# When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding

arXiv: https://arxiv.org/abs/2606.00953 · HTML: https://mlsanity.com/paper/2606.00953/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 31 May 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 22 of 22)

- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems](https://mlsanity.com/paper/2306.03091/) (2023)
- [Scaling Large Language Model-based Multi-Agent Collaboration](https://mlsanity.com/paper/2406.07155/) (2024)
- [An LLM Compiler for Parallel Function Calling](https://mlsanity.com/paper/2312.04511/) (2023)
- [CodePlan: Repository-level Coding using LLMs and Planning](https://mlsanity.com/paper/2309.12499/) (2023)
- [DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories](https://mlsanity.com/paper/2405.19856/) (2024)
- [Repoformer: Selective Retrieval for Repository-Level Code Completion](https://mlsanity.com/paper/2403.10059/) (2024)
- [Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study](https://mlsanity.com/paper/2403.08604/) (2024)
- [Graph-enhanced Large Language Models in Asynchronous Plan Reasoning](https://mlsanity.com/paper/2402.02805/) (2024)
- [Large Language Models Miss the Multi-Agent Mark](https://mlsanity.com/paper/2505.21298/) (2025)
- [CooperBench: Why Coding Agents Cannot be Your Teammates Yet](https://mlsanity.com/paper/2601.13295/) (2026)
- [TCP: a Benchmark for Temporal Constraint-Based Planning](https://mlsanity.com/paper/2505.19927/) (2025)
- [DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models](https://mlsanity.com/paper/2601.11895/) (2026)
- [Towards Realistic Project-Level Code Generation via Multi-Agent Collaboration and Semantic Architecture Modeling](https://mlsanity.com/paper/2511.03404/) (2025)
- [Language Model Teams as Distributed Systems](https://mlsanity.com/paper/2603.12229/) (2026)

## Built on by (most cited first, 5 of 5)

- [Claim Plane: Enforceable Change Intents and Dynamic Scope for Parallel Coding Agents](https://mlsanity.com/paper/2607.21909/) (2026)
- [The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks](https://mlsanity.com/paper/2608.16630/) (2026)
- [Claim Plane: Reliability Gains and the Limits of Selective Concurrency for Parallel Coding Agents: A 30-Pair, Three-Seed Confirmatory Study of Deterministic Pre-Write Admission](https://mlsanity.com/paper/2608.00947/) (2026)
- [ParallelPilot: Supporting Coordination and Monitoring in Parallel AI Coding](https://mlsanity.com/paper/2609.33113/) (2026)
- [Scaling Inference-Time Compute with Teams of Coding Agents](https://mlsanity.com/paper/2610.17471/) (2026)

## Abstract (arXiv)

Multi-agent Large Language Model (LLM) systems offer a way to decompose complex tasks, such as coding, through parallelization and context isolation. However, adding agents in practice introduces inter-agent communication overhead, which incurs extra cost and can sometimes offset the efficiency gains. We formalize multi-agent orchestration as a graph partitioning problem that captures the communication-to-computation trade-off: task decomposition can shorten critical-path computation, but cross-agent dependencies require costly context transfer. We instantiate this view in repository-level software engineering and present Cohesion-aware Coder (Co-Coder), which builds dependency graphs from static analysis, isolates structural hub files, partitions the graph via community detection, and executes the partition with a dependency-aware scheduler. Across 28 real-world tasks on DevEval and CodeProjectEval, Co-Coder advances the Pareto-frontier over sequential and file-based parallel baselines as well as Claude Code with Agent Teams, lifting pass rate by up to 14.0%, achieving up to a 2.10x wall-clock speedup, and reducing API cost by up to 35%, with the largest gains on the most dependency-dense projects. Co-coder demonstrates how cohesion-aware orchestration can make parallel coding agents both theoretically grounded and practically efficient, suggesting a broader design principle for multi-agent systems.