paper-with-me

홈 › Papers

Harmonizing Dense and Sparse Signals in Multi-turn RL: Dual-Horizon Credit Assignment for Industrial Sales Agents

2026-03-02 · Haojin Yang, Ai Jian, Xinyue Huang, Yiwei Wang, Weipeng Zhang, Ke Zeng, Xunliang Cai, Jingqing Ruan arxiv

Optimizing large language models for industrial sales requires balancing long-term commercial objectives (e.g., conversion rate) with immediate linguistic constraints such as fluency and compliance. Conventional reinforcement learning often merges these heterogeneous goals into a single reward, causing high-magnitude session-level rewards to overwhelm subtler turn-level signals, which leads to unstable training or reward hacking. To address this issue, we propose Dual-Horizon Credit Assignment (DuCA), a framework that disentangles optimization across time scales. Its core, Horizon-Independent Advantage Normalization (HIAN), separately normalizes advantages from turn-level and session-level rewards before fusion, ensuring balanced gradient contributions from both immediate and long-term objectives to the policy update. Extensive experiments with a high-fidelity user simulator show DuCA outperforms the state-of-the-art GRPO baseline, achieving a 6.82% relative improvement in conversion rate, reducing inter-sentence repetition by 82.28%, and lowering identity detection rate by 27.35%, indicating a substantial improvement for an industrial sales scenario that effectively balances the dual demands of strategic performance and naturalistic language generation.

📄 PDF Abstract BibTeX arXiv:2603.01481

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

MIA 2022 Shared Task Submission: Leveraging Entity Representations, Dense-Sparse Hybrids, and Fusion-in-Decoder for Cross-Lingual Question Answering

2022-07-05 · NAACL (MIA) 2022 7 · Zhucheng Tu, Sarguna Janani Padmanabhan

We describe our two-stage system for the Multilingual Information Access (MIA) 2022 Shared Task on Cross-Lingual Open-Retrieval Question Answering. The first stage consists of multilingual passage retrieval with a hybrid…

Cross-Lingual Question AnsweringDecoderLanguage ModelingLanguage Modelling+3

SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregation

2026-03-17 · Long Li, Zhijian Zhou, Jiangxuan Long, Peiyang Liu 외 arxiv

Agentic Reinforcement Learning (RL) shows promise for complex tasks, but Text-to-SQL remains mostly restricted to single-turn paradigms. A primary bottleneck is the credit assignment problem. In traditional paradigms, re…

Reinforcement Learning

SigFormer: Sparse Signal-Guided Transformer for Multi-Modal Human Action Segmentation

2023-11-29 · Qi Liu, Xinchen Liu, Kun Liu, Xiaoyan Gu 외

Multi-modal human action segmentation is a critical and challenging task with a wide range of applications. Nowadays, the majority of approaches concentrate on the fusion of dense signals (i.e., RGB, optical flow, and de…

Action SegmentationOptical Flow Estimationvalid

You Only Acquire Sparse-channel (YOAS): A Unified Framework for Dense-channel EEG Generation

2024-06-21 · Hongyu Chen, Weiming Zeng, Luhui Cai, Lei Wang 외

High-precision acquisition of dense-channel electroencephalogram (EEG) signals is often impeded by the costliness and lack of portability of equipment. In contrast, generating dense-channel EEG signals effectively from s…

EEGElectroencephalogram (EEG)

RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents

2026-07-06 · Qiang Liu, Taian Guo, Ruizhi Qiao, Xing Sun arxiv

Reinforcement learning holds significant potential for training large language models (LLMs) to handle multi-turn interactive tasks. However, in long-horizon, multi-turn tasks characterized by sparse outcome rewards, dir…

Reinforcement Learning