Tracked topic
…We propose CorVer (Corpus Verify), a lightweight, plug-in-ready process reward that replaces neural verifiers with a corpus-grounded signal derived from Wikipedia co-occurrence statistics . CorVer assigns sentence-level credit…
…Second, the token-level logit signal itself is brittle, depending on a narrow overlap of plausible next tokens between teacher and student, and prone to amplifying degenerate patterns such as repetition loops…
…To address this challenge, we propose Gated Cropped Attention-Delta steering (GCAD), which extracts steering signals from system-prompt contributions to self-attention and applies them with token-level gating . Across persona…
…AI-generated summary Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coarse supervision for long-horizon interaction. On…
…We introduce Claw-Eval-Live, a live benchmark for workflow agents that separates a refreshable signal layer, updated across releases from public workflow-demand signals, from a reproducible, time-stamped release snapshot…
…By inserting an SAE module into a pretrained VLM and training it with standard reconstruction objectives , we find that the learned sparse latent features naturally capture attack-relevant signals. These features enable…
…Our results show that BenchEvolver can convert saturated benchmarks into frontier-level evaluation suites and reusable training signal . View arXiv page View PDF Project page GitHub 6 Add to collection Community Static…
…supervised signal, on-policy signal , and decaying weights on the few-shot SFT dataset to prevent overfitting from multiple-epoch training. On several benchmarks, FEST outperforms baselines with magnitudes less SFT data…
…Recent OPD methods increasingly focus on selecting which trajectories to learn from, which tokens are most informative, and which supervision signals are most reliable. Motivated by this trend, we rethink optimization granularity…
…Prior work has explored LLM-augmented, multimodal, and text-enhanced approaches to sequential recommendation, and while some methods partially combine semantic, acoustic, or engagement signals, none jointly model all three within a…