arXiv subjects

Minhao Sun

Publications and source records attributed to Minhao Sun.

5 recordsLinked to original sources

arXiv2026

Same Trajectory, Different Knowledge: Information-State-Aware On-Policy Distillation for Search Agents

On-policy distillation trains search agents with teacher feedback on student-generated trajectories. Recent methods augment the teacher's context with supporting evidence, reference answers, or hindsight information. However, this privileged information may allow the teacher to rely on facts that the student cannot reliably recover from its current state. The resulting information-state mismatch can lead the teacher to undervalue retrieval that helps the student establish those facts. To address this mismatch, we introduce Information-State-Aware Distillation (ISA-Distill), which adapts teacher feedback to the student's factual recoverability. ISA-Distill estimates how reliably the student can recover action-relevant knowledge and derives teacher feedback for the same sampled action from two complementary views. The fact-use view supplies the teacher with the relevant fact, producing feedback that guides the student in using knowledge. The evidence-seeking view instead presents the information need, producing feedback that guides the student in acquiring supporting evidence. The two signals are weighted toward fact use when recoverability is high and toward evidence seeking when it is low, and the resulting feedback guides policy optimization. Experiments across diverse QA benchmarks and model scales demonstrate improved answer accuracy and retrieval efficiency. Our code and model checkpoints will be open-sourced.

cs.IR↗

arXiv2026

Search When Needed, Proceed When Reliable: Metacognitive Reliability Supervision for Efficient Agentic Search

Efficient agentic search requires large language models (LLMs) to determine whether they can reliably proceed with their current knowledge or need additional external evidence. Supervision based on final-answer correctness or trajectory-level feedback evaluates realized trajectory performance. However, observed trajectory performance is jointly shaped by stochastic generation, retrieval quality, and downstream reasoning. Such signals therefore provide only indirect evidence of how reliable the current decision state was and how retrieved evidence changed its reliability. An effective reward should encourage search when external information is needed and favor searches that contribute to the answer. To this end, we propose a metacognitive framework for training LLMs to make search decisions based on the reliability of their intermediate reasoning states. Our framework estimates the reliability of local conclusions to distinguish whether the current information supports proceeding without search from how much retrieved evidence improves that reliability. The current-state reliability score assesses whether the model can proceed without search. The search-action score measures how retrieved evidence changes estimated reliability. Together, these scores define a reliability-aware process reward for Group Relative Policy Optimization (GRPO), providing finer-grained supervision for search and no-search behavior. Experiments across seven question-answering benchmarks demonstrate that our method achieves a better accuracy-efficiency trade-off than strong agentic-search baselines. Our code and model checkpoints will be open-sourced.

cs.IR↗

arXiv2026

RACE: Learning Multimodal Search through Referential Abstraction and Compositional Evidence

Training multimodal search agents requires tasks that make visually grounded search necessary for determining the answer. Textual identity clues and unused target evidence allow shortcuts in synthetic questions, weakening supervision for visual search and evidence integration. We propose RACE, an image-conditioned task synthesis framework that constructs dependencies from images to targets and from target-specific evidence to answers. Referential Abstraction (RA) replaces identity-revealing text with specific visual references or ambiguous relational references resolved by searching among depicted candidates. Compositional Evidence (CE) links retrieved facts about multiple entities in one image or entities from different images into joint questions whose answers require every designated contribution. Both operations also apply to images found during search, allowing new visual observations to determine subsequent search targets or supply answer evidence. Fine-tuning Qwen3.5-27B on only 12K teacher-generated trajectories from RACE raises average accuracy across ten multimodal benchmarks from 53.5 to 56.0, a relative improvement of approximately 4.7% over the matched base agent. Our code, data, and model will be publicly available.

cs.CV↗

arXiv2026

SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task

Recent advances in large language models (LLMs) have enabled search agents to autonomously tackle complex tasks across extended search and reasoning horizons. However, training effective search agents remains challenging due to the lack of scalable and long-horizon tasks, and the difficulty of evaluating and correcting intermediate reasoning and tool-use behaviors. We introduce SearchArt, a scalable framework for training long-horizon search agents through verification-driven task synthesis and a multi-stage post-training pipeline. SearchArt constructs large-scale datasets for complex search-, research- and user-oriented tasks by synthesizing diverse information-seeking QA pairs and corresponding search trajectories from web documents and automatically generated evidence graphs. To ensure the reliability of the synthesized data, we design a verification pipeline that jointly evaluates QA consistency, trajectory quality, and the relevance of retrieved evidence. The verified trajectories are subsequently used in a multi-stage training process comprising supervised fine-tuning and reinforcement learning-based policy optimization. Search agents trained with SearchArt exhibit adaptive search planning, iterative evidence aggregation, and complex reasoning over extended interaction horizons. Experimental results demonstrate that, with only (Qwen3.5-) 27B parameters, SearchArt scores 74.39 on BrowseComp-ZH, 70.06 on BrowseComp, and 52.55 on Deepresearch-bench, matching or surpassing frontier closed-source agents on both deepsearch and deepresearch benchmarks.

cs.IR↗

arXiv2026

UniPAR: A Unified Framework for Pedestrian Attribute Recognition

Pedestrian Attribute Recognition is a foundational computer vision task that provides essential support for downstream applications, including person retrieval in video surveillance and intelligent retail analytics. However, existing research is frequently constrained by the ``one-model-per-dataset" paradigm and struggles to handle significant discrepancies across domains in terms of modalities, attribute definitions, and environmental scenarios. To address these challenges, we propose UniPAR, a unified Transformer-based framework for PAR. By incorporating a unified data scheduling strategy and a dynamic classification head, UniPAR enables a single model to simultaneously process diverse datasets from heterogeneous modalities, including RGB images, video sequences, and event streams. We also introduce an innovative phased fusion encoder that explicitly aligns visual features with textual attribute queries through a late deep fusion strategy. Experimental results on the widely used benchmark datasets, including MSP60K, DukeMTMC, and EventPAR, demonstrate that UniPAR achieves performance comparable to specialized SOTA methods. Furthermore, multi-dataset joint training significantly enhances the model's cross-domain generalization and recognition robustness in extreme environments characterized by low light and motion blur. The source code of this paper will be released on https://github.com/Event-AHU/OpenPAR

cs.CV↗