arXiv AI
Local Work, Global Progress: A Convergence Theory of AI Agent Collaboration
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 7
Verifying Coordination in Parallel Coding Agents: NP-Bench and a Scheduling Planner
The paper introduces NP‑Bench, a benchmark and a proactive scheduling planner that coordinates parallel large‑language‑model coding agents. By partitioning work scopes and ordering merges ahead of time, the planner improves clean‑integration rates from 1/9 to 9/9 and eliminates merge conflicts, outperforming both no‑coordination and reactive‑detection baselines. It also demonstrates that cross‑session memory can eliminate repeated mistakes and that routing facts to agents does not improve long‑context accuracy at scale.
arXiv AI
Oct 23
Parallel AI Agent Collaboration as Graph-Structured Distributed Block Optimization
arXiv:2610. 30074v1 Announce Type: cross Abstract: Parallel AI agents can produce useful local edits yet degrade a shared solution when their edits are combined.
arXiv AI
1d ago
MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability
MASBench is a benchmark for evaluating large language model (LLM)-based multi‑agent systems (MAS) under partial observability, a realistic constraint where agents only see limited environmental information. The benchmark is structured into three progressive task categories—Reasoning, Scheduling, and Game—and assesses three collaboration mechanisms: Protocol, Memory, and Routing. It provides deterministic evaluation metrics such as performance score, communication cost, and cost effectiveness, and includes empirical results across various LLM backbones to guide effective MAS design.
arXiv AI
Sep 21
Scaling Discovery through Test-Time Communication
The paper demonstrates that test‑time communication among agents can significantly outperform independent parallel attempts on complex tasks. In experiments on the ARC‑AGI‑3 benchmark, a team of $k$ communicating agents matched the success rate of $4k$ independent agents, with the advantage growing as the team size increased. The study also shows that communication enables solving tasks that no single agent can solve, and that these benefits transfer to research‑oriented problems such as polyomino packing and MNIST classifier compression, where communicating agents surpassed prior best scores.
arXiv AI
Aug 25
The Interaction Tax: When Communication Erases Diversity in Multi-Agent Teams
arXiv:2608.23541v1 Announce Type: cross Abstract: Does multi-agent LLM interaction help or hurt? Some work reports gains from debate (Du et al., 2024), critique loops (Chen et al., 2025), and mixture...
arXiv AI
Jun 9
Benchmarking Open-Ended Multi-Agent Coordination in Language Agents
arXiv:2606. 08340v1 Announce Type: new Abstract: As language models are increasingly deployed as autonomous agents, they must coordinate with others over long horizons in open-ended interactive tasks.