Effective Strategies for Asynchronous Software Engineering Agents

• URL: http://arxiv.org/abs/2603.21489v1
• Date: Mon, 23 Mar 2026 02:26:35 GMT
• Title: Effective Strategies for Asynchronous Software Engineering Agents
• Abstract summary: We introduce a structured multi-agent coordination paradigm grounded in three core SWE primitives: centralized task delegation, asynchronous execution, and isolated workspaces.<n>We find that CAID improves accuracy over single-agent baselines by 26.7% absolute on paper reproduction tasks (PaperBench) and 14.3% on Python library development tasks (Commit0).
• Score: 52.76455094324273
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: AI agents have become increasingly capable at isolated software engineering (SWE) tasks such as resolving issues on Github. Yet long-horizon tasks involving multiple interdependent subtasks still pose challenges both with respect to accuracy, and with respect to timely completion. A natural approach to solving these long-horizon tasks in a timely manner is asynchronous multi-agent collaboration, where multiple agents work on different parts of the task at the same time. But effective application of multi-agent systems has proven surprisingly difficult: concurrent edits by multiple agents interfere with each other, dependencies are difficult to synchronize, and combining partial progress into a coherent whole is challenging. On the other hand, human developers have long relied on mature collaboration infrastructure to manage these challenges in large software projects. Inspired by these collaboration primitives, we introduce Centralized Asynchronous Isolated Delegation (CAID), a structured multi-agent coordination paradigm grounded in three core SWE primitives: centralized task delegation, asynchronous execution, and isolated workspaces. CAID constructs dependency-aware task plans through a central manager, executes subtasks concurrently in isolated workspaces, and consolidates progress via structured integration with executable test-based verification. In empirical evaluation, we find that CAID improves accuracy over single-agent baselines by 26.7% absolute on paper reproduction tasks (PaperBench) and 14.3% on Python library development tasks (Commit0). Through systematic analysis, we find that branch-and-merge is a central coordination mechanism for multi-agent collaboration, and that SWE primitives such as git worktree, git commit, and git merge enable it to be realized in a reliable and executable manner.

Related papers

• When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding [19.03671411536556]
  Multi-agent Large Language Model (LLM) systems offer a way to decompose complex tasks, such as coding, through parallelization and context isolation.<n>We formalize multi-agent orchestration as a graph partitioning problem that captures the communication-to-computation trade-off.<n>We 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.
  arXiv  Detail & Related papers  (2026-05-31T02:10:12Z)
• Multi-agent Collaboration with State Management [21.19345862774123]
  When multiple agents edit a shared concurrently, their changes can silently conflict and inconsistent views lead to integration failures.<n>Existing multi-agent systems address this through workspace isolation (e.g., one git worktree per agent)<n>We propose STORM, i.e., STate-ORiented Management for multi-agent collaboration.
  arXiv  Detail & Related papers  (2026-05-19T23:45:33Z)
• Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems [65.90791804095561]
  Multi-agent systems address this through structured collaboration among specialized agents, but tighter coordination amplifies a less explored risk.<n>Existing surveys cover individual agent capabilities, multi-agent collaboration, or agent self-evolution separately, leaving the causal dependencies among them unexamined.<n>This survey provides a unified review organized around four causally linked stages, which we term the LIFE progression: Lay the capability foundation, Integrate agents through collaboration, Find faults through attribution, and Evolve through autonomous self-improvement.
  arXiv  Detail & Related papers  (2026-05-14T14:36:13Z)
• HULK: Large-scale Hierarchical Coordination under Continual and Uncertain Temporal Tasks [5.337512368549053]
  This work tackles the large-scale coordination problem under continual and uncertain temporal tasks.<n>The proposed hierarchical framework, HULK, consists of two interleaved layers: the rolling assignment of currently known tasks to subteams within a certain horizon, and the dynamic coordination within a subteam given the detected subtasks during online execution.<n>The method is validated rigorously over large-scale heterogeneous systems under various temporal tasks and environment uncertainties.
  arXiv  Detail & Related papers  (2026-05-09T06:10:40Z)
• Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs [52.26652574704317]
  Large language models (LLMs) are increasingly deployed in teams, yet existing coordination approaches often occupy two extremes.<n>We introduce Language Agent Teams for Task Evolution (LATTE), a framework for coordinating LLM teams inspired by distributed systems.
  arXiv  Detail & Related papers  (2026-05-07T14:19:17Z)
• EmCoop: A Framework and Benchmark for Embodied Cooperation Among LLM Agents [18.802912315746564]
  EmCoop is a benchmark framework for studying cooperation in embodied multi-agent systems.<n>Our framework separates a high-level cognitive layer from a low-level embodied interaction layer.<n>We propose generalizable, process-level metrics that diagnose collaboration quality and failure modes.
  arXiv  Detail & Related papers  (2026-02-27T22:28:33Z)
• Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AI [1.8244641115869653]
  We present Federation of Agents (FoA), a distributed orchestration framework that transforms multi-agent coordination into dynamic, capability-driven collaboration.<n>FoA introduces Versioned Capability Vectors (VCVs), machine-readable profiles that make agent capabilities searchable through semantic embeddings.<n>We show 13x improvements over single-model baselines, with clustering-enhanced laboration particularly effective for complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-09-24T14:38:06Z)
• Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration [63.90193684394165]
  We introduce multi-agent cross-task experiential learning (MAEL), a novel framework that endows LLM-driven agents with explicit cross-task learning and experience accumulation.<n>During the experiential learning phase, we quantify the quality for each step in the task-solving workflow and store the resulting rewards.<n>During inference, agents retrieve high-reward, task-relevant experiences as few-shot examples to enhance the effectiveness of each reasoning step.
  arXiv  Detail & Related papers  (2025-05-29T07:24:37Z)
• When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements [56.29265568399648]
  We argue that disagreements prevent premature consensus and expand the explored solution space.<n>Disagreements on task-critical steps can derail collaboration depending on the topology of solution paths.
  arXiv  Detail & Related papers  (2025-02-21T02:24:43Z)
• SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering [74.04271300772155]
  SyncMind is a framework that systematically defines the out-of-sync problem faced by large language model (LLM) agents in software engineering.<n>Based on SyncMind, we create SyncBench, a benchmark featuring 24,332 instances of agent out-of-sync scenarios in real-world CSE.
  arXiv  Detail & Related papers  (2025-02-10T19:38:36Z)
• Multi-Agent Collaboration via Cross-Team Orchestration [31.506350304184526]
  Large Language Models (LLMs) have significantly impacted various domains, especially through organized autonomous agents.<n>We introduce Cross-Team Orchestration (Croto), a scalable multi-team framework that enables orchestrated teams to jointly propose various task-oriented solutions.<n>Experiments reveal a notable increase in software quality compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-06-13T10:18:36Z)
• AutoAgents: A Framework for Automatic Agent Generation [27.74332323317923]
  AutoAgents is an innovative framework that adaptively generates and coordinates multiple specialized agents to build an AI team according to different tasks. Our experiments on various benchmarks demonstrate that AutoAgents generates more coherent and accurate solutions than the existing multi-agent methods.
  arXiv  Detail & Related papers  (2023-09-29T14:46:30Z)
• A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks [111.34055449929487]
  We introduce the novel task FurnMove in which agents work together to move a piece of furniture through a living room to a goal. Unlike existing tasks, FurnMove requires agents to coordinate at every timestep. We identify two challenges when training agents to complete FurnMove: existing decentralized action sampling procedures do not permit expressive joint action policies. Using SYNC-policies and CORDIAL, our agents achieve a 58% completion rate on FurnMove, an impressive absolute gain of 25 percentage points over competitive decentralized baselines.
  arXiv  Detail & Related papers  (2020-07-09T17:59:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.