Tag
This arXiv paper studies intrinsic self-correction across 29 open-weight LLMs on BoolQ, GSM8K, and Corr2Cause, finding that revision can flip previously correct answers into errors and that self-correction should be treated as a selective revision policy rather than a uniformly beneficial second pass.
This paper proposes RRDrive, a risk-aware occupancy representation for register-based end-to-end autonomous driving, which improves trajectory prediction and selection in complex scenes, achieving notable performance gains.
This paper presents a tail-risk-aware scheduling method for agentic LLM workflows that reduces tail latency by optimizing turn release decisions, achieving up to a 3.50x speedup in P95 workflow flow time under contention.
This paper presents an artificial life predator-prey model of foraging under noisy perception, showing that uncertainty-aware decision policies significantly improve survival compared to blindly trusting perceptual labels, and that agents transition from exploratory to conservative strategies as uncertainty increases.
Proposes ERAHBO, an efficient heteroscedastic Bayesian optimization method for risk-aware hyperparameter optimization in reinforcement learning, using adaptive re-sampling to improve sample efficiency over fixed-budget approaches.
This paper proposes efficient online learning algorithms for policy evaluation in MDPs with dynamic utility-based shortfall risk (UBSR) measures under linear function approximation, introducing the UBSR-TD algorithm and demonstrating its convergence and practical effectiveness.
Introduces FinInvest-GTCN, a graph-temporal-causal network for risk-aware venture capital investment decisions, achieving state-of-the-art risk-adjusted returns with explainable predictions.