an Jiaotong University)

Recent advances in large language models (LLMs) have scaled the potential for reasoning and agentic search, wherein models autonomously plan, retrieve, and reason over external knowledge to answer complex queries. However, the iterative think–search loop accumulates long system memories, leading...

LLM agents operating in open environments face escalating risks from indirect prompt injection, particularly within the tool stream where manipulated metadata and runtime feedback hijack execution flow. Existing defenses encounter a critical dilemma as advanced models prioritize injected rules du...

Automated feature generation extracts informative features from raw tabular data without manual intervention and is crucial for accurate, generalizable machine learning. Traditional methods rely on predefined operator libraries and cannot leverage task semantics, limiting their ability to produce...

Small LLMs often struggle to match the agentic capabilities of large, costly models. While reinforcement learning can help, progress has been limited by two structural bottlenecks: existing open-source agentic training data are narrow in task variety and easily solved; real-world APIs lack divers...

While model-based verifiers are essential for scaling Reinforcement Learning with Verifiable Rewards (RLVR), current outcome-centric verification paradigms primarily focus on the consistency between the final result and the ground truth, often neglecting potential errors in the derivation process...

The post-training stage of Large Language Models (LLMs) typically involves Supervised Fine-Tuning (SFT) followed by preference alignment to ensure LLM to generate safe, helpful, and instruction-aligned content. The SFT model critically serves as both the initialization and reference model for sub...

Scientific diagrams convey explicit structural information, yet modern text-to-image models often produce visually plausible but structurally incorrect results. Existing benchmarks either rely on image-centric or subjective metrics insensitive to structure, or evaluate intermediate symbolic repre...

Geographic reasoning is a fundamental cognitive capability that requires models to infer plausible locations by synthesizing visual evidence with spatial world knowledge. Despite recent advances in large vision-language models (LVLMs), existing evaluation paradigms remain largely outcome-centric,...

Personalized Large Language Models (PLLMs) aim to align model outputs with individual user preferences, a crucial capability for user-centric applications. However, the prevalent approach of fine-tuning a separate module for each user faces two major limitations: (1) storage costs scale linearly...

Large language model (LLM) agents require long-term user memory for consistent personalization, but limited context windows hinder tracking evolving preferences over long interactions. Existing memory systems mainly rely on static, hand-crafted update rules; although reinforcement learning (RL)-b...

Despite substantial advancements in aligning LLMs with human values, current safety mechanisms remain susceptible to jailbreak attacks. We attribute this vulnerability to the distributional discrepancies between alignment-oriented prompts and malicious prompts. To investigate this, and drawing in...

Large Language Models (LLMs) as automatic evaluators, commonly referred to as LLM-as-a-Judge, have also attracted growing attention. This approach plays a vital role in aligning LLMs with human judgments, providing accurate and reliable assessments. However, LLM-based judgment models often exhibi...

With the widespread deployment of large language models (LLMs), existing safety benchmarks remain largely focused on explicitly harmful content, overlooking context-dependent expressions such as dogwhistles, the language that conveys harmful intent while appearing benign on the surface. To addres...

While Supervised Fine-Tuning (SFT) is the prevailing method for equipping Large Language Models (LLMs) with function calling capabilities, its effectiveness is often compromised by two critical challenges: 1) Imbalanced Training Signals , where lengthy Chain-of-Thought (CoT) reasoning tokens domi...

Large language models (LLMs), despite their powerful capabilities, suffer from factual hallucinations where they generate verifiable falsehoods. We identify a root of this issue: the imbalanced data distribution in the pretraining corpus, which leads to a state of “low-probability truth” and “hig...

Large language models have demonstrated strong reasoning capabilities in general knowledge question answering. However, their ability to handle temporal information remains limited. To address this limitation, existing approaches often design time-sensitive reasoning pipelines that rely on extern...

Diagnostic prediction and clinical reasoning are critical tasks in healthcare applications. While large language models have shown strong capabilities in commonsense reasoning, they still struggle with diagnostic reasoning due to limited domain knowledge. Existing approaches often rely on interna...

Multi-hop Question Answering (MHQA) aims to answer questions that require multi-step reasoning. The complexity of user queries, coupled with potential knowledge deficiencies in Large Language Models (LLMs), gives rise to two pivotal challenges that underpin the performance on this task: the corre...

Recent advancements in large language models (LLMs) have catalyzed the rise of reasoningintensive inference paradigms, where models perform explicit step-by-step reasoning before generating final answers. While such approaches improve answer quality and interpretability, they incur substantial co...

Generative recommendation (GR) has shown great promise in industrial applications, particularly for candidate generation and end-to-end recommendations. However, existing GR training paradigms suffer from two fundamental mismatches with real-world deployment requirements. First, they optimize for...

Multi-hop question answering (MHQA) enables accurate answers to complex queries by retrieving and reasoning over evidence dispersed across multiple documents. Existing MHQA approaches mainly rely on iterative retrieval-augmented generation, which suffer from the following two major issues. On one...

Cross-domain Sequential Recommendation (CDSR) has been proposed to enrich user-item interactions by incorporating information from various domains. Despite current progress, the domain imbalance issue and domain transition issue hinder further development of CDSR. The former presents a phenomenon...

Large vision-language models (LVLMs) have shown significant progress in video understanding, but they struggle to scale to long videos due to limited context windows. Existing methods reduce input dimensionality via frame sampling and feature compression, yet discard details and incur high comput...

Cognitive diagnosis aims to infer students' mastery levels over knowledge components from their learning interactions, supporting personalized education applications. However, existing models encode responses as binary correctness labels, discarding information about which specific option a stude...

Deep-research agents are capable of executing multi-step web exploration, targeted retrieval, and sophisticated question answering. Despite their powerful capabilities, deep-research agents face two critical bottlenecks: (1) the lack of large-scale, challenging datasets with real-world difficulty...

Deep Research agents driven by LLMs have automated the scholarly discovery pipeline, from planning and query formulation to iterative web exploration. Yet they remain constrained by a static, ''one-size-fits-all'' retrieval paradigm. Current systems fail to adaptively adjust the depth and breadth...