English
Related papers

Related papers: SQL-ASTRA: Alleviating Sparse Feedback in Agentic …

200 papers

Reinforcement Learning (RL) has emerged as a mainstream paradigm for training Mobile GUI Agents, yet it struggles with the temporal credit assignment problem inherent in long-horizon tasks. A primary challenge lies in the trade-off between…

Several studies have employed reinforcement learning (RL) to address the challenges of regional adaptive traffic signal control (ATSC) and achieved promising results. In this field, existing research predominantly adopts multi-agent…

Artificial Intelligence · Computer Science 2026-01-14 Qiang Li , Ningjing Zeng , Lina Yu

There is a surge of interest in using formal languages such as Linear Temporal Logic (LTL) to precisely and succinctly specify complex tasks and derive reward functions for Reinforcement Learning (RL). However, existing methods often assign…

Robotics · Computer Science 2025-05-20 Minjae Kwon , Ingy ElSayed-Aly , Lu Feng

Automatic speech recognition (ASR) is a core component of human--computer interaction and an increasingly important front-end for LLM-based assistants and agents. However, most current ASR systems still follow a single-pass paradigm, which…

Artificial Intelligence · Computer Science 2026-05-29 Zixuan Jiang , Yanqiao Zhu , Peng Wang , Qinyuan Chen , Xinjian Zhao , Xipeng Qiu , Wupeng Wang , Zhifu Gao , Xiangang Li , Kai Yu , Xie Chen

Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) - where models iteratively reason, generate code, and verify through execution - remains challenging for existing reinforcement learning (RL) approaches.…

Machine Learning · Computer Science 2026-04-21 Yifeng Ding , Hung Le , Songyang Han , Kangrui Ruan , Zhenghui Jin , Varun Kumar , Zijian Wang , Anoop Deoras

Time series modeling is crucial for many applications, however, it faces challenges such as complex spatio-temporal dependencies and distribution shifts in learning from historical context to predict task-specific outcomes. To address these…

Artificial Intelligence · Computer Science 2024-08-28 Chidaksh Ravuru , Sagar Srinivas Sakhinana , Venkataramana Runkana

Multi-step agentic reinforcement learning benefits from fine-grained credit assignment, yet existing approaches offer limited options: critic-free methods like GRPO assign a uniform advantage to every action in a trajectory, while learned…

Machine Learning · Computer Science 2026-04-14 Tao Wang , Suhang Zheng , Xiaoxiao Xu

In multi-agent environments, agents often struggle to learn optimal policies due to sparse or delayed global rewards, particularly in long-horizon tasks where it is challenging to evaluate actions at intermediate time steps. We introduce…

Multiagent Systems · Computer Science 2024-12-20 Aditya Kapoor , Sushant Swamy , Kale-ab Tessera , Mayank Baranwal , Mingfei Sun , Harshad Khadilkar , Stefano V. Albrecht

Sparse-reward reinforcement learning (RL) remains fundamentally hard: without structure, any agent needs $\Omega(|\mathcal{S}||\mathcal{A}|/p)$ samples to recover rewards. We introduce Policy-Aware Matrix Completion (PAMC) as a first…

Machine Learning · Computer Science 2025-09-10 Ibne Farabi Shihab , Sanjeda Akter , Anuj Sharma

Advances in large language models (LLMs) are driving a shift toward using reinforcement learning (RL) to train agents from iterative, multi-turn interactions across tasks. However, multi-turn RL remains challenging as rewards are often…

Artificial Intelligence · Computer Science 2026-05-20 Aladin Djuhera , Swanand Ravindra Kadhe , Farhan Ahmed , Syed Zawad , Heiko Ludwig , Holger Boche

Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse outcome-based reward for training. Such feedback fails to…

Artificial Intelligence · Computer Science 2026-04-29 Kaixuan Fan , Kaituo Feng , Manyuan Zhang , Tianshuo Peng , Zhixun Li , Yilei Jiang , Shuang Chen , Peng Pei , Xunliang Cai , Xiangyu Yue

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks. With the paradigm shift toward self-evolving agentic learning, models are increasingly expected…

Artificial Intelligence · Computer Science 2026-04-21 Xinshun Feng , Xinhao Song , Lijun Li , Gongshen Liu , Jing Shao

In Automatic Speech Recognition (ASR) systems, a recurring obstacle is the generation of narrowly focused output distributions. This phenomenon emerges as a side effect of Connectionist Temporal Classification (CTC), a robust sequence…

Audio and Speech Processing · Electrical Eng. & Systems 2024-03-19 SooHwan Eom , Eunseop Yoon , Hee Suk Yoon , Chanwoo Kim , Mark Hasegawa-Johnson , Chang D. Yoo

Rewards serve as a measure of user satisfaction and act as a limiting factor in interactive recommender systems. In this research, we focus on the problem of learning to reward (LTR), which is fundamental to reinforcement learning. Previous…

Machine Learning · Computer Science 2023-10-31 Jialin Liu , Xinyan Su , Zeyu He , Xiangyu Zhao , Jun Li

Tool-Integrated Reasoning (TIR) enables large language models (LLMs) to solve complex tasks by interacting with external tools, yet existing approaches depend on high-quality synthesized trajectories selected by scoring functions and sparse…

Artificial Intelligence · Computer Science 2026-02-02 Siyu Gong , Linan Yue , Weibo Gao , Fangzhou Yao , Shimin Di , Lei Feng , Min-Ling Zhang

Multi-turn Text-to-SQL aims to translate a user's conversational utterances into executable SQL while preserving dialogue coherence and grounding to the target schema. However, most existing systems only regard this task as a simple text…

Computation and Language · Computer Science 2026-04-21 Taicheng Guo , Hai Wang , ChaoChun Liu , Mohsen Golalikhani , Xin Chen , Xiangliang Zhang , Chandan K. Reddy

Adversarial inverse reinforcement learning (IRL) for multi-agent task allocation (MATA) is challenged by non-stationary interactions and high-dimensional coordination. Unconstrained reward inference in these settings often leads to high…

Machine Learning · Computer Science 2026-02-10 Huilin Yin , Zhikun Yang , Linchuan Zhang , Daniel Watzenig

Agentic retrieval-augmented generation (RAG) systems enable large language models (LLMs) to solve complex tasks through multi-step interaction with external retrieval tools. However, such multi-step interaction often involves redundant…

Artificial Intelligence · Computer Science 2026-04-21 Jingbo Sun , Wenyue Chong , Songjun Tu , Qichao Zhang , Yaocheng Zhang , Jiajun Chai , Xiaohan Wang , Wei Lin , Guojun Yin , Dongbin Zhao

Entity recognition in Automatic Speech Recognition (ASR) is challenging for rare and domain-specific terms. In domains such as finance, medicine, and air traffic control, these errors are costly. If the entities are entirely absent from the…

Computation and Language · Computer Science 2026-03-18 Abhishek Kumar , Aashraya Sachdeva

Reinforcement learning can train LLM agents from sparse task rewards, but long-horizon credit assignment remains challenging: a single success-or-failure signal must be distributed across many actions. Existing methods rely on…

Artificial Intelligence · Computer Science 2026-05-20 Xiaozhe Li , Tianyi Lyu , Yang Li , Yichuan Ma , Peiji Li , Linyang Li , Qipeng Guo , Dahua Lin , Kai Chen