Conversational search systems require effective handling of context-dependent queries that often contain ambiguity, omission, and coreference.Conversational Query Reformulation (CQR) addresses this challenge by transforming these queries into self-contained forms suitable for off-the-shelf retrievers.However, existing CQR approaches suffer from two critical constraints: high dependency on costly external supervision from human annotations or large language models, and insufficient alignment between the rewriting model and downstream retrievers.We present ConvSearch-R1, the first self-driven framework that completely eliminates dependency on external rewrite supervision by leveraging reinforcement learning to optimize reformulation directly through retrieval signals.Our novel two-stage approach combines Self-Driven Policy Warm-Up to address the cold-start problem through retrievalguided self-distillation, followed by Retrieval-Guided Reinforcement Learning with a specially designed rank-incentive reward shaping mechanism that addresses the sparsity issue in conventional retrieval metrics.Extensive experiments on TopiOCQA and QReCC datasets demonstrate that ConvSearch-R1 significantly outperforms previous state-of-the-art methods, achieving over 10% improvement on the challenging TopiOCQA dataset while using smaller 3B parameter models without any external supervision.

Large language models (LLMs) have been proposed as powerful tools for detecting software vulnerabilities, where task-specific fine-tuning is typically employed to provide vulnerability-specific knowledge to the LLMs. However, existing fine-tuning techniques often treat source code as plain text, losing the graph-based structural information inherent in code.Graph-enhanced soft prompt tuning addresses this by translating the structural information into contextual cues that the LLM can understand. However, current methods are primarily designed for general graph-related tasks and focus more on adjacency information, they fall short in preserving the rich semantic information (e.g., control/data flow) within code graphs. They also fail to ensure computational efficiency while capturing graph-text interactions in their cross-modal alignment module.This paper presents CGP-Tuning, a new code graph-enhanced, structure-aware soft prompt tuning method for vulnerability detection. CGP-Tuning introduces type-aware embeddings to capture the rich semantic information within code graphs, along with an efficient cross-modal alignment module that achieves linear computational costs while incorporating graph-text interactions. It is evaluated on the latestDiverseVuldataset and three advanced open-source code LLMs, CodeLlama, CodeGemma, and Qwen2.5-Coder. Experimental results show that CGP-Tuning delivers model-agnostic improvements and maintains practical inference speed, surpassing the best graph-enhanced soft prompt tuning baseline by an average of four percentage points and outperforming non-tuned zero-shot prompting by 15 percentage points.

To provide higher data rate and larger capacity in the next generation mobile communication network, the cell size of future mobile communication system will be very small, which causes more frequent handoff between cells and different wireless systems, and also causes more signaling cost. So a new framework of hierarchical network-layer mobility management based on dynamic domain management is given to provide a more efficient location management scheme and reduce the overhead of signaling. A handoff strength measurement algorithm and a dynamic domain management scheme are presented in this paper, regarding the unequal distribution characteristics of the mobile communication subscribers and the services. The simulation result shows that flexible dynamic domain management and re-organizing can obviously reduce the signaling cost and improve the traffic quality of the mobile terminals.