arXiv AI July 16, 2026 By Zhaohui Wang

Uncertainty-Aware Sequential Decision Rules for Event-Triggered LLM Invocation in Streaming Systems

arXiv:2607. 13048v1 Announce Type: cross Abstract: Streaming inference pipelines increasingly pair lightweight fast models with Large Language Models (LLMs) that provide rich semantic understanding at substantial cost.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

llms

arXiv AI

Sep 15

When Should a World Model Move? Loss-Conditioned State Execution

The paper introduces loss‑conditioned state execution, a model‑agnostic technique that decides whether to apply a world model’s proposed state change or keep the current state based on whether the change reduces downstream loss. It formalizes state movability as the existence of a loss‑reducing feasible correction and constructs loss‑specific proposals from predictive distributions, executing them only when a groupwise lower confidence bound on loss improvement is positive. Experiments on forecasting and dynamics benchmarks show that the method accepts updates for a subset of cases, achieving lower bounded loss than persistence or always executing the proposal, and highlights that event predictability and loss‑based decisions must be evaluated separately.

By Jintao Xu, Zhengyu Chen, Ben Zhang, Yongzhi Qi, Jianshen Zhang

benchmarks

arXiv AI

Jun 30

SCARCE: Scalable Cascade Analysis for Rare-event Characterisation via Embeddings

arXiv:2606. 29623v1 Announce Type: new Abstract: Rare events govern the safety profile of modern AI systems, yet their probabilities are extremely difficult to estimate: direct Monte Carlo requires prohibitive sample budgets.

By Yingjie Wang, Yi Dong, Edmund Lau, Jie Meng, Taylor T Johnson, Xiaowei Huang

llms rag safety

arXiv AI

Jun 24

Learning to Trigger: Reinforcement Learning at the Large Hadron Collider

arXiv:2606. 23993v1 Announce Type: cross Abstract: High-throughput scientific facilities such as the Large Hadron Collider depend on real-time event filtering (\textit{triggering}) under tight constraints on bandwidth, latency, and storage.

By Zixin Ding, Shaghayegh Emam, Giovanna Salvi, Cecilia Tosciri, Abhijith Gandrakota, Jennifer Ngadiuba, Nhan Tran, Christian Herwig, David W. Miller, Yuxin Chen

agents reinforcement-learning fine-tuning efficiency benchmarks

arXiv AI

Jul 23

CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning

arXiv:2607. 20129v1 Announce Type: new Abstract: Quantized small autoregressive reasoning models can enter long, repetitive, or unproductive trajectories, yet inference-time compute is usually allocated without observing how a trajectory develops.

By El Hassane Ettifouri, Ayoub Belfatmi, Mahaman Sanoussi Yahaya Alassan, Walid Dahhane

llms efficiency

arXiv AI

Jul 8

Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade

arXiv:2607. 06503v1 Announce Type: new Abstract: Large language model (LLM) agents solving multi-step tasks frequently commit to trajectories that are doomed to fail, yet continue to consume substantial inference compute before the failure becomes observable.

By Kai Ruan, Zihe Huang, Ziqi Zhou, Qianshan Wei, Xuan Wang, Hao Sun

llms agents

arXiv AI

Sep 15

MemRiskBench: Trace-Aware Risk-Preserving Evaluation for Long-Horizon LLM Agents

arXiv:2609.14976v1 Announce Type: new Abstract: Long-horizon LLM agents accumulate memory across sessions, creating sparse but high-impact risks: stale facts, conflicting updates, cross-user leakage,...

By Jianhua Jiang, Dongbo Yuan, Weihua Li

llms agents efficiency benchmarks

One email a morning, machine-written

Related stories

When Should a World Model Move? Loss-Conditioned State Execution

SCARCE: Scalable Cascade Analysis for Rare-event Characterisation via Embeddings

Learning to Trigger: Reinforcement Learning at the Large Hadron Collider

CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning

Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade

MemRiskBench: Trace-Aware Risk-Preserving Evaluation for Long-Horizon LLM Agents