Multi-agent orchestration

Related

Organizations

AnthropicStanford University

Techniques

Agent skillsFormal theorem proving

Trends

• Efficiency methods cut the compute and memory models need

Items

1. Sep 11

   Skills work better as fresh-context subagents

   An empirical study finds that invoking reusable skill packages as fresh-context subagents beats loading skill instructions into the main context when packages expose clear input-output contracts, at the cost of extra coordination tokens.

2. Sep 11

   PARSER decouples reading from reasoning for agents

   Frozen per-chunk subagents read long contexts in parallel while an RL-trained lead agent runs scatter-gather rounds, beating the strongest sequential-memory baseline by 5.7 points on multi-hop QA and cutting inference latency up to 11x.

3. Aug 10

   Claude raises the Riemann zeta critical-line bound

   An unreleased research version of Claude, coordinating about 60 subagents across two Claude Code sessions and 31M output tokens, raised the proven fraction of zeta zeros on the critical line from 41.6% to 67.2%, formalized in Lean.

4. Apr 28

   Stanford's RecursiveMAS

   Casting a multi-agent system as one latent-space recursive computation, with a RecursiveLink module that passes latent state between agents instead of text, yields 8.3% higher average accuracy, 1.2-2.4x faster inference, and 34.6-75.6% fewer tokens across 9 benchmarks.