Chuhuai Yue

Chengqi Dong, Chuhuai Yue, Hang He et al.

We identify and formally characterize credit misassignment as a systematic failure mode of GRPO in tool-augmented multimodal search agents: its uniform broadcast of trajectory-level advantages to all tokens causes valuable tool-use steps in failing trajectories to be penalized no differently from valueless ones. We further empirically quantify the scale of this phenomenon. Over half of failing trajectories and failing tool-use actions exhibit correctable credit misassignment, demonstrating that the wasted training signal is both substantial and structurally exploitable. Building on this insight, we propose Tool-Aware Policy Optimization (TAPO), which exploits the parameter-determinism property of information-acquisition tools: similar call parameters define equivalent information-acquisition actions and should therefore share comparable action credit. TAPO constructs counterfactual witnesses within the current training batch and compensates misassigned negative credit via confidence-gated conservative advantage correction. It requires no additional annotation, models, or sampling, and introduces negligible computational overhead. Across multiple multimodal search benchmarks, TAPO delivers consistent, plug-and-play improvements over strong baselines for three mainstream RL algorithms (GRPO, GSPO, and SAPO). Our code and models will be publicly released upon acceptance.

Hang He, Chuhuai Yue, Chengqi Dong et al.

Visual DeepSearch requires multimodal large reasoning model (MLRM) agents to answer complex visual queries by repeatedly inspecting image regions, grounding intermediate reasoning in visual evidence, and connecting fine-grained clues across long reasoning chains. However, existing benchmarks mainly focus on single-step visual understanding or static image-question answering, offering limited evaluation of iterative image inspection, visual-anchor grounding, and multi-hop evidence integration. In this work, we introduce VistaHop, a benchmark for evaluating vision-centric search and multi-hop visual reasoning in Visual DeepSearch. VistaHop contains 300 high-resolution images, 25 visual search scenarios, and 350 multi-hop QA tasks that require models to follow evidence chains from visual anchors or fuse information across multiple image-grounded reasoning paths. We further develop VistaArena, a unified evaluation environment that supports tool-augmented reasoning with text search, image search, image cropping, and evidence-based answer validation. Experiments on seven representative MLRMs show that current models remain far from solving VistaHop: the best model, SenseNova-MARS-32B, achieves only 24.31% Pass@1. These results reveal persistent limitations in visual grounding, evidence revisiting, long-chain reasoning, and multi-anchor information fusion, highlighting the need for stronger benchmarks and training methods for Visual DeepSearch.

Jiajun Chai, Guojun Yin, Zekun Xu et al.

Large language models excel at basic reasoning but struggle with tasks that require interaction with external tools. We present RLFactory, a plug-and-play reinforcement learning post-training framework for multi-round tool use. RLFactory tackles (i) tool-call stability and adaptability amid tool heterogeneity and interface issues via an asyncio-based asynchronous caller and a decoupled tool/training architecture, and (ii) diverse evaluation needs via a reward layer supporting rule-based, model-judgment, and tool-verification signals. It reconstructs the MDP by introducing observation markers from tool feedback, closing the loop among model, tools, and environment, and implements a generate-parse-invoke-update workflow for dynamic policy optimization. On Search-R1 with Qwen3-4B, RLFactory achieves a 0.486 test score on the Natural Questions (NQ) dataset, surpassing larger models trained with similar techniques (e.g., Qwen2.5-7B-Instruct-GRPO at 0.473), and increases training throughput by 6.8x. RLFactory provides a low-barrier, highly adaptable framework for strengthening multi-round tool use of LLMs in real-world scenarios. Code: https://github.com/Simple-Efficient/RL-Factory.

Hang He, Chuhuai Yue, Chengqi Dong et al.

Recent advances in large reasoning models (LRMs) have enabled agentic search systems to perform complex multi-step reasoning across multiple sources. However, most studies focus on general information retrieval and rarely explores vertical domains with unique challenges. In this work, we focus on local life services and introduce LocalSearchBench, which encompass diverse and complex business scenarios. Real-world queries in this domain are often ambiguous and require multi-hop reasoning across merchants and products, remaining challenging and not fully addressed. As the first comprehensive benchmark for agentic search in local life services, LocalSearchBench includes over 150,000 high-quality entries from various cities and business types. We construct 300 multi-hop QA tasks based on real user queries, challenging agents to understand questions and retrieve information in multiple steps. We also developed LocalPlayground, a unified environment integrating multiple tools for agent interaction. Experiments show that even state-of-the-art LRMs struggle on LocalSearchBench: the best model (DeepSeek-V3.1) achieves only 34.34% correctness, and most models have issues with completeness (average 77.33%) and faithfulness (average 61.99%). This highlights the need for specialized benchmarks and domain-specific agent training in local life services. Code, Benchmark, and Leaderboard are available at localsearchbench.github.io.

Chengqi Dong, Chuhuai Yue, Hang He et al.

Recent VLM-based agents aim to replicate OpenAI O3's ``thinking with images" via tool use, but most open-source methods limit input to a single image, falling short on real-world multi-image QA tasks. To address this, we propose IMAgent, an open-source vision agent trained via end-to-end reinforcement learning dedicated for complex multi-image tasks. By leveraging a multi-agent system, we generate challenging and visually-rich multi-image QA pairs to fully activate the tool-use potential of the base VLM. Through manual verification, we obtain MIFG-QA, comprising 10k samples for training and evaluation. With deeper reasoning steps, VLMs may increasingly ignore visual inputs. We therefore develop two specialized tools for visual reflection and confirmation, allowing the model to proactively reallocate its attention to image content during inference. Benefiting from our well-designed action-trajectory two-level mask strategy, IMAgent achieves stable tool use behavior via pure RL training without requiring costly supervised fine-tuning data. Extensive experiments demonstrate that IMAgent maintains strong performance on existing single-image benchmarks while achieving substantial improvements on our proposed multi-image dataset, with our analysis providing actionable insights for the research community. Codes and data will be released soon.

Chuhuai Yue, Chengqi Dong, Yinan Gao et al.

Large reasoning models (LRMs) have recently achieved significant progress in complex reasoning tasks, aided by reinforcement learning with verifiable rewards. However, LRMs often suffer from overthinking, expending excessive computation on simple problems and reducing efficiency. Existing efficient reasoning methods typically require accurate task assessment to preset token budgets or select reasoning modes, which limits their flexibility and reliability. In this work, we revisit the essence of overthinking and identify that encouraging effective steps while penalizing ineffective ones is key to its solution. To this end, we propose a novel rule-based verifiable stepwise reward mechanism (VSRM), which assigns rewards based on the performance of intermediate states in the reasoning trajectory. This approach is intuitive and naturally fits the step-by-step nature of reasoning tasks. We conduct extensive experiments on standard mathematical reasoning benchmarks, including AIME24 and AIME25, by integrating VSRM with PPO and Reinforce++. Results show that our method achieves substantial output length reduction while maintaining original reasoning performance, striking an optimal balance between efficiency and accuracy. Further analysis of overthinking frequency and pass@k score before and after training demonstrates that our approach in deed effectively suppresses ineffective steps and encourages effective reasoning, fundamentally alleviating the overthinking problem. All code will be released upon acceptance.

Haomiao Liu, Hao Xu, Chuhuai Yue et al.

Unknown Object Detection (UOD) aims to identify objects of unseen categories, differing from the traditional detection paradigm limited by the closed-world assumption. A key component of UOD is learning a generalized representation, i.e. objectness for both known and unknown categories to distinguish and localize objects from the background in a class-agnostic manner. However, previous methods obtain supervision signals for learning objectness in isolation from either localization or classification information, leading to poor performance for UOD. To address this issue, we propose a transformer-based UOD framework, UN-DETR. Based on this, we craft Instance Presence Score (IPS) to represent the probability of an object's presence. For the purpose of information complementarity, IPS employs a strategy of joint supervised learning, integrating attributes representing general objectness from the positional and the categorical latent space as supervision signals. To enhance IPS learning, we introduce a one-to-many assignment strategy to incorporate more supervision. Then, we propose Unbiased Query Selection to provide premium initial query vectors for the decoder. Additionally, we propose an IPS-guided post-process strategy to filter redundant boxes and correct classification predictions for known and unknown objects. Finally, we pretrain the entire UN-DETR in an unsupervised manner, in order to obtain objectness prior. Our UN-DETR is comprehensively evaluated on multiple UOD and known detection benchmarks, demonstrating its effectiveness and achieving state-of-the-art performance.

Zekun Xu, Siyu Xia, Chuhuai Yue et al.

As large language models (LLMs) are increasingly used in Text-to-SQL tasks, Reinforcement Learning (RL) has become a common method for improving performance. Existing methods primarily rely on static execution feedback, which restricts real-time error correction. However, integrating multi-turn tool invocation along with dynamic feedback could significantly improve adaptability and robustness, ultimately enhancing model performance. To address these issues, we propose MTIR-SQL, an innovative Multi-turn Tool-Integrated Reasoning reinforcement learning framework for Text-to-SQL. Our approach introduces an execution-aware multi-turn reasoning paradigm that seamlessly incorporates database execution feedback at each reasoning step, enabling context-sensitive query generation and progressive refinement throughout the reasoning process. The framework extends the GRPO algorithm to accommodate complex multi-turn interaction scenarios. Considering the training instability characteristics of MTIR and the potential for significant Deviation of model distribution from the initial model, we enhance the GRPO algorithm by adding a trajectory filtering mechanism and removing KL loss constraints. Experimental results demonstrate that MTIR-SQL, with 4B parameters, achieves \textbf{64.4}\% accuracy in the BIRD Dev and 84.6% execution accuracy in the SPIDER Dev, significantly outperforming existing approaches.