…We propose SkillAdaptor, a training-free step-level skill adaptation framework with explicit failure attribution , and it can plug into OpenClaw-class agent harnesses. Given a failed trajectory, SkillAdaptor identifies a first…
…confident in their own answers than in identical answers provided by a user. Extensive experiments across six recent open-weight LLMs, three benchmarks, and three confidence elicitation methods show that models assign…
…They supply unambiguous detailed instructions and solely reward execution correctness, so an agent that makes a lucky guess for a missing requirement will score identically to one that would have asked to…
…We identify that its chunk-level synthesis and few denoising steps are intrinsically suited for TTS, significantly lowering computational overhead while enabling fine-grained temporal control. Driven by this insight, we introduced…
…We argue that this default itself is part of the problem and identify a teacher-side exposure mismatch : when the teacher conditions on reasoning far beyond the student's current competence, the…
…To obtain reliable self-supervision for online learning , we identify a Generative-Discriminative Gap within LVLMs, where models exhibit higher accuracy on discriminative verification than open-ended generation. Leveraging this capability, we…
…generation compute, and substantially improves overall reasoning performance. View arXiv page View PDF Add to collection Community Trace tournaments can provide denser reward signals when verifier rewards are identical. Neat paper. The…
…Using this lens, we identify three technical axes. First, reward design spans eight families, including orchestration rewards for parallelism speedup, split correctness, and aggregation quality. Second, reward and credit signals attach to…
…2D sticker generators, our MuSS-augmented model achieves state-of-the-art narrative effectiveness and cross-shot identity preservation. View arXiv page View PDF GitHub 13 Add to collection Community TL;DR…
…Formally, we prove that constraining the learned field to be conservative reduces hypothesis complexity and tightens out-of-distribution generalization bounds. We further characterize the identifiability of recovered rewards and bound how…