English
Related papers

Related papers: Agentic Critical Training

200 papers

Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this…

Artificial Intelligence · Computer Science 2025-10-08 Zhuofeng Li , Haoxiang Zhang , Seungju Han , Sheng Liu , Jianwen Xie , Yu Zhang , Yejin Choi , James Zou , Pan Lu

Reinforcement Learning (RL) significantly enhances the reasoning abilities of large language models (LLMs), yet applying it to multi-turn agentic tasks remains challenging due to the long-horizon nature of interactions and the stochasticity…

Artificial Intelligence · Computer Science 2026-04-03 Jingyue Gao , Yanjiang Guo , Xiaoshuai Chen , Jianyu Chen

Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies,…

Artificial Intelligence · Computer Science 2026-05-13 Xingyuan Hua , Sheng Yue , Ju Ren

Recently, the emergence of agentic RL has showcased that RL could also effectively improve the agentic reasoning ability of LLMs, yet the key design principles and optimal practices remain unclear. In this work, we conduct a comprehensive…

Computation and Language · Computer Science 2025-10-14 Zhaochen Yu , Ling Yang , Jiaru Zou , Shuicheng Yan , Mengdi Wang

We study predictive multilingual evaluation: estimating how well a model will perform on a task in a target language when direct benchmark results are missing. This problem is common in multilingual deployment, where evaluation coverage is…

Computation and Language · Computer Science 2026-04-13 Avni Mittal , Shanu Kumar , Sandipan Dandapat , Monojit Choudhury

Vision-Language-Action (VLA) models have emerged as a promising paradigm for robotic manipulation by leveraging pre-trained vision-language representations. However, current VLA training methods suffer from two critical limitations: poor…

Robotics · Computer Science 2026-05-25 Ruofan Jin , Zaixi Zhang

Large Language Models (LLMs) perform well in language tasks but often lack collaborative awareness and struggle to optimize global performance in multi-agent settings. We present a reinforcement learning-augmented LLM agent framework that…

Artificial Intelligence · Computer Science 2026-01-01 Dong Qiu , Duo Xu , Limengxi Yue

Actor-critic (AC) methods are widely used in reinforcement learning (RL) and benefit from the flexibility of using any policy gradient method as the actor and value-based method as the critic. The critic is usually trained by minimizing the…

Machine Learning · Computer Science 2023-11-01 Sharan Vaswani , Amirreza Kazemi , Reza Babanezhad , Nicolas Le Roux

Reinforcement Learning (RL) has emerged as a powerful paradigm for training LLM-based agents, yet remains limited by low sample efficiency, stemming not only from sparse outcome feedback but also from the agent's inability to leverage prior…

Machine Learning · Computer Science 2026-03-19 Dilxat Muhtar , Jiashun Liu , Wei Gao , Weixun Wang , Shaopan Xiong , Ju Huang , Siran Yang , Wenbo Su , Jiamang Wang , Ling Pan , Bo Zheng

Agentic methods have emerged as a powerful and autonomous paradigm that enhances reasoning, collaboration, and adaptive control, enabling systems to coordinate and independently solve complex tasks. We extend this paradigm to safety…

Artificial Intelligence · Computer Science 2025-10-30 Juan Ren , Mark Dras , Usman Naseem

Recent research on Reasoning of Large Language Models (LLMs) has sought to further enhance their performance by integrating meta-thinking -- enabling models to monitor, evaluate, and control their reasoning processes for more adaptive and…

Artificial Intelligence · Computer Science 2025-05-28 Ziyu Wan , Yunxiang Li , Xiaoyu Wen , Yan Song , Hanjing Wang , Linyi Yang , Mark Schmidt , Jun Wang , Weinan Zhang , Shuyue Hu , Ying Wen

LLM agents increasingly operate in open-ended environments spanning hundreds of sequential episodes, yet they remain largely stateless: each task is solved from scratch without converting past experience into better future behavior. The…

Computation and Language · Computer Science 2026-04-24 Wujiang Xu , Jiaojiao Han , Minghao Guo , Kai Mei , Xi Zhu , Han Zhang , Dimitris N. Metaxas

Large Language Models (LLMs) often require domain-specific fine-tuning to address targeted tasks, which risks degrading their general capabilities. Maintaining a balance between domain-specific enhancements and general model utility is a…

Computation and Language · Computer Science 2025-06-05 Jun Rao , Zepeng Lin , Xuebo Liu , Xiaopeng Ke , Lian Lian , Dong Jin , Shengjun Cheng , Jun Yu , Min Zhang

Large language models (LLMs) have shown increasing capacity at planning and executing a high-level goal in a live computer environment (e.g. MiniWoB++). To perform a task, recent works often require a model to learn from trace examples of…

Computation and Language · Computer Science 2023-10-24 Tao Li , Gang Li , Zhiwei Deng , Bryan Wang , Yang Li

Standard reinforcement learning (RL) for large language model (LLM) agents typically optimizes extrinsic rewards, prioritizing isolated task completion over continual adaptation. Consequently, agents often converge to suboptimal policies…

Artificial Intelligence · Computer Science 2026-03-31 Xiaoying Zhang , Zichen Liu , Yipeng Zhang , Xia Hu , Wenqi Shao

Large language model based agents often fail in unfamiliar environments due to premature exploitation: a tendency to act on prior knowledge before acquiring sufficient environment-specific information. We identify autonomous exploration as…

Artificial Intelligence · Computer Science 2026-05-18 Ziang Ye , Wentao Shi , Yuxin Liu , Yu Wang , Zhengzhou Cai , Yaorui Shi , Qi Gu , Xunliang Cai , Fuli Feng

Formative feedback is widely recognized as one of the most effective drivers of student learning, yet it remains difficult to implement equitably at scale. In large or low-resource courses, instructors often lack the time, staffing, and…

Computers and Society · Computer Science 2025-12-01 Chenyu Zhang , Xiaohang Luo

Researchers and practitioners have recently reframed powerful Large Language Models (LLMs) as agents, enabling them to automate complex tasks largely via the use of specialized functions. To facilitate the development of LLM agents, we…

Artificial Intelligence · Computer Science 2024-08-01 Shaokun Zhang , Jieyu Zhang , Jiale Liu , Linxin Song , Chi Wang , Ranjay Krishna , Qingyun Wu

Autonomous multi-agent systems (MAS) are useful for automating complex tasks but raise trust concerns due to risks such as miscoordination or goal misalignment. Explainability is vital for users' trust calibration, but explainable MAS face…

Artificial Intelligence · Computer Science 2025-10-30 Bálint Gyevnár , Christopher G. Lucas , Stefano V. Albrecht , Shay B. Cohen

Improving Large Language Model (LLM) agents for sequential decision-making tasks typically requires extensive task-specific knowledge engineering--custom prompts, curated examples, and specialized observation/action spaces. We investigate a…

Machine Learning · Computer Science 2025-05-20 Vishnu Sarukkai , Zhiqiang Xie , Kayvon Fatahalian