9 papers
LU-500: A Logo Benchmark for Concept Unlearning
Keyu Li, Jin Gao, Jialing Zhang +1
Concept unlearning is increasingly used to limit the reproduction of protected or unsafe visual concepts in text-to-image models. Existing evaluations, however, mostly study target…
The Cost of Knowing: A Resource-Aware Protocol for Benchmarking Hallucination Beyond Static Leaderboards
Keyu Li, Jin Gao, Dequan Wang
On standard factuality tasks, frontier models now cluster near the top of the scale. The question is therefore shifting from how factual a system is toward how much compute that fa…
AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts
Keyu Li, Junhao Shi, Yang Xiao +11
Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain f…
Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems
Keyu Li, Jin Gao, Dequan Wang
While Multi-Agent Systems (MAS) are increasingly deployed for complex workflows, their emergent properties-particularly the accumulation of bias-remain poorly understood. Because r…
daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently
Mohan Jiang, Dayuan Fu, Junhao Shi +8
While Large Language Models (LLMs) excel at short-term tasks, scaling them to long-horizon agentic workflows remains challenging. The core bottleneck lies in the scarcity of traini…
Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Training
Dayuan Fu, Yunze Wu, Xiaojie Cai +13
Large Language Model (LLM) agents have recently shown strong potential in domains such as automated coding, deep research, and graphical user interface manipulation. However, train…