arXiv:2608.20807v1 Announce Type: new Abstract: Environmental exposures such as air pollution and greenness have been associated with affective and…
Category: AI
Certified Multi-Turn Robustness for LLM Safety via Compositional Bounds and Safety Persistence
arXiv:2608.20820v1 Announce Type: new Abstract: Large language models (LLMs) are vulnerable to multi-turn jailbreak attacks that progressively manipulate…
CAS: Conformalized Agentic Search via Adaptive Retrieval and Policy Weighting
arXiv:2608.20771v1 Announce Type: new Abstract: Search Agents face a severe reliability crisis during reinforcement learning (RL) fine-tuning. Heuristic…
Automated Trajectory Evaluation for Mobile Agents via Step-Level Consequence Reasoning and Aggregation
arXiv:2608.20797v1 Announce Type: new Abstract: Evaluating language-guided mobile agents has recently shifted from rule-based to model-based approaches to…
Knowing but Not Saying: Preventing Factual Access Failures in LLM SFT via Recall-Anchored Distillation
arXiv:2608.20794v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) can degrade factual behavior outside the target domain. This degradation is…
Structure for Reading, Prose for Writing: Asymmetric Structural Conditioning in Multi-Agent Document Authoring
arXiv:2608.20786v1 Announce Type: new Abstract: Multi-agent pipelines that author formal documents must both read a requester’s forms and write against…
Beyond Endpoint Gains: A Weight-Delta Audit of Medical Specialization
arXiv:2608.20768v1 Announce Type: new Abstract: Specialist language models are usually understood through endpoint gains: the generalist scores lower, the…
Continuous-Time Quantum Walks based Graph Neural Network
arXiv:2608.20738v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) are widely used on graph-structured data, but most suffer from two key…
Is Multimodal Speculative Decoding Ready for Diffusion-Based Parallel Drafting? A Survey and Empirical Diagnosis
arXiv:2608.20743v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation by allowing a lightweight drafter to propose…
ForeTime-VLA: Causal Future-Token Distillation from a World Action Model for Conveyor-Belt Manipulation
arXiv:2608.20735v1 Announce Type: new Abstract: Manipulating moving objects requires a policy to anticipate contact events, yet vision-language-action…