arXiv:2609.36655v1 Announce Type: new Abstract: Continual test-time adaptation (CTTA) adapts a source model to an unlabeled test stream whose distribution may change over time. Existing TTA methods o...
arXiv:2606. 15569v1 Announce Type: new Abstract: Test-time training (TTT) adapts a pretrained model to each prompt via parameter updates, improving accuracy under pretraining-to-test distribution shifts.
arXiv:2610. 12232v1 Announce Type: new Abstract: Test-time adaptation (TTA) methods for time-series forecasting update a deployed model, or a small adapter around it, from incoming ground truth.
arXiv:2610.16129v1 Announce Type: cross Abstract: Deploying LLM agents in non-stationary environments requires continually revising their instructions as the task drifts, yet rewriting after every re...
arXiv:2610.07946v1 Announce Type: cross Abstract: Visual disruptions can arise while a robot is executing a task, leaving a vision-language-action (VLA) policy to respond without knowing the disrupti...
arXiv:2606. 23957v1 Announce Type: new Abstract: Learning Koopman operators with autoencoders enables linear prediction in a latent space, but long-horizon rollouts often drift off the learned manifold, leading to phase and amplitude errors on systems with switching, continuous spectra, or strong transients.
arXiv:2608. 01130v1 Announce Type: new Abstract: A broad range of models face the mismatch where they are updated through trajectory losses but are evaluated by downstream task reward.
The study introduces RegimeShift‑Surrogates, a streaming benchmark that tests surrogate models across eight tasks and multiple regimes. It compares revalidation—choosing the model with lowest current‑window validation loss—to stateful adaptive controllers and finds that revalidation consistently outperforms stateful methods, achieving lower mean log regret in most task‑scenario combinations. The results suggest that fresh validation evidence is more valuable than carrying over past evidence when dealing with distribution shifts.
arXiv:2605.06908v2 Announce Type: replace-cross Abstract: Adaptive test-time compute for LLM agents aims to invoke extra computation only when it improves performance. Existing methods typically use...
arXiv:2608.30427v1 Announce Type: cross Abstract: Speculative decoding speeds up generation with an efficient draft model (drafter) that proposes tokens for a target model to verify in one pass, pres...
arXiv:2607. 08837v1 Announce Type: cross Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers.
HERO is a method that improves large language models for program generation by combining offline and test‑time harness optimization. It learns reusable prompt updates from execution‑verified successes and failures, validates candidate revisions before adoption, and then refines each generated code instance using execution feedback. On four SQL, Cypher, and Python benchmarks, HERO achieves the best offline performance, raising pass@1 by 7.6 points over the initial prompt and adding another 2.0 points through test‑time refinement while improving execution efficiency.