LLM Digest

Story

arxiv_cs_ai · Nov 12, 2026 · paper

Source brief

From Delegation to Coordination: Learning Efficient Multi-Agent Deep Research

arxiv.orgNov 12, 2026
original source linked

In brief

Multi-agent deep-research systems use delegation to parallelize search and keep long tool traces out of the main agent's context. Yet delegation helps only when task allocation and subtask execution are coordinated: t...

Feed lens

agenteval

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

From Delegation to Coordination: Learning Efficient Multi-Agent Deep Research

Earlier in this thread 4 items

Coordinated Mixed-Precision KV Cache Quantization for Efficient LLM-based Multi-agent Systems

MDSKILL: Learning to Internalize Skill Memory through Multi-View Distillation for Efficient Dynamic Agent Self-Evolution

How We Optimized Browser Use for Deep Agents

Is Your Long-Horizon Benchmark Really Deep? Measuring and Synthesizing Depth in Terminal Tasks