6 papers
Harness-agnostic detection and immunization of reward hacking in self-evolving language models
Rongxin Yang, Yang Liu, Shang Luo +10
Self-evolving language models improve by proposing candidate updates and keeping whatever raises a visible score. When that score is an imperfect proxy for the capability one actua…
Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents
Chenhao Wu, Haoxuan Jia, Yang Liu +11
Large language model agents are increasingly deployed as autonomous loops. Starting from one human goal, such a system repeatedly discovers work, plans, executes tool calls, verifi…
Hindsight Memory-PRM: Supervising Memory Management with Auditable Hindsight Credit
Haoxuan Jia, Yang Liu, Yingguang Yang +14
Memory operations of long-horizon LLM agents are hard to supervise: an operation's value is unobservable when it is taken. But they are special -- they leave machine-readable evide…
OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories
Yibing Liu, Yangze Liu, Xiaolong Yin +4
Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external write…
FinHarness: An Inline Lifecycle Safety Harness for Finance LLM Agents
Haoxuan Jia, Yang Liu, Bin Chong +10
Finance LLM agents must simultaneously block prompt-induced unauthorized actions and approve legitimate multi-step business workflows. However, boundary filters often miss irrevers…
Reducing Detail Hallucinations in Long-Context Regulatory Understanding via Targeted Preference Optimization
Yang Liu, Bin Chong, Yuhan Lin +7
Large language models (LLMs) frequently produce \emph{detail hallucinations} when processing long regulatory documents, including subtle errors in threshold values, units, scopes,…