Large language models (LLMs) are increasingly used to support consequential decisions, yet their reliability under equivalent representations of uncertainty remains unclear. Existing work has documented prompt sensitivity, cognitive biases, and confidence miscalibration, but it is still unknown whether high-stakes advi...
Yu-Yao Zhang, Ya-Kun Cui, Han Zhu et al.· 0 citations
LLM agents can exceed their authorization boundaries while pursuing user goals without an adversary. We formalize this phenomenon as authorization drift across data, tool, scope, and time, and introduce the Authorization Drift Benchmark (ADB): 648 samples across seven domains, each pairing a sufficient compliant path w...
Reinforcement learning (RL) is credited with teaching reasoning models to write {wait} before reconsidering a step, yet large RL accuracy gains do not require the word. This view can confuse what RL discovers with what a model inherits from its training data. We trace the word through open models'training histories, re...
Zhi-Zhuo Kou, Si-Zai Hou, Long Chen et al.· 0 citations
Automated alpha factor discovery is critical for modern quantitative research. While large language models (LLMs) have increasingly been integrated into quantitative workflows, existing agent-based approaches remain highly susceptible to severe backtest overfitting. To address this challenge, we propose EvoQuantLab, a...
Hao-Lin Yang, Zhi-Qiang Qian, Chu-Tian Chen et al.· 0 citations
This study evaluates rendered code in repository-level repair workflows and introduces controlled agent settings to separate unguided repository exploration from more structured repair stages, and positions rendered code as a viable but conditional compression mechanism for realistic coding agents.
Weijie Liang, Yuanfeng Song, Xing Chen et al.· 0 citations
Decoupled Proactive Safety Monitoring is formalized along three dimensions: whether to intervene, when to intervene, and what the risk is, to address proactive intervention limitations in Large Language Models.
Jia-Peng Sun, Yu-Jin Zhou, Han Zhu et al.· Proceedings of the 2026 Conf...· 0 citations
Evaluation across 18 proprietary and open-source agents uncovers a Right-Answer-Wrong-Reason effect and reveals that hallucination subclasses cluster rather than scatter, forming distinct agentic framework, legal task, and category profiles validate the diagnostic power of LexAgentHallu for evaluating agentic hallucina...
Yu-Jin Zhou, Min Zheng, Chuxue Cao et al.· 0 citations
This work introduces MINT-Safe, an open-source visual multi-turn training dataset comprising 11,270 multi-image dialogues and 500 refusal VQA pairs, and proposes TAD-Align, a dialogue safety alignment framework centered on a turn-aware dual-objective reward function.
Han Zhu, Jia-Le Chen, Chengkun Cai et al.· 0 citations
SkillProx is introduced, a proximal-gradient-inspired forward--backward framework that couples closed-loop diagnostic evolution with utility-aware proximal refinement and demonstrates the complementary effects of closed-loop diagnosis and proximal refinement.
Mingxuan Zheng, Yu-Jin Zhou, Chuxue Cao et al.· 2 citations
Omni-RewardBench is introduced, the first benchmark for comprehensive evaluation of ORMs across modalities and demonstrates that current OLLMs fall short as reward models, revealing several common failure modes such as perception failure, modality dominance failure, and cross-modal fusion failure.
Chi-Min Chan, Yujin Zhou, Pengcheng Wen et al.· Annual Meeting of the Associ...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.