5 papers · 1 filter
Self-Evolving Agents through Privileged Retrospective Distillation
Yuhang Zhou, Yifan Wu, Bo Peng +5
Self-evolving agents aim to improve from their own experience rather than remain fixed after deployment, but naturally collected trajectories often lack ground-truth solutions or v…
Discovered, Not Designed: Population Evolution for Collaborative and Compute-Intensive Model Discovery
Bo Peng, Lizhu Zhang, Yuhang Zhou +5
LLM-driven evolution enables iterative model development, but two practical goals remain underexplored: finding model designs that transfer across related tasks and sustaining impr…
OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification
Yuhang Zhou, Lizhu Zhang, Yifan Wu +5
On-Policy Distillation (OPD) trains a student model on its own generative trajectories under dense token-level feedback from a stronger teacher, mitigating both the off-policy dist…
Multi-Token Residual Prediction
Yufeng Xu, Zishuo Bao, Qian Wang +6
Diffusion Language Models (DLMs) generate text by iteratively denoising masked token sequences, offering a tradeoff between parallelism and quality compared to autoregressive model…
PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents
Minghao Yan, Bo Peng, Benjamin Coleman +11
Large language models have become drivers of evolutionary search, but most systems rely on a fixed, prompt-elicited policy to sample next candidates. This limits adaptation in prac…