Haochen Zeng, Andrew Bao, Jiajun Cheng, Chengyu Song
Proof-of-Vulnerability (PoV) input generation is a critical task in software security and supports downstream applications such as bug reproduction and patch validation. Generating a PoV input requires solving two sets of constraints: (1) reachability constraints for reaching vulnerable code locations, and (2) triggering constraints for activating the target vulnerability. Existing approaches, including directed greybox fuzzing and LLM-assisted fuzzing, struggle to efficiently satisfy these constraints. This work presents an agentic method that mimics human experts. Human analysts iteratively study code to extract semantic reachability and triggering constraints, form hypotheses about PoV triggering strategies, encode them as test inputs, and refine their understanding using debugging feedback. We automate this process with an agentic directed fuzzing framework called PBFuzz. PBFuzz tackles four challenges in agentic PoV generation: autonomous code reasoning for semantic constraint extraction, custom program-analysis tools for targeted inference, persistent memory to avoid hypothesis drift, and property-based testing for efficient constraint solving while preserving input structure. Experiments on the Magma benchmark show strong results. PBFuzz triggered 57 vulnerabilities, surpassing all baselines, and uniquely triggered 17 vulnerabilities not exposed by existing fuzzers. PBFuzz achieved this within a 30-minute budget per target, whereas conventional approaches were allotted 24 hours. Median time-to-exposure was 339 seconds for PBFuzz versus 8,680 seconds for AFL++ with CmpLog, giving a 25.6x efficiency improvement with an API cost of 1.83 USD per vulnerability. In real-world applications, PBFuzz reproduced three FFmpeg 1-day CVEs that had no public PoVs and identified three previously unknown Bento4 vulnerabilities.
Expanding Large Language Models(LLMs) to new languages is a costly endeavor, demanding extensive Continued Pre-Training(CPT) and data-intensive alignment. While recent data-free merging techniques attempt to bypass alignment by fusing a multilingual CPT-enhanced model with its instruct counterpart, they are plagued by a critical trade-off: mitigating parameter conflicts to preserve original abilities inevitably dilutes new language acquisition, and vice-versa. To resolve this conflict, we introduce , which upcycles a dense model into a Mixture-of-Experts(MoE) architecture, allocating different experts to different languages. Alignment ability is then transferred by grafting a MoE-expanded parameter delta(\Delta_{\text{instruct}}) to the CPT-enhanced base model, bypassing the complex alignment phase. Experiments demonstrate ’s superiority even against baselines with similar FLOPs or number of parameters; it improves performance on expanded languages while effectively preserving original capabilities. We further show our approach is highly applicable across different models and Post-training deltas.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Shanbo Cheng ByteDance Inc., Shuaijie She, Yu Bao ByteDance Research, Jianbing Zhang Nanjing University, Jiajun Chen, Shujian Huang Nanjing University
Large language models (LLMs) with long context windows offer the potential to translate entire documents in a single pass, yet they frequently suffer from catastrophic information distortion, undermining the strict faithfulness required for translation. This challenge is compounded by the scarcity of document-level parallel data, which makes both supervised fine-tuning and reliable evaluation prohibitively expensive. We propose LongDu, a self-supervised post-training framework that improves long-document translation reliability via round-trip consistency. Given monolingual documents, LongDu samples multiple candidate translations, back-translates each candidate, and optimizes the model to prefer translations that best reconstruct the source. To make this signal robust for long-form generation, we design a reward that filters trivial failure modes (e.g., copying and local language drift) before applying a reconstruction and fluency score, enabling stable reinforcement learning without human annotations. We additionally introduce Long-CIRT, an automatic evaluation protocol that quantifies information distortion by measuring how much a LLM’s performance degrades after a translation cycle. Across multiple base models, LongDu substantially improves information retention and translation quality, with gains that generalize beyond the training length range and to unseen target languages.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表