Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs

Large Language Models (LLMs) with inference-time scaling techniques show promise for code generation, yet face notable efficiency and scalability challenges. Construction-based tree-search methods suffer from rapid growth in tree size, high token consumption, and lack of anytime property. In contrast, improvement-based methods offer better performance but often struggle with uninformative reward signals and inefficient search strategies. In this work, we propose \textbf{ReLoc}, a unified local search framework which effectively performs step-by-step code revision. Specifically, ReLoc explores a series of local revisions through four key algorithmic components: initial code drafting, neighborhood code generation, candidate evaluation, and incumbent code updating, each of which can be instantiated with specific decision rules to realize different local search algorithms such as Hill Climbing (HC) or Genetic Algorithm (GA). Furthermore, we develop a specialized revision reward model that evaluates code quality based on revision distance to produce fine-grained preferences that guide the local search toward more promising candidates. Finally, our extensive experimental results demonstrate that our approach achieves superior performance across diverse code generation tasks, significantly outperforming both construction-based tree search as well as the state-of-the-art improvement-based code generation methods.

GDBA Revisited: Unleashing the Power of Guided Local Search for Distributed Constraint Optimization

Local search is an important class of incomplete algorithms for solving Distributed Constraint Optimization Problems (DCOPs) but it often converges to poor local optima. While GDBA provides a comprehensive rule set to escape premature convergence, its empirical benefits remain marginal on general-valued problems. In this work, we systematically examine GDBA and identify three factors that potentially lead to its inferior performance, i.e., over-aggressive constraint violation conditions, unbounded penalty accumulation, and uncoordinated penalty updates. To address these issues, we propose Distributed Guided Local Search (DGLS), a novel GLS framework for DCOPs that incorporates an adaptive violation condition to selectively penalize constraints with high cost, a penalty evaporation mechanism to control the magnitude of penalization, and a synchronization scheme for coordinated penalty updates. We theoretically show that the penalty values are bounded, and agents play a potential game in our DGLS. Our extensive empirical results on various standard benchmarks demonstrate the great superiority of DGLS over state-of-the-art baselines. Particularly, compared to Damped Max-sum with high damping factors (e.g., 0.7 or 0.9), our DGLS achieves competitive performance on general-valued problems, and outperforms it by significant margins (\textbf{3.77\%--66.3\%}) on structured problems in terms of anytime results.

StarDojo: Benchmarking Open-Ended Behaviors of Agentic Multimodal LLMs in Production-Living Simulations with Stardew Valley

Autonomous agents navigating human society must master both production activities and social interactions, yet existing benchmarks rarely evaluate these skills simultaneously. To bridge this gap, we introduce StarDojo, a novel benchmark based on Stardew Valley, designed to assess AI agents in open-ended production-living simulations. In StarDojo, agents are tasked to perform essential livelihood activities such as farming and crafting, while simultaneously engaging in social interactions to establish relationships within a vibrant community. StarDojo features 1,000 meticulously curated tasks across five key domains: farming, crafting, exploration, combat, and social interactions. Additionally, we provide a compact subset of 100 representative tasks for efficient model evaluation. The benchmark offers a unified, user-friendly interface that eliminates the need for keyboard and mouse control, supports all major operating systems, and enables the parallel execution of multiple environment instances, making it particularly well-suited for evaluating the most capable foundation agents, powered by multimodal large language models (MLLMs). Extensive evaluations of state-of-the-art MLLMs agents demonstrate substantial limitations, with the best-performing model, GPT-4.1, achieving only a 12.7% success rate, primarily due to challenges in visual understanding, multimodal reasoning and low-level manipulation. As a user-friendly environment and benchmark, StarDojo aims to facilitate further research towards robust, open-ended agents in complex production-living environments.

AgentOrchestra: A Hierarchical Multi-Agent Framework for General-Purpose Task Solving

Recent advances in agent systems based on large language models (LLMs) have demonstrated strong capabilities in solving complex tasks. However, most current methods lack mechanisms for coordinating specialized agents and have limited ability to generalize to new or diverse domains. We introduce \projectname, a hierarchical multi-agent framework for general-purpose task solving that integrates high-level planning with modular agent collaboration. Inspired by the way a conductor orchestrates a symphony and guided by the principles of \textit{extensibility}, \textit{multimodality}, \textit{modularity}, and \textit{coordination}, \projectname features a central planning agent that decomposes complex objectives and delegates sub-tasks to a team of specialized agents. Each sub-agent is equipped with general programming and analytical tools, as well as abilities to tackle a wide range of real-world specific tasks, including data analysis, file operations, web navigation, and interactive reasoning in dynamic multimodal environments. \projectname supports flexible orchestration through explicit sub-goal formulation, inter-agent communication, and adaptive role allocation. We evaluate the framework on three widely used benchmark datasets covering various real-world tasks, searching web pages, reasoning over heterogeneous modalities, etc. Experimental results demonstrate that \projectname consistently outperforms flat-agent and monolithic baselines in task success rate and adaptability. These findings highlight the effectiveness of hierarchical organization and role specialization in building scalable and general-purpose LLM-based agent systems.

EconGym: A Scalable AI Testbed with Diverse Economic Tasks

Artificial intelligence (AI) has become a powerful tool for economic research, enabling large-scale simulation and policy optimization. However, applying AI effectively requires simulation platforms for scalable training and evaluation-yet existing environments remain limited to simplified, narrowly scoped tasks, falling short of capturing complex economic challenges such as demographic shifts, multi-government coordination, and large-scale agent interactions. To address this gap, we introduce EconGym, a scalable and modular testbed that connects diverse economic tasks with AI algorithms. Grounded in rigorous economic modeling, EconGym implements 11 heterogeneous role types (e.g., households, firms, banks, governments), their interaction mechanisms, and agent models with well-defined observations, actions, and rewards. Users can flexibly compose economic roles with diverse agent algorithms to simulate rich multi-agent trajectories across 25+ economic tasks for AI-driven policy learning and analysis. Experiments show that EconGym supports diverse and cross-domain tasks-such as coordinating fiscal, pension, and monetary policies-and enables benchmarking across AI, economic methods, and hybrids. Results indicate that richer task composition and algorithm diversity expand the policy space, while AI agents guided by classical economic methods perform best in complex settings. EconGym also scales to 10k agents with high realism and efficiency.

Skywork Open Reasoner 1 Technical Report

The success of DeepSeek-R1 underscores the significant role of reinforcement learning (RL) in enhancing the reasoning capabilities of large language models (LLMs). In this work, we present Skywork-OR1, an effective and scalable RL implementation for long Chain-of-Thought (CoT) models. Building on the DeepSeek-R1-Distill model series, our RL approach achieves notable performance gains, increasing average accuracy across AIME24, AIME25, and LiveCodeBench from 57.8% to 72.8% (+15.0%) for the 32B model and from 43.6% to 57.5% (+13.9%) for the 7B model. Our Skywork-OR1-32B model surpasses both DeepSeek-R1 and Qwen3-32B on the AIME24 and AIME25 benchmarks, while achieving comparable results on LiveCodeBench. The Skywork-OR1-7B and Skywork-OR1-Math-7B models demonstrate competitive reasoning capabilities among models of similar size. We perform comprehensive ablation studies on the core components of our training pipeline to validate their effectiveness. Additionally, we thoroughly investigate the phenomenon of entropy collapse, identify key factors affecting entropy dynamics, and demonstrate that mitigating premature entropy collapse is critical for improved test performance. To support community research, we fully open-source our model weights, training code, and training datasets.

MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent Systems

LLM-based multi-agent systems (MAS) have demonstrated significant potential in enhancing single LLMs to address complex and diverse tasks in practical applications. Despite considerable advancements, the field lacks a unified codebase that consolidates existing methods, resulting in redundant re-implementation efforts, unfair comparisons, and high entry barriers for researchers. To address these challenges, we introduce MASLab, a unified, comprehensive, and research-friendly codebase for LLM-based MAS. (1) MASLab integrates over 20 established methods across multiple domains, each rigorously validated by comparing step-by-step outputs with its official implementation. (2) MASLab provides a unified environment with various benchmarks for fair comparisons among methods, ensuring consistent inputs and standardized evaluation protocols. (3) MASLab implements methods within a shared streamlined structure, lowering the barriers for understanding and extension. Building on MASLab, we conduct extensive experiments covering 10+ benchmarks and 8 models, offering researchers a clear and comprehensive view of the current landscape of MAS methods. MASLab will continue to evolve, tracking the latest developments in the field, and invite contributions from the broader open-source community.

Enhance Mobile Agents Thinking Process Via Iterative Preference Learning

The Chain of Action-Planning Thoughts (CoaT) paradigm has been shown to improve the reasoning performance of VLM-based mobile agents in GUI tasks. However, the scarcity of diverse CoaT trajectories limits the expressiveness and generalization ability of such agents. While self-training is commonly employed to address data scarcity, existing approaches either overlook the correctness of intermediate reasoning steps or depend on expensive process-level annotations to construct process reward models (PRM). To address the above problems, we propose an Iterative Preference Learning (IPL) that constructs a CoaT-tree through interative sampling, scores leaf nodes using rule-based reward, and backpropagates feedback to derive Thinking-level Direct Preference Optimization (T-DPO) pairs. To prevent overfitting during warm-up supervised fine-tuning, we further introduce a three-stage instruction evolution, which leverages GPT-4o to generate diverse Q\&A pairs based on real mobile UI screenshots, enhancing both generality and layout understanding. Experiments on three standard Mobile GUI-agent benchmarks demonstrate that our agent MobileIPL outperforms strong baselines, including continual pretraining models such as OS-ATLAS and UI-TARS. It achieves state-of-the-art performance across three standard Mobile GUI-Agents benchmarks and shows strong generalization to out-of-domain scenarios.

Mobile-Bench-v2: A More Realistic and Comprehensive Benchmark for VLM-based Mobile Agents

VLM-based mobile agents are increasingly popular due to their capabilities to interact with smartphone GUIs and XML-structured texts and to complete daily tasks. However, existing online benchmarks struggle with obtaining stable reward signals due to dynamic environmental changes. Offline benchmarks evaluate the agents through single-path trajectories, which stands in contrast to the inherently multi-solution characteristics of GUI tasks. Additionally, both types of benchmarks fail to assess whether mobile agents can handle noise or engage in proactive interactions due to a lack of noisy apps or overly full instructions during the evaluation process. To address these limitations, we use a slot-based instruction generation method to construct a more realistic and comprehensive benchmark named Mobile-Bench-v2. Mobile-Bench-v2 includes a common task split, with offline multi-path evaluation to assess the agent's ability to obtain step rewards during task execution. It contains a noisy split based on pop-ups and ads apps, and a contaminated split named AITZ-Noise to formulate a real noisy environment. Furthermore, an ambiguous instruction split with preset Q\&A interactions is released to evaluate the agent's proactive interaction capabilities. We conduct evaluations on these splits using the single-agent framework AppAgent-v1, the multi-agent framework Mobile-Agent-v2, as well as other mobile agents such as UI-Tars and OS-Atlas. Code and data are available at https://huggingface.co/datasets/xwk123/MobileBench-v2.

Group-in-Group Policy Optimization for LLM Agent Training

Recent advances in group-based reinforcement learning (RL) have driven frontier large language models (LLMs) in single-turn tasks like mathematical reasoning. However, their scalability to long-horizon LLM agent training remains limited. Unlike static tasks, agent-environment interactions unfold over many steps and often yield sparse or delayed rewards, making credit assignment across individual steps significantly more challenging. In this work, we propose Group-in-Group Policy Optimization (GiGPO), a novel RL algorithm that achieves fine-grained credit assignment for LLM agents while preserving the appealing properties of group-based RL: critic-free, low memory, and stable convergence. GiGPO introduces a two-level structure for estimating relative advantage: (i) At the episode-level, GiGPO computes macro relative advantages based on groups of complete trajectories; (ii) At the step-level, GiGPO introduces an anchor state grouping mechanism that retroactively constructs step-level groups by identifying repeated environment states across trajectories. Actions stemming from the same state are grouped together, enabling micro relative advantage estimation. This hierarchical structure effectively captures both global trajectory quality and local step effectiveness without relying on auxiliary models or additional rollouts. We evaluate GiGPO on two challenging agent benchmarks, ALFWorld and WebShop, using Qwen2.5-1.5B-Instruct and Qwen2.5-7B-Instruct. Crucially, GiGPO delivers fine-grained per-step credit signals and achieves performance gains of > 12\% on ALFWorld and > 9\% on WebShop over the GRPO baseline: all while maintaining the same GPU memory overhead, identical LLM rollout, and incurring little to no additional time cost.