ArXiv TLDR

Elias Lumer

3 papers · Latest:

Natural Language Processing

Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?

Research shows optimal clarification timing for long-horizon agents varies by information type, challenging "earlier is better" and highlighting task-intrinsic timing profiles.

2605.07937
Natural Language Processing

Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents

This paper introduces a framework to evaluate LLM research agents' source attribution, revealing high link validity but low factual accuracy in citations.

2605.06635
Natural Language Processing

Agentic Jackal: Live Execution and Semantic Value Grounding for Text-to-JQL

This paper introduces Jackal, an execution-based text-to-JQL benchmark, and Agentic Jackal, an LLM agent improving query accuracy by 9%.

2604.09470

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.