6 papers
Beyond Perfect Teammates: Multi-Agent Collaboration with Unreliable Colleagues
Chen Huang, Yiyang Zhang, Yuhao Wu +2
LLM-based multi-agent collaboration is increasingly used to solve complex tasks by dividing work among specialized agents and integrating complementary expertise. Yet existing syst…
SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers
Shaowen Wang, Ge Zhang, Kairong Luo +6
Looped Transformers increase effective depth by iterating a shared block of layers, but most evaluations compare at fixed model size, conflating architectural advantage with extra…
Bait-and-Recover: Poisoning Internal Refusal Signals to Defend LLMs against White-Box Editing Jailbreaks
Tian Gao, Zhipeng Xie, Yuhao Wu +2
Open-weight large language models face a low-cost white-box threat from representation engineering attacks. Attackers can estimate refusal directions and search for projection-matr…
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
Yuhao Wu, Jingyuan Zhang, Jiajun Shi +16
As agents move from research prototypes to deployed tools, their capability increasingly depends on model-external execution infrastructure, commonly termed the agent harness. Chan…
Aspire: Can Models Self-Evolve from Vague Goals?
Yuhao Wu, Jingyuan Zhang, Jiajun Shi +18
Many important forms of human learning begin with a vague goal, such as "become a better physicist" or "improve at research." Learners must interpret the goal, identify capability…
S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?
Jiajun Shi, Siyuan Tao, Yuhao Wu +18
Large language models (LLMs) increasingly interact with external environments and accumulate substantial behavioral experience, yet existing agent benchmarks largely evaluate them…