9 papers
The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents
Mingguang Chen, Licheng Wang, Bo Qu
Frontier language models solve reasoning problems in a single forward pass that would have been research contributions years ago, yet fail at multi-hour tasks: losing track of earl…
The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale
Mingguang Chen, Bo Qu, Licheng Wang
Accuracy changes after language-model self-revision are usually interpreted as changes in reasoning. We show this can fail at the answer-extraction boundary, and test the failure c…
Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
Mingguang Chen, Licheng Wang, Bo Qu
AI systems increasingly participate in their own improvement: revising their outputs, adapting their own harnesses during deployment, training on data they generate, and, increasin…
Spore: Efficient and Training-Free Privacy Extraction Attack on LLMs via Inference-Time Hybrid Probing
Yu Cui, Ruiqing Yue, Hang Fu +6
With the wide adoption of personal AI assistants such as OpenClaw, privacy leakage in user interaction contexts with large language model (LLM) agents has become a critical issue.…
Towards Provably Secure Generative AI: Reliable Consensus Sampling
Yu Cui, Hang Fu, Sicheng Pan +9
Existing research on generative AI security is primarily driven by mutually reinforcing attack and defense methodologies grounded in empirical experience. This dynamic frequently g…
Can LLMs Threaten Human Survival? Benchmarking Potential Existential Threats from LLMs via Prefix Completion
Yu Cui, Yifei Liu, Hang Fu +4
Research on the safety evaluation of large language models (LLMs) has become extensive, driven by jailbreak studies that elicit unsafe responses. Such response involves information…