Agent skills provide frozen large language model (LLM) agents with reusable procedural guidance, and recent work shows that such skills can be optimized with ground-truth (GT) feedback. Many applications, however, lack GT labels, task scores, rewards, or reliable task-specific evaluators. We therefore introduce Self-Supervised Skill Optimization (SSO), a comparative framework that learns a reusable skill from unlabeled task instances alone. At each step, SSO runs the current skill on an unlabeled batch, uses a subset of the resulting executions to generate complete skill probes, and runs the probes on the same batch. An LLM judge compares the resulting answers, trajectories, artifacts, or terminal states. A separate behavior extractor identifies behavioral differences without seeing the judge's decisions. SSO uses these decisions to aggregate evidence for and against the observed behaviors across instances. It then ranks the behaviors by the resulting evidence and renders a new complete skill from the highest-ranked behaviors. The update is accepted only if the new skill outperforms the current one on an unlabeled validation set. SSO outperforms existing GT-free prompt optimizers on both closed-ended and open-ended tasks. On closed-ended benchmarks, it approaches and sometimes exceeds the strongest GT-based skill optimizer without using any GT feedback.
Siran Peng, Cui-Yu Yang, Tianyu Fu et al.· arXiv.org· 0 citations
The results show that evolving skill memory is not merely an inference-time plug-in: it changes policy learning and the future training distribution while retaining value as optional external memory.
Zenghuang Fu, Zhaoyang Li, Qiuyuan Ai et al.· arXiv.org· 1 citation
WebRetriever is introduced, a large-scale benchmark encompassing 800 websites and 1,550 tasks across diverse domains, including consumer, professional, and enterprise sectors, with comprehensive coverage of user intent patterns, and NavEval (Navigation Evaluation), a novel LLM-as-Judge framework that leverages rich interaction context beyond visual screenshots.
This work systematically characterize the implicit biases introduced by low-rank adaptation during alignment and establishes two theorems showing that low-rank alignment induces preferences for parameter subspaces with flat gradients and feature subspaces robust to perturbations, providing a principled explanation for the observed structure-preserving behavior.
Mingjia Shi, Shuo Wang, Xiaobo Wang et al.· arXiv.org· 0 citations
LiLa-WAM is proposed, a lightweight world-action model that reasons about the future in a compact latent space and can be trained end-to-end on a single 24GB GPU and the Visual Transition Token (VTT), a language-free task representation that encodes each task as a direction in visual feature space.
Fan Yang, Yu-Ting Su, Xiaobo Wang et al.· 4 citations
CoEvoKG is introduced, a framework that turns a knowledge graph into both a source of verifiable training tasks and a persistent evidence memory for agent evolution, closing the loop between model self evolution and knowledge accumulation.
Zhaoyang Li, Zenghuang Fu, Qiuyuan Ai et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
