English
Related papers

Related papers: Training LLMs for Multi-Step Tool Orchestration wi…

200 papers

Reinforcement learning (RL) enhanced large language models (LLMs), particularly exemplified by DeepSeek-R1, have exhibited outstanding performance. Despite the effectiveness in improving LLM capabilities, its implementation remains highly…

Computation and Language · Computer Science 2025-02-25 Shuhe Wang , Shengyu Zhang , Jie Zhang , Runyi Hu , Xiaoya Li , Tianwei Zhang , Jiwei Li , Fei Wu , Guoyin Wang , Eduard Hovy

Recent curriculum techniques in the post-training stage of LLMs have been empirically observed to outperform non-curriculum approaches in improving reasoning performance, yet a principled understanding of their effectiveness and limitations…

Machine Learning · Computer Science 2026-05-05 Dake Bu , Wei Huang , Andi Han , Atsushi Nitanda , Hau-San Wong , Qingfu Zhang , Taiji Suzuki

Large language models (LLMs) deployed as agents solve user-specified tasks over multiple steps while keeping the required manual engagement to a minimum. Crucially, such LLMs need to ground their generations in any feedback obtained to…

Computation and Language · Computer Science 2025-02-19 Jonas Gehring , Kunhao Zheng , Jade Copet , Vegard Mella , Quentin Carbonneaux , Taco Cohen , Gabriel Synnaeve

Single-task RL agents are typically trained under a fixed reward function, which limits their robustness to reward misspecification and their ability to adapt to changing preferences. We introduce Reward-Conditioned Reinforcement Learning…

Machine Learning · Computer Science 2026-05-20 Michal Nauman , Marek Cygan , Pieter Abbeel

While recent Large Language Models (LLMs) have proven useful in answering user queries, they are prone to hallucination, and their responses often lack credibility due to missing references to reliable sources. An intuitive solution to…

Computation and Language · Computer Science 2024-09-04 Chengyu Huang , Zeqiu Wu , Yushi Hu , Wenya Wang

Large Language Models (LLMs) are prone to hallucination, especially during multi-hop and reasoning-intensive tasks such as mathematical problem solving. While Outcome Reward Models verify only final answers, Process Reward Models (PRMs)…

Computation and Language · Computer Science 2025-05-27 Tej Deep Pala , Panshul Sharma , Amir Zadeh , Chuan Li , Soujanya Poria

Online matching problems arise in many complex systems, from cloud services and online marketplaces to organ exchange networks, where timely, principled decisions are critical for maintaining high system performance. Traditional heuristics…

Machine Learning · Statistics 2025-10-09 Chiara Mignacco , Matthieu Jonckheere , Gilles Stoltz

A central belief in scaling reinforcement learning with verifiable rewards for instruction following (IF) tasks is that, a diverse mixture of verifiable hard and unverifiable soft constraints is essential for generalizing to unseen…

Machine Learning · Computer Science 2026-01-14 Yirong Zeng , Yufei Liu , Xiao Ding , Yutai Hou , Yuxian Wang , Haonan Song , Wu Ning , Dandan Tu , Qixun Zhang , Bibo Cai , Yuxiang He , Ting Liu

Recent methodologies in LLM self-training mostly rely on LLM generating responses and filtering those with correct output answers as training data. This approach often yields a low-quality fine-tuning training set (e.g., incorrect plans or…

Computation and Language · Computer Science 2024-11-19 Dan Zhang , Sining Zhoubian , Ziniu Hu , Yisong Yue , Yuxiao Dong , Jie Tang

Large language models (LLMs) have advanced significantly in code generation, yet their ability to follow complex programming instructions with layered and diverse constraints remains underexplored. Existing benchmarks often prioritize…

Software Engineering · Computer Science 2025-07-02 Guoliang Duan , Mingwei Liu , Yanlin Wang , Chong Wang , Xin Peng , Zibin Zheng

Reinforcement learning (RL) holds significant promise for training LLM agents to handle complex, goal-oriented tasks that require multi-step interactions with external environments. However, a critical challenge when applying RL to these…

Computation and Language · Computer Science 2025-05-28 Hanlin Wang , Chak Tou Leong , Jiashuo Wang , Jian Wang , Wenjie Li

In model-based reinforcement learning (MBRL), most algorithms rely on simulating trajectories from one-step dynamics models learned on data. A critical challenge of this approach is the compounding of one-step prediction errors as length of…

Machine Learning · Computer Science 2023-10-12 Abdelhakim Benechehab , Giuseppe Paolo , Albert Thomas , Maurizio Filippone , Balázs Kégl

LLM agents operating over massive, dynamic tool libraries rely on effective retrieval, yet standard single-shot dense retrievers struggle with complex requests. These failures primarily stem from the disconnect between abstract user goals…

Computation and Language · Computer Science 2026-01-13 Wei Fang , James Glass

When applying reinforcement learning (RL) to a new problem, reward engineering is a necessary, but often difficult and error-prone task a system designer has to face. To avoid this step, we propose LR4GPM, a novel (deep) RL method that can…

Machine Learning · Computer Science 2023-03-17 Junqi Qian , Paul Weng , Chenmien Tan

Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to achieve remarkable reasoning in domains like mathematics and coding, where verifiable rewards provide clear signals. However, extending this paradigm to financial…

Artificial Intelligence · Computer Science 2026-01-09 Rui Sun , Yifan Sun , Sheng Xu , Li Zhao , Jing Li , Daxin Jiang , Cheng Hua , Zuo Bai

Recent advancements in tool learning have enabled large language models (LLMs) to integrate external tools, enhancing their task performance by expanding their knowledge boundaries. However, relying on tools often introduces tradeoffs…

Computation and Language · Computer Science 2025-03-11 Hongshen Xu , Zihan Wang , Zichen Zhu , Lei Pan , Xingyu Chen , Lu Chen , Kai Yu

From a first-principles perspective, it may seem odd that the strongest results in foundation model fine-tuning (FT) are achieved via a relatively complex, two-stage training procedure. Specifically, one first trains a reward model (RM) on…

Machine Learning · Computer Science 2025-10-20 Gokul Swamy , Sanjiban Choudhury , Wen Sun , Zhiwei Steven Wu , J. Andrew Bagnell

Reinforcement Learning (RL) is a promising approach for solving various control, optimization, and sequential decision making tasks. However, designing reward functions for complex tasks (e.g., with multiple objectives and safety…

Artificial Intelligence · Computer Science 2021-07-23 Xuan Zhao , Marcos Campos

Recent advancements in code generation have shown remarkable success across software domains, yet hardware description languages (HDLs) such as Verilog remain underexplored due to their concurrency semantics, syntactic rigidity, and…

Machine Learning · Computer Science 2025-08-27 Fu Teng , Miao Pan , Xuhong Zhang , Zhezhi He , Yiyao Yang , Xinyi Chai , Mengnan Qi , Liqiang Lu , Jianwei Yin

Although LLMs exhibit strong reasoning capabilities, existing training methods largely depend on outcome-based feedback, which can produce correct answers with flawed reasoning. Prior work introduces supervision on intermediate steps but…

Computation and Language · Computer Science 2026-01-30 Jundong Xu , Hao Fei , Huichi Zhou , Xin Quan , Qijun Huang , Shengqiong Wu , William Yang Wang , Mong-Li Lee , Wynne Hsu