Science 2026-03-10 Finn G. Vamosi , Nils D. Forkert

Multiagent collaboration has emerged as a promising framework for enhancing the reasoning capabilities of large language models (LLMs). Despite improvements in reasoning, the approach introduces substantial computational overhead resulting…

Artificial Intelligence · Computer Science 2025-05-21 Sugyeong Eo , Hyeonseok Moon , Evelyn Hayoon Zi , Chanjun Park , Heuiseok Lim

It is critical that the models pay attention not only to accuracy but also to the certainty of prediction. Uncertain predictions of deep models caused by noisy data raise significant concerns in trustworthy AI areas. To explore and handle…

Machine Learning · Computer Science 2023-03-30 Wei Wei , Jiahuan Zhou , Hongze Li , Ying Wu

Bias in large language models (LLMs) remains a persistent challenge, manifesting in stereotyping and unfair treatment across social groups. While prior research has primarily focused on individual models, the rise of multi-agent systems…

Multiagent Systems · Computer Science 2025-10-14 Thi-Nhung Nguyen , Linhao Luo , Thuy-Trang Vu , Dinh Phung

A challenge in reinforcement learning (RL) is minimizing the cost of sampling associated with exploration. Distributed exploration reduces sampling complexity in multi-agent RL (MARL). We investigate the benefits to performance in MARL when…

Machine Learning · Computer Science 2022-05-03 Justin Lidard , Udari Madhushani , Naomi Ehrich Leonard

Large language models (LLMs) are highly vulnerable to input confirmation bias. When a prompt implies a preferred answer, models often reinforce that bias rather than explore alternatives. This phenomenon remains underexplored, yet it is…

Computation and Language · Computer Science 2025-12-30 Hazel Kim , Philip Torr

Large language model (LLM) agents are increasingly deployed in structured biomedical data environments, yet they often produce fluent but overconfident outputs when reasoning over complex multi-table data. We introduce an uncertainty-aware…

Cooperative multi-agent reinforcement learning (MARL) requires agents to discover joint strategies in a combinatorially large state-action space, yet effective coordination configurations are exceedingly rare. Intrinsic motivation, which…

Multiagent Systems · Computer Science 2026-05-05 Dahyun Oh , Minhyuk Yoon , H. Jin Kim

Automatic Multi-Agent Systems (MAS) generation has emerged as a promising paradigm for solving complex reasoning tasks. However, existing frameworks are fundamentally bottlenecked when applied to knowledge-intensive domains (e.g.,…

Artificial Intelligence · Computer Science 2026-03-24 Hehai Lin , Yu Yan , Zixuan Wang , Bo Xu , Sudong Wang , Weiquan Huang , Ruochen Zhao , Minzhi Li , Chengwei Qin