arXiv subjects

Guojun Yin

Publications and source records attributed to Guojun Yin.

At least 55 records · Page 3Linked to original sources

arXiv2026

Dual-level Modality Debiasing Learning for Unsupervised Visible-Infrared Person Re-Identification

Two-stage learning pipeline has achieved promising results in unsupervised visible-infrared person re-identification (USL-VI-ReID). It first performs single-modality learning and then operates cross-modality learning to tackle the modality discrepancy. Although promising, this pipeline inevitably introduces modality bias: modality-specific cues learned in the single-modality training naturally propagate into the following cross-modality learning, impairing identity discrimination and generalization. To address this issue, we propose a Dual-level Modality Debiasing Learning (DMDL) framework that implements debiasing at both the model and optimization levels. At the model level, we propose a Causality-inspired Adjustment Intervention (CAI) module that replaces likelihood-based modeling with causal modeling, preventing modality-induced spurious patterns from being introduced, leading to a low-biased model. At the optimization level, a Collaborative Bias-free Training (CBT) strategy is introduced to interrupt the propagation of modality bias across data, labels, and features by integrating modality-specific augmentation, label refinement, and feature alignment. Extensive experiments on benchmark datasets demonstrate that DMDL could enable modality-invariant feature learning and a more generalized model. The code is available at https://github.com/priester3/DMDL.

cs.CV↗

arXiv2026

Training Multi-Image Vision Agents via End2End Reinforcement Learning

Recent VLM-based agents aim to replicate OpenAI O3's "thinking with images" via tool use, yet most open-source methods restrict inputs to a single image, limiting their applicability to real-world multi-image QA tasks. To address this gap, we propose IMAgent, an open-source visual agent trained with end-to-end reinforcement learning for fine-grained single/multi-image reasoning. During inference, VLMs tend to gradually neglect visual inputs; to mitigate this issue, we design two dedicated tools for visual reflection and verification, enabling the model to actively refocus attention on image content. Beyond that, we, for the first time, reveal how tool usage enhances agent performance from an attention perspective. Equipped with a carefully designed two-layer motion trajectory masking strategy and tool-use reward gain, IMAgent acquires an effective tool-use paradigm through pure reinforcement learning, eliminating the need for costly supervised fine-tuning data. To further unleash the inherent tool-usage potential of the base VLM and fill data gaps, we construct a challenging, visually enriched multi-image QA dataset via multi-agent system. Extensive experiments validate that IMAgent achieves SOTA performance across mainstream single and multi-image benchmarks, and our in-depth analysis offers actionable insights for the community. Code and data will be released soon.

cs.CV↗

arXiv2026

CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling

Reward modeling is essential for aligning Large Language Models(LLMs) with human preferences, yet conventional reward models suffer from poor interpretability and heavy reliance on costly expert annotations. While recent rubric-based approaches enhance evaluation transparency, they lack systematic quality control, yielding noisy and redundant criteria, failing to mitigate persistent biases (e.g., verbosity, position) in LLM evaluators, and creating a scalability-reliability trade-off. To address these limitations, we propose CDRRM (Contrast-Driven Rubric Reward Model), a framework built on a novel Contrast-then-Synthesis paradigm for high-quality rubric generation and guided preference judgment. CDRRM first conducts multi-dimensional contrastive profiling on preference pairs to identify causal discriminative factors, then synthesizes these insights into compact, context-aware rubrics to guide preference judg- ments. Extensive experiments on three authoritative benchmarks (RewardBench, RMBench, RMB) demonstrate that CDRRM achieves state-of-the-art performance across diverse domains and effectively mitigates aforementioned evaluation biases. Notably, our approach delivers exceptional data efficiency: training the rubric generator on only 3k high-quality samples empowers a frozen pre-trained judge model to outperform fully fine-tuned baselines. This work offers a scalable, interpretable, and data-efficient path for reward modeling.

cs.AI↗

arXiv2026

SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training

In recent years, pre-trained large language models have achieved remarkable success across diverse tasks. Besides the pivotal role of self-supervised pre-training, their effectiveness in downstream applications also depends critically on the post-training process, which adapts models to task-specific data and objectives. However, this process inevitably introduces model shifts that can influence performance in different domains, and how such shifts transfer remains poorly understood. To open up the black box, we propose the SAE-based Transferability Score (STS), a new metric that leverages sparse autoencoders (SAEs) to forecast post-training transferability. Taking supervised fine-tuning as an example, STS identifies shifted dimensions in SAE representations and calculates their correlations with downstream domains, enabling reliable estimation of transferability \textit{before} fine-tuning. Extensive experiments across multiple models and domains show that STS accurately predicts the transferability of supervised fine-tuning, achieving Pearson correlation coefficients above 0.7 with actual performance changes. Beyond this, we take an initial step toward extending STS to reinforcement learning. We believe that STS can serve as an {\color{black} interpretable} tool for guiding post-training strategies in LLMs. Code is available at https://github.com/PKU-ML/STS.

cs.AI↗

arXiv2026

AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generation

Large language model(LLM)-driven multi-agent systems(MAS) coordinate specialized agents through predefined interaction topologies and have shown promise for complex tasks such as competition-level code generation. Recent studies demonstrate that carefully designed multi-agent workflows and communication graphs can significantly improve code generation performance by leveraging collaborative reasoning. However, existing methods neither adapt topology density to task difficulty nor iteratively refine the topology within an instance using execution feedback, which leads to redundant communication and performance bottlenecks. To address these issues, we propose AgentConductor: a reinforcement learning-optimized MAS with an LLM-based orchestrator agent as its core, which enables end-to-end feedback-driven dynamic generation of interaction topologies. For each query, AgentConductor infers agent roles and task difficulty, then constructs a task-adapted, density-aware layered directed acyclic graph (DAG) topology, underpinned by two key innovations. First, we design a novel topological density function that captures communication-aware mathematical characterizations of multi-agent interactions. Second, we adopt difficulty interval partitioning to avoid excessive pruning for precise topological density upper bound measurement per difficulty level and finer-grained control. Empirically, across three competition-level and two foundational code datasets, AgentConductor achieves state-of-the-art accuracy, outperforming the strongest baseline by up to 14.6% in pass@1 accuracy, 13% in density reduction, and 68% in token cost reduction.

cs.MA↗

arXiv2026

ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models

Large language models (LLMs) transcend passive generation and act as goal-directed agents by invoking external tools. Reinforcement learning (RL) offers a principled framework for optimizing these emergent tool-use policies, yet the prevailing paradigm relies exclusively on sparse outcome rewards and lacks consideration of the particularity of tool-use tasks, inflating policy-gradient variance and resulting in inefficient training. To better understand and address these challenges, we first establish a theoretical link between policy entropy and training stability of tool-use tasks, which reveals that structured, low-entropy tokens are primary determinants of rewards. Motivated by this insight, we propose \textbf{Res}haped \textbf{T}oken-level policy gradients (\textbf{ResT}) for tool-use tasks. ResT reshapes the policy gradient through entropy-informed token reweighting, progressively upweighting reasoning tokens as training proceeds. This entropy-aware scheme enables a smooth shift from structural correctness to semantic reasoning and stabilizes convergence in multi-turn tool-use tasks. Evaluation on BFCL and API-Bank shows that ResT achieves state-of-the-art results, outperforming prior methods by up to $8.76\%$. When fine-tuned on a 4B base LLM, ResT further surpasses GPT-4o by $4.11\%$ on single-turn tasks and $1.50\%$ on multi-turn base tasks. Code is available at https://github.com/1229095296/ResT_Tool_use_LLM.git.

cs.CL↗

arXiv2026

Rethinking Personalization in Large Language Models at the Token Level

With large language models (LLMs) now performing strongly across diverse tasks, there is growing demand for them to personalize outputs for individual users. Personalization is typically framed as an additional layer on top of a base NLP task, requiring model responses to meet user-specific needs while still accomplishing the underlying task. From a token-level perspective, different tokens in a response contribute to personalization to varying degrees. Tokens with higher personalization relevance should therefore receive greater emphasis when developing personalized LLMs. However, accurately estimating such personalization degrees remains challenging. To address this challenge, we propose PerContrast, a self-contrast method that estimates each output token's dependence on user-specific information through causal intervention. Building on this mechanism, we develop the PerCE loss, which adaptively upweights tokens with higher estimated personalization degrees during training via a bootstrap procedure, enabling the model to alternate between estimating and optimizing these tokens. Experiments on multiple LLMs demonstrate that PerCE substantially improves personalization performance with minimal additional cost, achieving average gains of over 10% and up to 68.04% on the LongLaMP dataset, along with strong cross-task and cross-scenario transferability. These results highlight the importance of token-level personalization modeling and establish token-aware training as a simple yet effective paradigm for advancing personalized LLMs.

cs.CL↗

arXiv2026

Your Group-Relative Advantage Is Biased

Reinforcement Learning from Verifier Rewards (RLVR) has emerged as a widely used approach for post-training large language models on reasoning tasks, with group-based methods such as GRPO and its variants gaining broad adoption. These methods rely on group-relative advantage estimation to avoid learned critics, yet its theoretical properties remain poorly understood. In this work, we uncover a fundamental issue of group-based RL: the group-relative advantage estimator is inherently biased relative to the true (expected) advantage. We provide the first theoretical analysis showing that it systematically underestimates advantages for hard prompts and overestimates them for easy prompts, leading to imbalanced exploration and exploitation. To address this issue, we propose History-Aware Adaptive Difficulty Weighting (HA-DW), an adaptive reweighting scheme that adjusts advantage estimates based on an evolving difficulty anchor and training dynamics. Both theoretical analysis and experiments on five mathematical reasoning benchmarks demonstrate that HA-DW consistently improves performance when integrated into GRPO and its variants. Our results suggest that correcting biased advantage estimation is critical for robust and efficient RLVR training.

cs.LG↗

arXiv2026

AWPO: Enhancing Tool-Use of Large Language Models through Adaptive Integration of Reasoning Rewards

While Reinforcement Learning (RL) shows promise in training tool-use Large Language Models (LLMs) using verifiable outcome rewards, existing methods largely overlook the potential of reasoning rewards based on chain-of-thought quality for better tool utilization. Furthermore, naïvely combining reasoning and outcome rewards may yield suboptimal performance or conflict with the primary optimization objective. To address this, we propose Advantage-Weighted Policy Optimization (AWPO), a principled RL framework that adaptively integrates reasoning rewards into advantage estimation to improve tool-use performance. AWPO incorporates variance-aware gating and difficulty-aware weighting to adaptively modulate advantages from reasoning signals based on group-relative statistics, alongside a tailored clipping mechanism for stable optimization. Extensive experiments demonstrate that AWPO achieves state-of-the-art performance across standard tool-use benchmarks, significantly outperforming strong baselines and leading closed-source models in challenging multi-turn scenarios. Notably, with exceptional parameter efficiency, our 4B model surpasses Grok-4 by $16.0\%$ in multi-turn accuracy while preserving generalization capability on the out-of-distribution MMLU-Pro benchmark.

cs.CL↗

arXiv2025

ToolForge: A Data Synthesis Pipeline for Multi-Hop Search without Real-World APIs

Training LLMs to invoke tools and leverage retrieved information necessitates high-quality, diverse data. However, existing pipelines for synthetic data generation often rely on tens of thousands of real API calls to enhance generalization, incurring prohibitive costs while lacking multi-hop reasoning and self-reflection. To address these limitations, we introduce ToolForge, an automated synthesis framework that achieves strong real-world tool-calling performance by constructing only a small number of virtual tools, eliminating the need for real API calls. ToolForge leverages a (question, golden context, answer) triple to synthesize large-scale tool-learning data specifically designed for multi-hop search scenarios, further enriching the generated data through multi-hop reasoning and self-reflection mechanisms. To ensure data fidelity, we employ a Multi-Layer Validation Framework that integrates both rule-based and model-based assessments. Empirical results show that a model with only 8B parameters, when trained on our synthesized data, outperforms GPT-4o on multiple benchmarks. Our code and dataset are publicly available at https://github.com/Buycar-arb/ToolForge .

cs.AI↗

arXiv2025

From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory

Large Language Models (LLMs) based agents have demonstrated remarkable potential in autonomous task-solving across complex, open-ended environments. A promising approach for improving the reasoning capabilities of LLM agents is to better utilize prior experiences in guiding current decisions. However, LLMs acquire experience either through implicit memory via training, which suffers from catastrophic forgetting and limited interpretability, or explicit memory via prompting, which lacks adaptability. In this paper, we introduce a novel agent-centric, trainable, multi-layered graph memory framework and evaluate how context memory enhances the ability of LLMs to utilize parametric information. The graph abstracts raw agent trajectories into structured decision paths in a state machine and further distills them into high-level, human-interpretable strategic meta-cognition. In order to make memory adaptable, we propose a reinforcement-based weight optimization procedure that estimates the empirical utility of each meta-cognition based on reward feedback from downstream tasks. These optimized strategies are then dynamically integrated into the LLM agent's training loop through meta-cognitive prompting. Empirically, the learnable graph memory delivers robust generalization, improves LLM agents' strategic reasoning performance, and provides consistent benefits during Reinforcement Learning (RL) training.

cs.CL↗

arXiv2025

MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL

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.

cs.AI↗

arXiv2025

ViPER: Empowering the Self-Evolution of Visual Perception Abilities in Vision-Language Model

The limited capacity for fine-grained visual perception presents a critical bottleneck for Vision-Language Models (VLMs) in real-world applications. Addressing this is challenging due to the scarcity of high-quality data and the limitations of existing methods: supervised fine-tuning (SFT) often compromises general capabilities, while reinforcement fine-tuning (RFT) prioritizes textual reasoning over visual perception. To bridge this gap, we propose a novel two-stage task that structures visual perception learning as a coarse-to-fine progressive process. Based on this task formulation, we develop ViPER, a self-bootstrapping framework specifically designed to enable iterative evolution through self-critiquing and self-prediction. By synergistically integrating image-level and instance-level reconstruction with a two-stage reinforcement learning strategy, ViPER establishes a closed-loop training paradigm, where internally synthesized data directly fuel the enhancement of perceptual ability. Applied to the Qwen2.5-VL family, ViPER produces the Qwen-Viper series. With an average gain of 1.7% on seven comprehensive benchmarks spanning various tasks and up to 6.0% on fine-grained perception, Qwen-Viper consistently demonstrates superior performance across different vision-language scenarios while maintaining generalizability. Beyond enabling self-improvement in perceptual capabilities, ViPER provides concrete evidence for the reciprocal relationship between generation and understanding, a breakthrough to developing more autonomous and capable VLMs.

cs.CV↗

arXiv2025

Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems

Evaluating and iterating upon recommender systems is crucial, yet traditional A/B testing is resource-intensive, and offline methods struggle with dynamic user-platform interactions. While agent-based simulation is promising, existing platforms often lack a mechanism for user actions to dynamically reshape the environment. To bridge this gap, we introduce RecInter, a novel agent-based simulation platform for recommender systems featuring a robust interaction mechanism. In RecInter platform, simulated user actions (e.g., likes, reviews, purchases) dynamically update item attributes in real-time, and introduced Merchant Agents can reply, fostering a more realistic and evolving ecosystem. High-fidelity simulation is ensured through Multidimensional User Profiling module, Advanced Agent Architecture, and LLM fine-tuned on Chain-of-Thought (CoT) enriched interaction data. Our platform achieves significantly improved simulation credibility and successfully replicates emergent phenomena like Brand Loyalty and the Matthew Effect. Experiments demonstrate that this interaction mechanism is pivotal for simulating realistic system evolution, establishing our platform as a credible testbed for recommender systems research. Our codes are available at https://github.com/jinsong8/RecInter.

cs.CL↗

arXiv2025

RLFactory: A Plug-and-Play Reinforcement Learning Post-Training Framework for LLM Multi-Turn Tool-Use

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.

cs.LG↗

arXiv2025

Promoting Efficient Reasoning with Verifiable Stepwise Reward

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.

cs.AI↗

arXiv2025

SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning

Large language models (LLMs) have achieved remarkable progress in reasoning tasks, yet the optimal integration of Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) remains a fundamental challenge. Through comprehensive analysis of token distributions, learning dynamics, and integration mechanisms from entropy-based perspectives, we reveal key differences between these paradigms: SFT induces coarse-grained global changes to LLM policy distributions, while RL performs fine-grained selective optimizations, with entropy serving as a critical indicator of training effectiveness. Building on these observations, we propose Supervised Reinforcement Fine-Tuning (SRFT), a single-stage method that unifies both fine-tuning paradigms through entropy-aware weighting mechanisms. Our approach simultaneously applies SFT and RL to directly optimize the LLM using demonstrations and self-exploration rollouts rather than through two-stage sequential methods. Extensive experiments show that SRFT achieves 59.1% average accuracy, outperforming zero-RL methods by 9.0% on five mathematical reasoning benchmarks and 10.9% on three out-of-distribution benchmarks.

cs.CL↗

arXiv2025

RLAE: Reinforcement Learning-Assisted Ensemble for LLMs

Ensembling large language models (LLMs) can effectively combine diverse strengths of different models, offering a promising approach to enhance performance across various tasks. However, existing methods typically rely on fixed weighting strategies that fail to adapt to the dynamic, context-dependent characteristics of LLM capabilities. In this work, we propose Reinforcement Learning-Assisted Ensemble for LLMs (RLAE), a novel framework that reformulates LLM ensemble through the lens of a Markov Decision Process (MDP). Our approach introduces a RL agent that dynamically adjusts ensemble weights by considering both input context and intermediate generation states, with the agent being trained using rewards that directly correspond to the quality of final outputs. We implement RLAE using both single-agent and multi-agent reinforcement learning algorithms ($\text{RLAE}_\text{PPO}$ and $\text{RLAE}_\text{MAPPO}$ ), demonstrating substantial improvements over conventional ensemble methods. Extensive evaluations on a diverse set of tasks show that RLAE outperforms existing approaches by up to $3.3\%$ accuracy points, offering a more effective framework for LLM ensembling. Furthermore, our method exhibits superior generalization capabilities across different tasks without the need for retraining, while simultaneously achieving lower time latency.

cs.LG↗