Papers with reinforcement learning (RL)
DecIF: Improving Instruction-Following through Decomposition (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to obtain high-quality instruction-following data rely heavily on existing documents and existing methods. |
| Approach: | They propose a data synthesis framework, DecIF, which automatically generates accurate and diverse instruction-following data from scratch for supervised fine-tuning and reinforcement learning. |
| Outcome: | Extensive experiments show that the proposed framework can synthesize accurate instruction-following data for both SFT and RL paradigms compared to baselines. |
D2Plan: Dual-Agent Dynamic Global Planning for Complex Retrieval-Augmented Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in reinforcement learning (RL) have empowered Large Language Models (LLMs) with the capability to perform autonomous retrieval during reasoning tasks. |
| Approach: | They propose a "D2Plan" paradigm for retrieval-augmented reasoning that integrates a 'Reasoner' and a'Purifier' |
| Outcome: | Experiments show that the proposed paradigm improves on QA benchmarks. |
RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning (2022.emnlp-main)
Copied to clipboard
Mingkai Deng, Jianyu Wang, Cheng-Ping Hsieh, Yihan Wang, Han Guo, Tianmin Shu, Meng Song, Eric Xing, Zhiting Hu
| Challenge: | Existing methods for finding the optimal prompt for a task are difficult to optimize. |
| Approach: | They propose an efficient discrete prompt optimization approach with reinforcement learning that generates the optimal discrete stimulus after training with reward. |
| Outcome: | The proposed approach is based on a parameter-efficient policy network that generates the optimal discrete prompt after training with reward. |
WebWISE: Unlocking Web Interface Control for LLMs via Sequential Exploration (2024.findings-naacl)
Copied to clipboard
| Challenge: | Prior work to control software has used reinforcement learning (RL), requiring many demonstrations and trials to learn simple interaction tasks. |
| Approach: | They propose a Large Language Model to automatically perform web software tasks using click, scroll, and text in- put operations using filtered Document Object Models as observations. |
| Outcome: | The proposed method performs better on the MiniWob++ benchmark with only one in-context example. |
Reasoning Structure Matters for Safety Alignment of Reasoning Models (2026.acl-long)
Copied to clipboard
| Challenge: | Large reasoning models (LRMs) achieve strong performance on complex reasoning tasks but often generate harmful responses to malicious user queries. |
| Approach: | They propose a method that alters the reasoning structure of large reasoning models to achieve effective safety alignment by supervised fine-tuning. |
| Outcome: | The proposed method is practical and generalizable, requiring no complex training or reward design. |
Object-oriented Neural Programming (OONP) for Document Understanding (P18-1)
Copied to clipboard
| Challenge: | Object-oriented Neural Programming (OONP) is a framework for semantically parsing documents in domains. |
| Approach: | They propose a framework for semantically parsing documents in specific domains using OONP . OOPN parsers use a rich family of operations to represent the semantics of the document . |
| Outcome: | The proposed framework can learn to handle fairly complicated ontology with training data of modest sizes. |
A Reinforcement Learning Framework for Robust and Secure LLM Watermarking (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing watermarking algorithms rely on heuristic green/red token lists . however, these lists are inconsistent and can be compromised . |
| Approach: | They propose a framework for robust and secure LLM watermarking using reinforcement learning. |
| Outcome: | The proposed method achieves state-of-the-art trade-off across all criteria with notable improvements in resistance to spoofing attacks without degrading other criteria. |
A Study of Reinforcement Learning for Neural Machine Translation (D18-1)
Copied to clipboard
| Challenge: | Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation systems. |
| Approach: | They propose to leverage reinforcement learning to boost the performance of NMT systems trained with monolingual data. |
| Outcome: | The proposed method achieves competitive results on translation tasks in English-German, Chinese-English and English-English systems. |
Phrase-Level Action Reinforcement Learning for Neural Dialog Response Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for dialog agent training lack a robust action space for entangled information, which can cause bias and deviate from natural human language. |
| Approach: | They propose phrase-level action reinforcement learning which allows the model to alter the sentence structure and content with the sequential action selection. |
| Outcome: | The proposed model achieves competitive results with state-of-the-art models on the MultiWOZ dataset, indicating that it is effective for solving task-oriented dialogs. |
Efficient Integration of External Knowledge to LLM-based World Models via Retrieval-Augmented Generation and Reinforcement Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing attempts to enhance LLM-based world models through prompting or fine-tuning approaches are either requiring human knowledge or computationally extensive. |
| Approach: | They propose a framework that leverages retrieval-augmented generation to integrate external knowledge to LLM-based world models. |
| Outcome: | The proposed framework outperforms baseline models and exhibits strong generalizability. |
Reinforcement Learning on Pre-Training Data (2026.acl-long)
Copied to clipboard
Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang
| Challenge: | Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings. |
| Approach: | They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data. |
| Outcome: | Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base. |
An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation (D19-1)
Copied to clipboard
| Challenge: | Existing methods to generate paraphrases are not trivial and often fail in practice. |
| Approach: | They propose to use imitation learning to boost the performance of generating paraphrases by using a pointer-generator model. |
| Outcome: | The proposed model outperforms the state-of-the-art methods on the benchmark datasets. |
Can GRPO Boost Complex Multimodal Table Understanding? (2025.emnlp-main)
Copied to clipboard
Xiaoqiang Kang, Shengen Wu, Zimu Wang, Yilin Liu, Xiaobo Jin, Kaizhu Huang, Wei Wang, Yutao Yue, Xiaowei Huang, Qiufeng Wang
| Challenge: | Existing table understanding methods struggle with low initialization accuracy and coarse rewards in tabular contexts. |
| Approach: | They propose a three-stage RL framework that enhances multimodal table understanding through: (1) Warm-up that prompts initial perception and reasoning capabilities; (2) Perception Alignment GRPO (PA-GRPO); (3) Hint-Completion GR PO (HC-GRP); |
| Outcome: | The proposed framework outperforms existing models on held-in and held-out datasets, outperforming SFT and GRPO largely. |
Reflective RAG: Self-Evaluation Driven Strategy Optimization in Agentic Retrieval-Augmented Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent agentic RAG systems lack the capacity to evaluate the utility of retrieved information, leading to brittle reasoning and suboptimal decision-making. |
| Approach: | They propose a framework that integrates self-evaluation to dynamically optimize retrieval and generation strategy. |
| Outcome: | The proposed framework outperforms strong agentic baselines on five knowledge-intensive QA benchmarks and improves training stability and generalization to multi-hop reasoning tasks. |
Check Your Work: Structured Checklist Feedback for Improving Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models have been driven by verifiable feedback in deterministic domains like mathematics and code. |
| Approach: | They propose to decompose granular, prompt-specific checklists into a scalar reward and use them to transform them into skalar rewards. |
| Outcome: | The proposed approach yields an 11.8% win-rate improvement on AlpacaEval 2.0 using Qwen3-8B, outperforming holistic reward models and existing checklist baselines. |
From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation (2024.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) often output text at a native level of speech, making them difficult to use for contexts where end-users are not fully proficient. |
| Approach: | They propose a framework to control the difficulty level of text generated by Large Language Models for contexts where end-users are not fully proficient. |
| Outcome: | The proposed framework surpasses GPT-4 and other models at fraction of the cost. |
Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models (2025.emnlp-main)
Copied to clipboard
Kaiyan Chang, Yonghao Shi, Chenglong Wang, Hang Zhou, Chi Hu, Xiaoqian Liu, Yingfeng Luo, Yuan Ge, Tong Xiao, JingBo Zhu
| Challenge: | Recent training-based TTS methods, such as continued reinforcement learning, have surged in popularity, while training-free TTS approaches are gradually fading from prominence. |
| Approach: | They propose a fine-grained sequential scaling method guided by process verification that integrates training-free TTS methods with other classical parallel scaling methods at the step level. |
| Outcome: | Experiments on five instruction-tuned large language models (LLMs) show that training-free TTS methods can extend reasoning performance boundaries. |
Beyond the Context Window: Scaling Agentic RL via End-to-end Optimized Context Compression (2026.acl-long)
Copied to clipboard
| Challenge: | Existing reinforcement learning pipelines suffer from degraded instruction following, excessive rollout costs, and strict context limits. |
| Approach: | They propose a reinforcement learning (RL) fine-tuning of large language model (LLM) agents for long-horizon multi-turn tool use where context length quickly becomes a bottleneck. |
| Outcome: | The proposed framework improves the success rate while maintaining the same or even lower working context length compared to baselines. |
GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have demonstrated that supervised fine-tuning and reinforcement learning are effective in integrating knowledge injection with robust generalization. |
| Approach: | They propose a unified post-training framework that addresses intrinsic limitations of supervised fine-tuning and reinforcement learning. |
| Outcome: | The proposed framework surpasses SFT-based methods and yields policies that integrate more smoothly with subsequent RL training. |
TPS-Bench: Evaluating AI Agents’ Tool Planning & Scheduling Abilities in Compounding Tasks (2026.acl-long)
Copied to clipboard
| Challenge: | Large language model (LLM) agents have demonstrated strong problem-solving competence across domains like research and coding. |
| Approach: | They propose to use a tool repository to analyze the ability of large language model agents to solve complex problems. |
| Outcome: | The proposed model outperforms open-source and closed-source models in task completion rate and efficiency. |