Skip to main content
Search

# Multi-Agent Collaboration

15 related articles

Subscribe to updates
  1. arXiv

    Open-source agent platform OpenLayout takes over VLSI physical design, lifting atomic-task Pass@1 well above a standalone LLM

    OpenLayout turns VLSI physical design from a scripted flow that senior engineers tune command by command into an automated loop run by specialized agents on commercial EDA tools. Its companion OpenLayout-Bench evaluates agent capability at TSMC 28nm: standalone Gemini 3.1-pro reaches only 18.9% Pass@1 on Tool A atomic tasks, while OpenLayout reaches 80.0% on the same metric, and on Tool B the standalone model reaches 19.3% versus 84.1% with OpenLayout. On the 10-design holistic flow suite, small and medium designs close timing, while NVDLA-large and Open910 retain residual DRC violations after Routeopt.

  2. arXiv

    Natural language now builds Dify workflows: ChatDify's planner-executor-reviewer agents reach 0.96 success on 100 production-style tasks

    Building an LLM workflow on a platform like Dify used to mean manually picking nodes, filling in parameters and wiring connections, which is slow and error-prone. ChatDify hands the job to three collaborating agents: a planner that decomposes the request into a directed acyclic graph, an executor that synthesizes node parameters under schema constraints and compiles them into Dify's DSL, and a reviewer that runs static checks plus sandboxed execution with LLM judging in a closed refinement loop. On 100 production-inspired Dify tasks with Qwen-3.7, GLM-5.1 and DeepSeek-v4 as backends, success rates were 0.96, 0.91 and 0.75, above the zero-shot baseline with dynamic repair.

  3. Test cases stop being hand-written one by one: five agents split the work and audit themselves, averaging a 93.4% mutation score across five datasets

    Software test-case design has long depended on manual work, and models that treat generation as one-shot text translation struggle with multi-layered business rules. A pipeline of five roles, parser, triage, architect, writer and auditor, turns test generation into a stateful reasoning process in which the auditor corrects scripts before output. Across five datasets spanning travel, telecom, financial regulation and a government job platform, the pipeline averaged a 93.4% mutation score, 1.4% hallucination and 7.8% redundancy, at an average generation time of 21.2 hours.

  4. Metal printing design stops relying on manual judgment: agents revise the part and the assessment code, cutting a thermal peak by 160 °C

    Design assessment for laser powder bed fusion no longer requires engineers to hand-carry results between preset rules and simulation tools. AgenticDfAM lets language-model agents interpret manufacturing guidance, select tools and propose redesigns, while geometric measurement and numerical comparison stay with executable tools. Across four case studies, three redesign strategies removed all reference violations on an analytical artifact, thermal feedback lowered a bracket's predicted layer-scale peak temperature by 160 °C, and a corrected support-construction procedure was reused in four build orientations.

  5. arXiv

    Robot memory stops guessing from keyframes: per-tick text lines lift success from 44.5% to 66.0% under a fixed policy

    Gamma replaces pixel keyframe memory with auditable text lines, raising average success on RoboMME's sixteen memory tasks from 44.5% to 66.0% under a fixed execution policy and matching the privileged subgoal ceiling on three tasks.

  6. Fact-checking articles can now be drafted automatically: QRAFT chains evidence, drafting and simulated editing, but experts still want a human in the loop

    QRAFT splits fact-checking article writing into evidence gathering, drafting and a simulated editorial review run by multiple LLM agents, beating prior text-generation methods on automatic metrics across 1,227 examples while still scoring well below expert-written articles with professional fact-checkers.

  7. arXiv

    LiveMACEBench evaluates five frontier LLM agents over 30 days of live markets and finds return rankings diverge sharply from capability metrics

    The work introduces LiveMACEBench, a process-aware benchmark that uses live cryptocurrency and U.S. equity markets as a naturally evolving testbed in which five frontier LLMs run continuous paper-trading trajectories under matched Base, Tool Use, Persistent Memory, Rule Following, and Multi-Agent Collaboration configurations, evaluated through both realized outcomes and trace-derived diagnostics; across roughly 30 days it finds a pronounced outcome–capability gap, with return rankings fluctuating and often diverging from capability-specific measurements while similar outcomes arise from markedly different patterns of mechanism use.

  8. arXiv

    AECG tops 11 of 12 framework-benchmark settings across three multi-agent frameworks and four benchmarks, with scope-preservation ablation dropping accuracy by up to 16.89 points

    The authors introduce AECG, a multi-agent memory governance framework that combines scope preservation, asymmetric evidence admission, dual-timescale reliability estimation, and downstream-exposure-aware budgeted review to turn memory from static storage into a reliability-governance loop; across three frameworks (AutoGen, MacNet, AgentNet) and four benchmarks (PDDL, FEVER, ScienceWorld, MBPP-Plus), AECG achieves the best score in 11 of 12 settings, improving over the strongest memory baseline by up to 10.23 percentage points, while removing scope preservation reduces accuracy by up to 16.89 points.

  9. arXiv

    CodePori uses a multi-agent system to automate code generation and surveys practitioners on its usability in real-world software development

    The study proceeded in two phases: it built a multi-agent system named CodePori to automate code generation, then used a survey in which participants evaluated the agents' performance on autonomous software development tasks; the results indicate that LLM-based multi-agent systems show potential for autonomous code generation, but successful integration requires addressing specific challenges such as short-term memory limitations, hallucinations, and code smells, and incorporating a practitioner-centric perspective.

  10. LLM multi-agent control framework reaches a 93% mean solve rate in a six-module simulated factory, with the orchestrator autonomously rerouting around a silent conveyor-belt fault in all ten runs

    The work pairs each factory module with a dedicated LLM-based agent and an MCP tool server that exposes the module's skills via OPC UA method calls, with agents coordinating over MQTT and grounded by real-time factory-state updates; in a simulation of a six-module hexagonal factory it compares orchestrator, peer-to-peer, and monolithic architectures across nine production challenges of increasing complexity, finding that monolithic and peer-to-peer both achieve the highest mean solve rate (93%) while the orchestrator uniquely resolves a silent conveyor-belt fault in all ten runs by autonomously rerouting plates around the blocked segment, and that all architectures exhibit emergent fault-diagnosis behavior without explicit failure-handling logic.