Recent advances in large language models (LLMs), such as OpenAI-o1 and
DeepSeek-R1, have demonstrated the effectiveness of test-time scaling, where
extended reasoning processes substantially enhance model performance. Despite
this, current models are constrained by limitations in handling long texts and
reinforcement learning (RL) training efficiency. To address these issues, we
propose a simple yet effective test-time scaling approach Multi-round Thinking.
This method iteratively refines model reasoning by leveraging previous answers
as prompts for subsequent rounds. Extensive experiments across multiple models,
including QwQ-32B and DeepSeek-R1, consistently show performance improvements
on various benchmarks such as AIME 2024, MATH-500, GPQA-diamond, and
LiveCodeBench. For instance, the accuracy of QwQ-32B improved from 80.3% (Round
1) to 82.1% (Round 2) on the AIME 2024 dataset, while DeepSeek-R1 showed a
similar increase from 79.7% to 82.0%. These results confirm that Multi-round
Thinking is a broadly applicable, straightforward approach to achieving stable
enhancements in model performance, underscoring its potential for future
developments in test-time scaling techniques. The key prompt: {Original
question prompt} The assistant's previous answer is:
We introduce a novel reinforcement learning algorithm (AGRO, for Any-Generation Reward Optimization) for fine-tuning large-language models. AGRO leverages the concept of generation consistency, which states that the optimal policy satisfies the notion of consistency across any possible generation of the model. We derive algorithms that find optimal solutions via the sample-based policy gradient and provide theoretical guarantees on their convergence. Our experiments demonstrate the effectiveness of AGRO in both on-policy and off-policy settings, showing improved performance on the mathematical reasoning dataset over baseline algorithms.
Large Language Models (LLMs) have shown remarkable capabilities in reasoning, exemplified by the success of OpenAI-o1 and DeepSeek-R1. However, integrating reasoning with external search processes remains challenging, especially for complex multi-hop questions requiring multiple retrieval steps. We propose ReSearch, a novel framework that trains LLMs to Reason with Search via reinforcement learning without using any supervised data on reasoning steps. Our approach treats search operations as integral components of the reasoning chain, where when and how to perform searches is guided by text-based thinking, and search results subsequently influence further reasoning. We train ReSearch on Qwen2.5-7B(-Instruct) and Qwen2.5-32B(-Instruct) models and conduct extensive experiments. Despite being trained on only one dataset, our models demonstrate strong generalizability across various benchmarks. Analysis reveals that ReSearch naturally elicits advanced reasoning capabilities such as reflection and self-correction during the reinforcement learning process.
Reinforcement learning (RL) is a critical component of large language model (LLM) post-training. However, existing on-policy algorithms used for post-training are inherently incompatible with the use of experience replay buffers, which can be populated scalably by distributed off-policy actors to enhance exploration as compute increases. We propose efficiently obtaining this benefit of replay buffers via Trajectory Balance with Asynchrony (TBA), a massively scalable LLM RL system. In contrast to existing approaches, TBA uses a larger fraction of compute on search, constantly generating off-policy data for a central replay buffer. A training node simultaneously samples data from this buffer based on reward or recency to update the policy using Trajectory Balance (TB), a diversity-seeking RL objective introduced for GFlowNets. TBA offers three key advantages: (1) decoupled training and search, speeding up training wall-clock time by 4x or more; (2) improved diversity through large-scale off-policy sampling; and (3) scalable search for sparse reward settings. On mathematical reasoning, preference-tuning, and automated red-teaming (diverse and representative post-training tasks), TBA produces speed and performance improvements over strong baselines.
Large Language Models (LLMs) have shown remarkable promise in reasoning and decision-making, yet their integration with Reinforcement Learning (RL) for complex robotic tasks remains underexplored. In this paper, we propose an LLM-guided hierarchical RL framework, termed LDSC, that leverages LLM-driven subgoal selection and option reuse to enhance sample efficiency, generalization, and multi-task adaptability. Traditional RL methods often suffer from inefficient exploration and high computational cost. Hierarchical RL helps with these challenges, but existing methods often fail to reuse options effectively when faced with new tasks. To address these limitations, we introduce a three-stage framework that uses LLMs for subgoal generation given natural language description of the task, a reusable option learning and selection method, and an action-level policy, enabling more effective decision-making across diverse tasks. By incorporating LLMs for subgoal prediction and policy guidance, our approach improves exploration efficiency and enhances learning performance. On average, LDSC outperforms the baseline by 55.9\% in average reward, demonstrating its effectiveness in complex RL settings. More details and experiment videos could be found in \href{https://raaslab.org/projects/LDSC/}{this link\footnote{https://raaslab.org/projects/LDSC}}.
Automatic math correction aims to check students' solutions to mathematical problems via artificial intelligence technologies. Most existing studies focus on judging the final answer at the problem level, while they ignore detailed feedback on each step in a math problem-solving process, which requires abilities of semantic understanding and reasoning. In this paper, we propose a reinforcement learning (RL)-based method to boost large language model (LLM) for step-level automatic math correction, named StepAMC. Particularly, we convert the step-level automatic math correction within the text classification task into an RL problem to enhance the reasoning capabilities of LLMs. Then, we design a space-constrained policy network to improve the stability of RL. Then, we introduce a fine-grained reward network to convert the binary human feedback into a continuous value. We conduct extensive experiments over two benchmark datasets and the results show that our model outperforms the eleven strong baselines.
Reinforcement learning from human feedback (RLHF) is an effective method for aligning large language models (LLMs) with human values. However, reward over-optimization remains an open challenge leading to discrepancies between the performance of LLMs under the reward model and the true human objectives. A primary contributor to reward over-optimization is the extrapolation error that arises when the reward model evaluates out-of-distribution (OOD) responses. However, current methods still fail to prevent the increasing frequency of OOD response generation during the reinforcement learning (RL) process and are not effective at handling extrapolation errors from OOD responses. In this work, we propose the Behavior-Supported Policy Optimization (BSPO) method to mitigate the reward over-optimization issue. Specifically, we define behavior policy as the next token distribution of the reward training dataset to model the in-distribution (ID) region of the reward model. Building on this, we introduce the behavior-supported Bellman operator to regularize the value function, penalizing all OOD values without impacting the ID ones. Consequently, BSPO reduces the generation of OOD responses during the RL process, thereby avoiding overestimation caused by the reward model's extrapolation errors. Theoretically, we prove that BSPO guarantees a monotonic improvement of the supported policy until convergence to the optimal behavior-supported policy. Empirical results from extensive experiments show that BSPO outperforms baselines in preventing reward over-optimization due to OOD evaluation and finding the optimal ID policy.
Large Language Models (LLMs) have demonstrated exceptional performance on a range of downstream NLP tasks by generating text that closely resembles human writing. However, the ease of achieving this similarity raises concerns from potential malicious uses at scale by bad actors, as LLM-generated text becomes increasingly difficult to discern from human text. Although detection methods have been developed to address this issue, bad actors can further manipulate LLM-generated texts to make them less detectable. In this work, we study how further editing texts with Reinforcement Learning from Human Feedback (RLHF), which aligns model outputs with human preferences, affects (a) the quality of generated texts for two tasks, and (b) the performance of LLM-generated text detectors, looking at both training-based and zero-shot detection methods. Although RLHF improves the quality of LLM-generated texts, we find that it also tends to produce more detectable, lengthy, and repetitive outputs. Additionally, we observe that training-based detectors are vulnerable to short texts and to texts that incorporate code, whereas zero-shot detectors exhibit greater robustness.
Although DRL (deep reinforcement learning) has emerged as a powerful tool for making better decisions than existing hand-crafted communication protocols, it faces significant limitations: 1) Selecting the appropriate neural network architecture and setting hyperparameters are crucial for achieving desired performance levels, requiring domain expertise. 2) The decision-making process in DRL models is often opaque, commonly described as a 'black box.' 3) DRL models are data hungry. In response, we propose CP-AgentNet, the first framework designed to use generative agents for developing communication network protocols. This approach addresses these challenges by creating an autonomous system for protocol design, significantly reducing human effort. We developed LLMA (LLM-agents-based multiple access) and CPTCP (CP-Agent-based TCP) for heterogeneous environments. Our comprehensive simulations have demonstrated the efficient coexistence of LLMA and CPTCP with nodes using different types of protocols, as well as enhanced explainability.
ComfyUI provides a widely-adopted, workflow-based interface that enables users to customize various image generation tasks through an intuitive node-based architecture. However, the intricate connections between nodes and diverse modules often present a steep learning curve for users. In this paper, we introduce ComfyGPT, the first self-optimizing multi-agent system designed to generate ComfyUI workflows based on task descriptions automatically. ComfyGPT comprises four specialized agents: ReformatAgent, FlowAgent, RefineAgent, and ExecuteAgent. The core innovation of ComfyGPT lies in two key aspects. First, it focuses on generating individual node links rather than entire workflows, significantly improving generation precision. Second, we proposed FlowAgent, a LLM-based workflow generation agent that uses both supervised fine-tuning (SFT) and reinforcement learning (RL) to improve workflow generation accuracy. Moreover, we introduce FlowDataset, a large-scale dataset containing 13,571 workflow-description pairs, and FlowBench, a comprehensive benchmark for evaluating workflow generation systems. We also propose four novel evaluation metrics: Format Validation (FV), Pass Accuracy (PA), Pass Instruct Alignment (PIA), and Pass Node Diversity (PND). Experimental results demonstrate that ComfyGPT significantly outperforms existing LLM-based methods in workflow generation.
In recent years, large language models (LLMs) have achieved breakthrough progress in many dialogue generation tasks. However, their lack of emotion and fine-grained role awareness limits the model's ability to provide personalized and diverse interactions further. Current methods face high costs in collecting high-quality annotated data for scenarios such as role-playing, and traditional human alignment methods are difficult to deploy due to the inherent diversity of model behavior in role-playing scenarios. Inspired by the alignment of models for safety behaviors through RLHF (Reinforcement Learning from Human Feedback), in this paper, we revisit model role-playing behavior from the perspective of persona alignment and propose a novel annotation-free framework named \textbf{\underline{P}}ersona-Aware \textbf{\underline{C}}ontrastive \textbf{\underline{L}}earning (PCL) to align LLMs' behavior during role-playing, enhancing the model's role consistency. Specifically, we first design a role chain method to encourage the model to self-question based on the role characteristics and dialogue context to adjust personality consistency. Then, we further enhance the model's role-playing strategy through iterative contrastive learning between the use of role characteristics and not. Experiments on both black-box and white-box LLMs show that LLMs equipped with PCL significantly outperform vanilla LLMs under automatic evaluation methods (CharEval \& GPT-4) and human expert evaluation.
Radiotherapy treatment planning is a complex and time-intensive process, often impacted by inter-planner variability and subjective decision-making. To address these challenges, we introduce Dose Optimization Language Agent (DOLA), an autonomous large language model (LLM)-based agent designed for optimizing radiotherapy treatment plans while rigorously protecting patient privacy. DOLA integrates the LLaMa3.1 LLM directly with a commercial treatment planning system, utilizing chain-of-thought prompting, retrieval-augmented generation (RAG), and reinforcement learning (RL). Operating entirely within secure local infrastructure, this agent eliminates external data sharing. We evaluated DOLA using a retrospective cohort of 18 prostate cancer patients prescribed 60 Gy in 20 fractions, comparing model sizes (8 billion vs. 70 billion parameters) and optimization strategies (No-RAG, RAG, and RAG+RL) over 10 planning iterations. The 70B model demonstrated significantly improved performance, achieving approximately 16.4% higher final scores than the 8B model. The RAG approach outperformed the No-RAG baseline by 19.8%, and incorporating RL accelerated convergence, highlighting the synergy of retrieval-based memory and reinforcement learning. Optimal temperature hyperparameter analysis identified 0.4 as providing the best balance between exploration and exploitation. This proof of concept study represents the first successful deployment of locally hosted LLM agents for autonomous optimization of treatment plans within a commercial radiotherapy planning system. By extending human-machine interaction through interpretable natural language reasoning, DOLA offers a scalable and privacy-conscious framework, with significant potential for clinical implementation and workflow improvement.
Recent advancements demonstrated by DeepSeek-R1 have shown that complex reasoning abilities in large language models (LLMs), including sophisticated behaviors such as self-verification and self-correction, can be achieved by RL with verifiable rewards and significantly improves model performance on challenging tasks such as AIME. Motivated by these findings, our study investigates whether similar reasoning capabilities can be successfully integrated into large vision-language models (LVLMs) and assesses their impact on challenging multimodal reasoning tasks. We consider an approach that iteratively leverages supervised fine-tuning (SFT) on lightweight training data and Reinforcement Learning (RL) to further improve model generalization. Initially, reasoning capabilities were distilled from pure-text R1 models by generating reasoning steps using high-quality captions of the images sourced from diverse visual datasets. Subsequently, iterative RL training further enhance reasoning skills, with each iteration's RL-improved model generating refined SFT datasets for the next round. This iterative process yielded OpenVLThinker, a LVLM exhibiting consistently improved reasoning performance on challenging benchmarks such as MathVista, MathVerse, and MathVision, demonstrating the potential of our strategy for robust vision-language reasoning. The code, model and data are held at https://github.com/yihedeng9/OpenVLThinker.
Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks. Recent advancements in Large Reasoning Models (LRMs), such as OpenAI o1 and DeepSeek-R1, have further improved performance in System-2 reasoning domains like mathematics and programming by harnessing supervised fine-tuning (SFT) and reinforcement learning (RL) techniques to enhance the Chain-of-Thought (CoT) reasoning. However, while longer CoT reasoning sequences improve performance, they also introduce significant computational overhead due to verbose and redundant outputs, known as the "overthinking phenomenon". In this paper, we provide the first structured survey to systematically investigate and explore the current progress toward achieving efficient reasoning in LLMs. Overall, relying on the inherent mechanism of LLMs, we categorize existing works into several key directions: (1) model-based efficient reasoning, which considers optimizing full-length reasoning models into more concise reasoning models or directly training efficient reasoning models; (2) reasoning output-based efficient reasoning, which aims to dynamically reduce reasoning steps and length during inference; (3) input prompts-based efficient reasoning, which seeks to enhance reasoning efficiency based on input prompt properties such as difficulty or length control. Additionally, we introduce the use of efficient data for training reasoning models, explore the reasoning capabilities of small language models, and discuss evaluation methods and benchmarking.
Reasoning large language models are rapidly evolving across various domains. However, their capabilities in handling complex financial tasks still require in-depth exploration. In this paper, we introduce Fin-R1, a reasoning large language model specifically designed for the financial sector. Fin-R1 is built using a two-stage architecture, leveraging a financial reasoning dataset distilled and processed based on DeepSeek-R1. Through supervised fine-tuning (SFT) and reinforcement learning (RL) training, it demonstrates performance close to DeepSeek-R1 with a parameter size of 7 billion across a range of financial reasoning tasks. It achieves the state-of-the-art (SOTA) in the FinQA and ConvFinQA tasks between those LLMs in our evaluation, surpassing larger models in other tasks as well. Fin-R1 showcases strong reasoning and decision-making capabilities, providing solutions to various problems encountered in the financial domain. Our code is available at https://github.com/SUFE-AIFLM-Lab/Fin-R1.
Enhancing the reasoning capabilities of large language models (LLMs) typically relies on massive computational resources and extensive datasets, limiting accessibility for resource-constrained settings. Our study investigates the potential of reinforcement learning (RL) to improve reasoning in small LLMs, focusing on a 1.5-billion-parameter model, DeepSeek-R1-Distill-Qwen-1.5B, under strict constraints: training on 4 NVIDIA A40 GPUs (48 GB VRAM each) within 24 hours. Adapting the Group Relative Policy Optimization (GRPO) algorithm and curating a compact, high-quality mathematical reasoning dataset, we conducted three experiments to explore model behavior and performance. Our results demonstrate rapid reasoning gains - e.g., AMC23 accuracy rising from 63% to 80% and AIME24 reaching 46.7%, surpassing o1-preview - using only 7,000 samples and a $42 training cost, compared to thousands of dollars for baseline models. However, challenges such as optimization instability and length constraints emerged with prolonged training. These findings highlight the efficacy of RL-based fine-tuning for small LLMs, offering a cost-effective alternative to large-scale approaches. We release our code and datasets as open-source resources, providing insights into trade-offs and laying a foundation for scalable, reasoning-capable LLMs in resource-limited environments. All are available at https://github.com/knoveleng/open-rs.
Large Language Model (LLM) alignment conventionally relies on supervised fine-tuning or reinforcement learning based alignment frameworks. These methods typically require labeled or preference datasets and involve updating model weights to align the LLM with the training objective or reward model. Meanwhile, in social sciences such as cross-cultural studies, factor analysis is widely used to uncover underlying dimensions or latent variables that explain observed patterns in survey data. The non-differentiable nature of these measurements deriving from survey data renders the former alignment methods infeasible for alignment with cultural dimensions. To overcome this, we propose a parameter efficient strategy that combines soft prompt tuning, which freezes the model parameters while modifying the input prompt embeddings, with Differential Evolution (DE), a black-box optimization method for cases where a differentiable objective is unattainable. This strategy ensures alignment consistency without the need for preference data or model parameter updates, significantly enhancing efficiency and mitigating overfitting. Our method demonstrates significant improvements in LLama-3-8B-Instruct's cultural dimensions across multiple regions, outperforming both the Naive LLM and the In-context Learning (ICL) baseline, and effectively bridges computational models with human cultural nuances.
In the field of video-language pretraining, existing models face numerous challenges in terms of inference efficiency and multimodal data processing. This paper proposes a KunLunBaize-VoT-R1 video inference model based on a long-sequence image encoder, along with its training and application methods. By integrating image packing technology, the Autonomy-of-Experts (AoE) architecture, and combining the video of Thought (VoT), a large language model (LLM) trained with large-scale reinforcement learning, and multiple training techniques, the efficiency and accuracy of the model in video inference tasks are effectively improved. Experiments show that this model performs outstandingly in multiple tests, providing a new solution for video-language understanding.
Game Description Generation (GDG) is the task of generating a game description written in a Game Description Language (GDL) from natural language text. Previous studies have explored generation methods leveraging the contextual understanding capabilities of Large Language Models (LLMs); however, accurately reproducing the game features of the game descriptions remains a challenge. In this paper, we propose reinforcement learning-based fine-tuning of LLMs for GDG (RLGDG). Our training method simultaneously improves grammatical correctness and fidelity to game concepts by introducing both grammar rewards and concept rewards. Furthermore, we adopt a two-stage training strategy where Reinforcement Learning (RL) is applied following Supervised Fine-Tuning (SFT). Experimental results demonstrate that our proposed method significantly outperforms baseline methods using SFT alone.
The objective of this study is to design and implement a reinforcement learning (RL) environment using D\&D 5E combat scenarios to challenge smaller RL agents through interaction with a robust adversarial agent controlled by advanced Large Language Models (LLMs) like GPT-4o and LLaMA 3 8B. This research employs Deep Q-Networks (DQN) for the smaller agents, creating a testbed for strategic AI development that also serves as an educational tool by simulating dynamic and unpredictable combat scenarios. We successfully integrated sophisticated language models into the RL framework, enhancing strategic decision-making processes. Our results indicate that while RL agents generally outperform LLM-controlled adversaries in standard metrics, the strategic depth provided by LLMs significantly enhances the overall AI capabilities in this complex, rule-based setting. The novelty of our approach and its implications for mastering intricate environments and developing adaptive strategies are discussed, alongside potential innovations in AI-driven interactive simulations. This paper aims to demonstrate how integrating LLMs can create more robust and adaptable AI systems, providing valuable insights for further research and educational applications.
Repository-level code completion aims to complete code based on the long contexts of the repository. Existing studies extract long contexts from the repository as inputs and leverage Large Language Models (LLMs) to generate code. However, we reveal a severe limitation of LLMs, i.e., LLMs may ignore the information within long contexts in code completion. In other words, even the contexts contain useful information (e.g., relevant APIs or similar code), LLMs may fail to utilize this information. We think this limitation is caused by an inherent bias in LLMs, i.e., relying on nearby contexts and ignoring long-range contexts. To address this, we propose a novel fine-tuning approach named CoLT. The core idea of CoLT is to provide explicit supervision signals, which emphasize that long-range contexts may hold relevant information. Specifically, CoLT proposes a reinforcement learning-based training, which explicitly encourages models to utilize the information within long contexts and punishes models for ignoring long contexts. To support CoLT, we release CoLT-132K, a large-scale dataset with 132k samples across four languages, each containing long-context inputs. We apply CoLT to a popular LLM - aiXcoder-7B and release aiXcoder-7B-v2. We conduct extensive experiments on CoLT-132K and a public benchmark - CrossCodeEval. Our experiments yield the results: 1. Effectiveness. CoLT substantially improves aiXcoder-7B. aiXcoder-7B-v2 outperforms aiXcoder-7B by up to 44% in exact match. aiXcoder-7B-v2 becomes the state-of-the-art 7B model in code completion and even surpasses larger models. 2. Generalizability. The capability learned by CoLT can generalize to new languages. Besides, CoLT is model-agnostic and effectively improves multiple LLMs. 3. Enhanced Context Utilization Capability. CoLT significantly improves the capability of LLMs in utilizing the relevant information within long contexts.
This paper studies how AI-assisted programming and large language models (LLM) improve software developers' ability via AI tools (LLM agents) like Github Copilot and Amazon CodeWhisperer, while integrating human feedback to enhance reinforcement learning (RLHF) with crowd-sourced computation to enhance text-to-code generation. Additionally, we demonstrate that our Bayesian optimization framework supports AI alignment in code generation by distributing the feedback collection burden, highlighting the value of collecting human feedback of good quality. Our empirical evaluations demonstrate the efficacy of this approach, showcasing how LLM agents can be effectively trained for improved text-to-code generation. Our Bayesian optimization framework can be designed for general domain-specific languages, promoting the alignment of large language model capabilities with human feedback in AI-assisted programming for code generation.
While Large Language Models (LLMs) excel at reasoning on text and Vision-Language Models (VLMs) are highly effective for visual perception, applying those models for visual instruction-based planning remains a widely open problem. In this paper, we introduce VIPER, a novel framework for multimodal instruction-based planning that integrates VLM-based perception with LLM-based reasoning. Our approach uses a modular pipeline where a frozen VLM generates textual descriptions of image observations, which are then processed by an LLM policy to predict actions based on the task goal. We fine-tune the reasoning module using behavioral cloning and reinforcement learning, improving our agent's decision-making capabilities. Experiments on the ALFWorld benchmark show that VIPER significantly outperforms state-of-the-art visual instruction-based planners while narrowing the gap with purely text-based oracles. By leveraging text as an intermediate representation, VIPER also enhances explainability, paving the way for a fine-grained analysis of perception and reasoning components.
Log anomaly detection refers to the task that distinguishes the anomalous log messages from normal log messages. Transformer-based large language models (LLMs) are becoming popular for log anomaly detection because of their superb ability to understand complex and long language patterns. In this paper, we propose LogLLaMA, a novel framework that leverages LLaMA2. LogLLaMA is first finetuned on normal log messages from three large-scale datasets to learn their patterns. After finetuning, the model is capable of generating successive log messages given previous log messages. Our generative model is further trained to identify anomalous log messages using reinforcement learning (RL). The experimental results show that LogLLaMA outperforms the state-of-the-art approaches for anomaly detection on BGL, Thunderbird, and HDFS datasets.
Large Language Models (LLMs) have significantly advanced automated code generation, yet they struggle with complex coding tasks requiring multi-step logical reasoning. High-quality reasoning data is crucial for improving LLMs' reasoning capabilities, but such datasets remain scarce. Existing approaches either rely on computationally expensive reinforcement learning (RL) or error-prone reasoning chains synthesized by LLMs, posing challenges in scalability and accuracy. To address this challenge, we propose SVRC (Structured and Validated Reasoning Chains for Code Generation), a novel framework that mines, restructures, and enriches reasoning chains from community-driven discussions on software engineering platforms. SVRC refines unstructured and incomplete discussions of coding problems by aligning them with Software Development Life Cycle (SDLC) principles, ensuring that reasoning chains capture real-world problem-solving strategies and support iterative refinement. To evaluate the effectiveness of SVRC, we introduce CodeThinker, an LLM fine-tuned on 12,444 reasoning-augmented samples generated by SVRC. Experiments on LiveCodeBench show that CodeThinker surpasses its base model by 42.86\% on medium-level code problems in terms of pass@1 and outperforms GPT-4o-mini and GPT-4o by 73.14\% and 115.86\%, respectively. Our ablation study further highlights that each component of SVRC contributes to the reasoning capabilities of CodeThinker.
Inference scaling empowers LLMs with unprecedented reasoning ability, with reinforcement learning as the core technique to elicit complex reasoning. However, key technical details of state-of-the-art reasoning LLMs are concealed (such as in OpenAI o1 blog and DeepSeek R1 technical report), thus the community still struggles to reproduce their RL training results. We propose the $\textbf{D}$ecoupled Clip and $\textbf{D}$ynamic s$\textbf{A}$mpling $\textbf{P}$olicy $\textbf{O}$ptimization ($\textbf{DAPO}$) algorithm, and fully open-source a state-of-the-art large-scale RL system that achieves 50 points on AIME 2024 using Qwen2.5-32B base model. Unlike previous works that withhold training details, we introduce four key techniques of our algorithm that make large-scale LLM RL a success. In addition, we open-source our training code, which is built on the verl framework, along with a carefully curated and processed dataset. These components of our open-source system enhance reproducibility and support future research in large-scale LLM RL.
Maintaining and scaling software systems relies heavily on effective code refactoring, yet this process remains labor-intensive, requiring developers to carefully analyze existing codebases and prevent the introduction of new defects. Although recent advancements have leveraged Large Language Models (LLMs) to automate refactoring tasks, current solutions are constrained in scope and lack mechanisms to guarantee code compilability and successful test execution. In this work, we introduce MANTRA, a comprehensive LLM agent-based framework that automates method-level refactoring. MANTRA integrates Context-Aware Retrieval-Augmented Generation, coordinated Multi-Agent Collaboration, and Verbal Reinforcement Learning to emulate human decision-making during refactoring while preserving code correctness and readability. Our empirical study, conducted on 703 instances of "pure refactorings" (i.e., code changes exclusively involving structural improvements), drawn from 10 representative Java projects, covers the six most prevalent refactoring operations. Experimental results demonstrate that MANTRA substantially surpasses a baseline LLM model (RawGPT ), achieving an 82.8% success rate (582/703) in producing code that compiles and passes all tests, compared to just 8.7% (61/703) with RawGPT. Moreover, in comparison to IntelliJ's LLM-powered refactoring tool (EM-Assist), MANTRA exhibits a 50% improvement in generating Extract Method transformations. A usability study involving 37 professional developers further shows that refactorings performed by MANTRA are perceived to be as readable and reusable as human-written code, and in certain cases, even more favorable. These results highlight the practical advantages of MANTRA and emphasize the growing potential of LLM-based systems in advancing the automation of software refactoring tasks.
We propose a new algorithm for fine-tuning large language models using reinforcement learning. Tapered Off-Policy REINFORCE (TOPR) uses an asymmetric, tapered variant of importance sampling to speed up learning while maintaining stable learning dynamics, even without the use of KL regularization. TOPR can be applied in a fully offline fashion, allows the handling of positive and negative examples in a unified framework, and benefits from the implementational simplicity that is typical of Monte Carlo algorithms. We demonstrate the effectiveness of our approach with a series of experiments on the GSM8K and MATH reasoning benchmarks, finding performance gains for training both a model for solution generation and as a generative verifier. We show that properly leveraging positive and negative examples alike in the off-policy regime simultaneously increases test-time accuracy and training data efficiency, all the while avoiding the ``wasted inference'' that comes with discarding negative examples. We find that this advantage persists over multiple iterations of training and can be amplified by dataset curation techniques, enabling us to match 70B-parameter model performance with 8B language models. As a corollary to this work, we find that REINFORCE's baseline parameter plays an important and unexpected role in defining dataset composition in the presence of negative examples, and is consequently critical in driving off-policy performance.
Large language models (LLMs) have unlocked new possibilities for generating synthetic training data in both natural language and code. By producing artificial but task-relevant examples, these models can significantly augment or even replace real-world datasets, especially when labeled data is scarce or sensitive. This paper surveys recent advances in using LLMs to create synthetic text and code, emphasizing prompt-based generation, retrieval-augmented pipelines, and iterative self-refinement. We show how these methods enrich low-resource tasks such as classification and question answering, as well as code-centric applications such as instruction tuning, code translation, and bug repair, by enabling automated verification of functional correctness. Alongside potential benefits like cost-effectiveness, broad coverage, and controllable diversity, we address challenges such as factual inaccuracies in generated text, lack of stylistic realism, and the risk of bias amplification. Proposed mitigations include filtering and weighting outputs and reinforcement learning with execution feedback for code. We conclude with open research directions like automated prompt engineering, cross-modal data synthesis, and robust evaluation frameworks, highlighting the importance of LLM-generated synthetic data in advancing AI while emphasizing ethical and quality safeguards.
With the rapid development of artificial intelligence, intelligent decision-making techniques have gradually surpassed human levels in various human-machine competitions, especially in complex multi-agent cooperative task scenarios. Multi-agent cooperative decision-making involves multiple agents working together to complete established tasks and achieve specific objectives. These techniques are widely applicable in real-world scenarios such as autonomous driving, drone navigation, disaster rescue, and simulated military confrontations. This paper begins with a comprehensive survey of the leading simulation environments and platforms used for multi-agent cooperative decision-making. Specifically, we provide an in-depth analysis for these simulation environments from various perspectives, including task formats, reward allocation, and the underlying technologies employed. Subsequently, we provide a comprehensive overview of the mainstream intelligent decision-making approaches, algorithms and models for multi-agent systems (MAS). Theseapproaches can be broadly categorized into five types: rule-based (primarily fuzzy logic), game theory-based, evolutionary algorithms-based, deep multi-agent reinforcement learning (MARL)-based, and large language models(LLMs)reasoning-based. Given the significant advantages of MARL andLLMs-baseddecision-making methods over the traditional rule, game theory, and evolutionary algorithms, this paper focuses on these multi-agent methods utilizing MARL and LLMs-based techniques. We provide an in-depth discussion of these approaches, highlighting their methodology taxonomies, advantages, and drawbacks. Further, several prominent research directions in the future and potential challenges of multi-agent cooperative decision-making are also detailed.