LLM Digest

Story

arxiv_agent_systems_research · Nov 9, 2026 · paper

Source brief

Dependable Long-Horizon LLM Agents: A Trajectory-Centered Empirical Study of Where Errors Enter and Which Controls Reach Them

arxiv.orgNov 9, 2026
original source linked

In brief

When an LLM agent fails part-way through a long task, the usual analysis records a symptom: a failure-mode label, or the agent and step judged responsible. It does not say where the error entered, which state carried it to the symptom, whether anything in the trajectory contradic

Read the original at arxiv.org →Open in live feed Read that day’s brief

Dependable Long-Horizon LLM Agents: A Trajectory-Centered Empirical Study of Where Errors Enter and Which Controls Reach Them

Earlier in this thread 4 items

Aligning Language Models with General Preferences: An Empirical Study of Direct Nash Optimization

An Empirical Study of Recent Large Language Models for Knowledge Graph to Text Generation on Standard Benchmarks

How Well Do Decision Models Transfer to Vietnamese? An Empirical Study of Text Classification

Tracing Hallucinations in LLM Reasoning for UML Class Diagram Generation: An Empirical Taxonomy and Mitigation Study