Skip to content

Author

Yu-Long Huang

6 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Recasting the Destroy Step of Large Neighborhood Search as Dense Segmentation

Large neighborhood search improves an incumbent by releasing selected variables and repairing the resulting subproblem under a time limit. FOVEA casts variable selection as dense semantic segmentation on a fixed $128\times128$ canvas. A small U-Net reads twelve semantic channels and predicts cell scores, which are deco...

Yang Liu, Yu-Long Huang, Jian-Sheng Zhang et al. · 0 citations
Preprint Oct 2026

The Window Is in the Reasoning: When LLM Agents Decide to Follow Prompt Injections

This work tests an assumption that whether an agent follows an injection is settled when the injection is read, and shows that the decision forms gradually as the agent reasons, which lowers the attack success rate of Qwen3 but raises it for two other models.

H. Jia, Yang Liu, Bin Chong et al. · 1 citation
#artificial intelligence Preprint Sep 2026

Harness-agnostic detection and immunization of reward hacking in self-evolving language models

This work introduces HackProbe, a monitor that attaches to an arbitrary self-evolving loop through two black-box hooks, with no access to weights or activations, and proves a detectability bound that converts a target error rate into an explicit probe-size budget, and delimit what probe rotation does and does not buy.

Rong-Xin Yang, Yang Liu, Shang Luo et al. · 2 citations
#natural language process... Preprint Aug 2026

Hindsight Memory-PRM: Supervising Memory Management with Auditable Hindsight Credit

Hindsight Memory-PRM exploits this audit trail twice: offline to train an operation-conditioned memory-utility critic, and online, where retrievals, citations, and one controlled deletion-and-reanswer per probe settle an intervention-calibrated entry-level presence credit.

H. Jia, Yang Liu, Ying-Guang Yang et al. · 0 citations
#artificial intelligence Preprint Aug 2026

Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents

LoopHarness is presented, which restores a persistent, non-decaying safety state at the loop level at the loop level, and gives a complete evaluation protocol on native Agent-SafetyBench tasks with paired clean and attacked episodes, an outer-state attack suite whose decisive evidence exists only across iterations, per...

Chenmin Wu, H. Jia, Yang Liu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.