Pith. sign in

REVIEW 12 cited by

Self-Evolving Multi-Agent Collaboration Networks for Software Development

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.16946 v1 pith:VTJNFI5A submitted 2024-10-22 cs.SE cs.AIcs.MA

Self-Evolving Multi-Agent Collaboration Networks for Software Development

classification cs.SE cs.AIcs.MA
keywords developmentsoftwarersde-benchautomaticbenchmarkcapabilitiescodingevomac
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

LLM-driven multi-agent collaboration (MAC) systems have demonstrated impressive capabilities in automatic software development at the function level. However, their heavy reliance on human design limits their adaptability to the diverse demands of real-world software development. To address this limitation, we introduce EvoMAC, a novel self-evolving paradigm for MAC networks. Inspired by traditional neural network training, EvoMAC obtains text-based environmental feedback by verifying the MAC network's output against a target proxy and leverages a novel textual backpropagation to update the network. To extend coding capabilities beyond function-level tasks to more challenging software-level development, we further propose rSDE-Bench, a requirement-oriented software development benchmark, which features complex and diverse software requirements along with automatic evaluation of requirement correctness. Our experiments show that: i) The automatic requirement-aware evaluation in rSDE-Bench closely aligns with human evaluations, validating its reliability as a software-level coding benchmark. ii) EvoMAC outperforms previous SOTA methods on both the software-level rSDE-Bench and the function-level HumanEval benchmarks, reflecting its superior coding capabilities. The benchmark can be downloaded at https://yuzhu-cai.github.io/rSDE-Bench/.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MetaPS: Adaptive Programmatic Strategy Selection for Market Agents

    cs.AI 2026-06 unverdicted novelty 6.0

    MetaPS trains models via simulation rollouts to select from programmatic strategy libraries for market agents, yielding better performance than fixed or direct LLM baselines across model sizes.

  2. Plan in Sandbox, Navigate in Open Worlds: Learning Physics-Grounded Abstracted Experience for Embodied Navigation

    cs.RO 2026-05 unverdicted novelty 6.0

    SAGE trains agents in physics-grounded semantic abstractions via RL with asymmetric clipping, achieving 53.21% LLM-Match Success on A-EQA (+9.7% over baseline) and encouraging physical robot transfer.

  3. EvoMAS: Learning Execution-Time Workflows for Multi-Agent Systems

    cs.AI 2026-05 unverdicted novelty 6.0

    EvoMAS trains a workflow adapter with policy gradients to dynamically instantiate stage-specific multi-agent workflows from a fixed agent pool, using explicit task-state construction and terminal success signals, and ...

  4. SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology

    cs.AI 2026-04 unverdicted novelty 6.0

    SkillGraph jointly evolves agent skills and collaboration topologies in multi-agent vision-language systems using a multimodal graph transformer and a skill designer, yielding consistent performance gains on benchmarks.

  5. Effective Strategies for Asynchronous Software Engineering Agents

    cs.CL 2026-03 conditional novelty 6.0

    CAID, a manager-driven multi-agent system using git worktrees, commits, and merges, improves long-horizon SWE success by roughly 14–27 absolute points over single-agent baselines.

  6. From Agentic to Autogenic Network Management for AI-Native 6G and Beyond: A Standards Perspective

    cs.NI 2026-07 conditional novelty 5.5

    Autogenic network management extends agentic AI with self-programming, self-reflection, self-orienting, and self-architecting so 6G management planes can generate and evolve their own automation software at runtime.

  7. Assistance to Autonomy: A Systematic Literature Review of Agentic AI across the Software Development Life Cycle

    cs.SE 2026-05 unverdicted novelty 5.0

    Systematic review of agentic AI in the SDLC finds output verifiability drives industrial adoption in later phases, with Planner-Executor-Reviewer as the dominant pattern, plus a new multi-agent LLM screening pipeline ...

  8. Reinforced Collaboration in Multi-Agent Flow Networks

    cs.LG 2026-05 unverdicted novelty 5.0

    MANGO optimizes multi-agent LLM workflows via flow networks, RL, and textual gradients, delivering up to 12.8% higher performance and 47.4% better efficiency while generalizing to new domains.

  9. ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows

    cs.AI 2026-05 unverdicted novelty 5.0

    ProfiliTable is a profiling-driven multi-agent system that builds semantic context through exploration and closed-loop refinement to produce more reliable tabular data transformations than prior LLM approaches.

  10. ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows

    cs.AI 2026-05 unverdicted novelty 5.0

    ProfiliTable is a multi-agent system with profiler, generator, and evaluator components that outperforms baselines on 18 tabular task types via dynamic profiling and closed-loop refinement.

  11. Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures

    cs.AI 2026-04 unverdicted novelty 4.0

    A survey comparing classical multi-agent systems with large foundation model-enabled multi-agent systems, showing how the latter enables semantic-level collaboration and greater adaptability.

  12. A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence

    cs.AI 2025-07 accept novelty 4.0

    The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.