English
Related papers

Related papers: TRACE: Capability-Targeted Agentic Training

200 papers

Recent advances in large language models (LLMs) have enabled the development of autonomous agents capable of complex reasoning and multi-step problem solving. However, these agents struggle to adapt to specialized environments and do not…

Machine Learning · Computer Science 2026-04-02 Marc-Antoine Allard , Arnaud Teinturier , Victor Xing , Gautier Viaud

Autonomous agents powered by large language models (LLMs) have the potential to enhance human capabilities, assisting with digital tasks from sending emails to performing data analysis. The abilities of existing LLMs at such tasks are often…

Machine Learning · Computer Science 2025-01-22 Hongjin Su , Ruoxi Sun , Jinsung Yoon , Pengcheng Yin , Tao Yu , Sercan Ö. Arık

Software issue resolution is a critical challenge in software engineering and has garnered increasing attention in recent years. With the rapid advancement of large language models (LLMs), substantial progress has been made in addressing…

In-context learning (ICL) with dynamically selected demonstrations combines the flexibility of prompting large language models (LLMs) with the ability to leverage training data to improve performance. While ICL has been highly successful…

Computation and Language · Computer Science 2025-06-17 Shivanshu Gupta , Sameer Singh , Ashish Sabharwal , Tushar Khot , Ben Bogin

Large language model agents rely on effective model context to obtain task-relevant information for decision-making. Many existing context engineering approaches primarily rely on the context generated from the past experience and retrieval…

Artificial Intelligence · Computer Science 2026-04-10 Linbo Liu , Guande Wu , Han Ding , Yawei Wang , Qiang Zhou , Yuzhe Lu , Zhichao Xu , Huan Song , Panpan Xu , Lin Lee Cheong

Training large language models (LLMs) as autonomous agents often begins with imitation learning, but it only teaches agents what to do without understanding why: agents never contrast successful actions against suboptimal alternatives and…

Artificial Intelligence · Computer Science 2026-03-10 Weize Liu , Minghui Liu , Sy-Tuyen Ho , Souradip Chakraborty , Xiyao Wang , Furong Huang

Ensembling large language models (LLMs) can effectively combine diverse strengths of different models, offering a promising approach to enhance performance across various tasks. However, existing methods typically rely on fixed weighting…

Machine Learning · Computer Science 2025-06-03 Yuqian Fu , Yuanheng Zhu , Jiajun Chai , Guojun Yin , Wei Lin , Qichao Zhang , Dongbin Zhao

While large language models (LLMs) have substantially improved Text-to-SQL generation, a pronounced gap remains between AI systems and human experts on challenging benchmarks such as BIRD-SQL. We argue this gap stems largely from the…

Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in complex reasoning and multi-turn interactions but struggle to continuously improve and adapt when deployed in new environments. One promising approach is…

Artificial Intelligence · Computer Science 2026-03-11 Jiongxiao Wang , Qiaojing Yan , Yawei Wang , Yijun Tian , Soumya Smruti Mishra , Zhichao Xu , Megha Gandhi , Panpan Xu , Lin Lee Cheong

With the rapid development of LLM-based agents, there is a growing trend to incorporate agent-specific data into the pre-training stage of LLMs, aiming to better align LLMs with real-world autonomous task execution. However, current…

Artificial Intelligence · Computer Science 2025-10-29 Jiarui Qin , Yunjia Xi , Junjie Huang , Renting Rui , Di Yin , Weiwen Liu , Yong Yu , Weinan Zhang , Xing Sun

Large Language Model (LLM) agents have demonstrated remarkable generalization capabilities across multi-domain tasks. Existing agent tuning approaches typically employ supervised finetuning on entire expert trajectories. However,…

Computation and Language · Computer Science 2025-06-06 Zhixun Chen , Ming Li , Yuxuan Huang , Yali Du , Meng Fang , Tianyi Zhou

Agentic Reinforcement Learning (RL) has empowered Large Language Models (LLMs) to utilize tools like Python interpreters for complex problem-solving. However, for parameter-constrained models (e.g., 4B--7B), the exploration phase is often…

Machine Learning · Computer Science 2026-01-22 Tianshi Xu , Yuteng Chen , Meng Li

Large language models (LLMs) have demonstrated remarkable capabilities across a range of text-generation tasks. However, LLMs still struggle with problems requiring multi-step decision-making and environmental feedback, such as online…

Artificial Intelligence · Computer Science 2025-02-18 Zhenfang Chen , Delin Chen , Rui Sun , Wenjun Liu , Chuang Gan

Large Language Models (LLMs) have shown superior performance in various applications and fields. To achieve better performance on specialized domains such as law and advertisement, LLMs are often continue pre-trained on in-domain data.…

Computation and Language · Computer Science 2024-06-25 Xiao Liang , Xinyu Hu , Simiao Zuo , Yeyun Gong , Qiang Lou , Yi Liu , Shao-Lun Huang , Jian Jiao

Reinforcement Learning (RL) has traditionally focused on training specialized agents to optimize predefined reward functions within narrowly defined environments. However, the advent of powerful Large Language Models (LLMs) and increasingly…

Artificial Intelligence · Computer Science 2026-05-18 Fangming Cui , Ruixiao Zhu , Cheng Fang , Sunan Li , Jiahong Li

We study what actually works and what doesn't for training large language models as agents via multi-turn reinforcement learning. Despite rapid progress, existing frameworks and definitions are fragmented, and there is no systematic…

Machine Learning · Computer Science 2025-12-09 Ruiyi Wang , Prithviraj Ammanabrolu

The rapid shift from stateless large language models (LLMs) to autonomous, goal-driven agents raises a central question: When is agentic AI truly necessary? While agents enable multi-step reasoning, persistent memory, and tool…

Artificial Intelligence · Computer Science 2025-12-03 Shubhi Asthana , Bing Zhang , Chad DeLuca , Ruchi Mahindru , Hima Patel

Resolving real-world software engineering (SWE) issues with autonomous agents requires complex, long-horizon reasoning. Current pipelines are bottlenecked by unoptimized demonstration data, sparse execution rewards, and computationally…

Software Engineering · Computer Science 2026-04-17 Hao Han , Jin Xie , Xuehao Ma , Weiquan Zhu , Ziyao Zhang , ZhiLiang Long , Hongkai Chen , Qingwen Ye

Recent advances in reinforcement learning for code generation have made robust environments essential to prevent reward hacking. As LLMs increasingly serve as evaluators in code-based RL, their ability to detect reward hacking remains…

Software Engineering · Computer Science 2026-01-29 Darshan Deshpande , Anand Kannappan , Rebecca Qian

Evaluating open-ended outputs from large language models (LLMs) remains challenging due to the absence of ground truth. Existing metrics rely on final-answer accuracy or surface-level statistics, leaving the reasoning process itself…

Artificial Intelligence · Computer Science 2026-05-29 Yundong Kim , Heyoung Yang