5 papers
Beyond Goodhart's Law: A Dynamic Benchmark for Evaluating Compliance in Multi-Agent Systems
Yiyang Zhao, Zhuo Zhang, Qingxuan Le +2
The rapid evolution of Large Language Models (LLMs) from passive assistants to autonomous, execution-capable agents has introduced critical operational risks. Most current evaluati…
EPIC-Bench: A Perception-Centric Benchmark for Fine-Grained Embodied Visual Grounding in Vision-Language Models
Haozhe Shan, Xiancong Ren, Han Dong +9
While large vision-language models (VLMs) are increasingly adopted as the perceptual backbone for embodied agents, existing benchmarks often rely on question-answering or multiple-…
Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory
Mingxi Zou, Zhihan Guo, Langzhang Liang +6
Long-horizon language agents must operate under limited runtime memory, yet existing memory mechanisms often organize experience around descriptive criteria such as relevance, sali…
CoTEvol: Self-Evolving Chain-of-Thoughts for Data Synthesis in Mathematical Reasoning
Zhuo Wang, Zhuo Zhang, Yafu Li +3
Large Language Models (LLMs) exhibit strong mathematical reasoning when trained on high-quality Chain-of-Thought (CoT) that articulates intermediate steps, yet costly CoT curation…
Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models
Yingqi Hu, Zhuo Zhang, Jingyuan Zhang +4
Federated large language models (FedLLMs) enable cross-silo collaborative training among institutions while preserving data locality, making them appealing for privacy-sensitive do…