5 citations · 6 across the 6 of their papers we have counts for
7 papers
Beyond Trajectory Rewards: Step-level Credit Assignment for Agentic Search via Graph Modeling
Yuchen Liu, Yingjie Feng, Lixiong Qin +5
In Agentic Search, trajectory-level outcome rewards fail to quantify the behavioral contributions of individual steps, while existing step-level reward methods typically rely on co…
Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting
Muxi Diao, Lele Yang, Wuxuan Gong +6
Supervised Fine-Tuning (SFT) is the standard paradigm for domain adaptation, yet it frequently incurs the cost of catastrophic forgetting. In sharp contrast, on-policy Reinforcemen…
ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents
Zhenyu Zhang, Tianyi Chen, Weiran Xu +2
Long-horizon tasks requiring multi-step reasoning and dynamic re-planning remain challenging for large language models (LLMs). Sequential prompting methods are prone to context dri…
BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems
Andy K. Zhang, Joey Ji, Celeste Menders +31
AI agents have the potential to significantly alter the cybersecurity landscape. Here, we introduce the first framework to capture offensive and defensive cyber-capabilities in evo…
Self-Supervised Learning for Neural Topic Models with Variance-Invariance-Covariance Regularization
Weiran Xu, Kengo Hirami, Koji Eguchi
In our study, we propose a self-supervised neural topic model (NTM) that combines the power of NTMs and regularized self-supervised learning methods to improve performance. NTMs us…
SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models
Muxi Diao, Rumei Li, Shiyang Liu +4
As large language models (LLMs) continue to advance in capability and influence, ensuring their security and preventing harmful outputs has become crucial. A promising approach to…
HFT: Half Fine-Tuning for Large Language Models
Tingfeng Hui, Zhenyu Zhang, Shuohuan Wang +3
Large language models (LLMs) with one or more fine-tuning phases have become a necessary step to unlock various capabilities, enabling LLMs to follow natural language instructions…