12 citations · 15 across the 16 of their papers we have counts for
9 papers · 1 filter
ToolBottleneckBench: Measuring Tool-Agent Performance under Controlled Pressures and Fixed Harness Budgets
Zichuan Xu, Yuyang Dong, Makoto Onizuka +1
The success score of a tool agent reflects both its model and the budgets of the harness that runs it. We present ToolBottleneckBench, a benchmark that measures tool-agent performa…
OPTS-TTPO: Enhancing Finite-Sample Policy-Gradient Learning with Tree Search
Junyu Lu, Shichao Weng, Zhiqiang Wang +10
The policy-gradient theorem gives the exact gradient under the current policy, but finite on-policy samples may miss rare high-return trajectories. We study whether tree search imp…
Language Models Give Group-Linked Fields the Wrong Weight
Zengqing Wu, Chuan Xiao
Large language models are increasingly used to judge people, and their answers can depend on inputs correlated with a protected attribute such as race, even when that attribute is…
Predicting the scale limits of social mechanisms in agent societies
Zengqing Wu, Chuan Xiao
Societies of interacting language-model agents offer a controllable and repeatable way to study collective behaviour at scales that would be difficult to test with people. Their sc…
When Do LLMs Apply the Wrong Law? Diagnosing LLM Failures in Temporal Legal Reasoning
Yiqian Huang, Shuyuan Zheng, Yang Zhou +7
Legal reasoning requires identifying which version of a statute applies to a case, typically based on when the legally relevant events occurred rather than when the case is adjudic…
Nonlinearity-Aware LoRA: Structured Gate Adaptation under Low-Rank Constraints
Shuai Yuan, Sudong Cai, Bingzhi Chen +4
Low-rank adaptation (LoRA) is commonly viewed as an update-space approximation to full fine-tuning, yet this view is incomplete for self-gated Transformer feed-forward networks. In…
Emergent Language as an Approach to Conscious AI
Zengqing Wu, Chuan Xiao
The question of whether artificial systems can be conscious remains open, in part because existing approaches either evaluate systems against theory-derived checklists (discriminat…
Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate
Xiqi Hao, Zengqing Wu, Yu-Xuan Qiu +4
Multi-agent debate (MAD) among large language models (LLMs) is often judged by answer changes and convergence, yet these outcomes alone cannot establish that peers improved the ans…
ShapleyLaw: A Game-Theoretic Approach to Multilingual Scaling Laws
Xuyang Cao, Qianying Liu, Chuan Xiao +7
In multilingual pretraining, the test loss of a pretrained model is heavily influenced by the proportion of each language in the pretraining data, namely the \textit{language mixtu…