5 papers · 1 filter
Safe Harness Self-Evolution: A Theoretical Analysis of Feasibility and Limits
Qianshu Cai, Yonggang Zhang, Jun Nie +6
Harness self-evolution is the process by which an agent modifies its prompts, tools, code, or orchestration in response to task feedback while keeping the underlying language model…
Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence
Zhiqin Yang, Jingwen Fu, Yuhan Liu +16
Recent advances in large reasoning models (LRMs) have shown that reinforcement learning with verifiable rewards (RLVR) can substantially improve reasoning in mathematics and code,…
Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement
Chunyang Jiang, Pingping Zhang, Yuzhi Zhao +9
Multimodal large language models (MLLMs) have achieved remarkable performance across vision-language tasks, but their progress depends heavily on large-scale, high-quality multimod…
MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems
Qianshu Cai, Yonggang Zhang, Xianzhang Jia +5
Autonomous agentic systems are largely static after deployment: they do not learn from user interactions, and recurring failures persist until the next human-driven update ships a…
Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment
Zhiqin Yang, Yonggang Zhang, Wei Xue +3
Direct Preference Optimization (DPO) has emerged as a popular alternative to Reinforcement Learning from Human Feedback (RLHF), offering theoretical equivalence with simpler implem…