openJiuwen: Beyond Static Harnesses for Long-Horizon Coding Agents
- URL: http://arxiv.org/abs/2608.27969v1
- Date: Fri, 28 Aug 2026 06:31:38 GMT
- Title: openJiuwen: Beyond Static Harnesses for Long-Horizon Coding Agents
- Abstract summary: We present openJiuwen, an open-source harness for developer composability and adaptive task execution.<n> openJiuwen provides a shared execution substrate and Rail-based capability composition across single agents, delegated subagents, and Swarm Flow.<n>We systematically evaluate openJiuwen on SWE-bench Verified and Terminal-Bench 2.1, where it achieves 82.6% and 87.19%, respectively.
- Score: 25.815001544093217
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Long-horizon coding agents operate over evolving repository states while increasingly relying on heterogeneous capabilities, delegated agents, and multi-agent coordination. These trends pose two complementary challenges for the agent harness. First, developers need to compose capabilities, reconfigure execution logic, and scale increasingly complex agent systems without repeatedly rebuilding orchestration. Second, complex coding tasks continuously produce new evidence---such as semantic diagnostics, execution outcomes, task progress, and changing context relevance---that should dynamically influence subsequent runtime decisions. We characterize these challenges as Structural Composability and Runtime Adaptivity. We present openJiuwen, an open-source harness designed for both developer composability and adaptive task execution. openJiuwen provides a shared execution substrate and Rail-based capability composition across single agents, delegated sub-agents, and Swarm Flow, enabling developers to construct sophisticated agent harnesses under common execution semantics. It further adapts framework-controlled runtime decisions around a fixed model policy, allowing evolving evidence to dynamically affect context, feedback, and task control toward successful completion. We systematically evaluate openJiuwen on SWE-bench Verified and Terminal-Bench 2.1, where it achieves 82.6% and 87.19%, respectively, exceeding the strongest selected official-leaderboard point estimates by 3.4 and 3.39 percentage points. These results show that openJiuwen achieves strong performance on complex coding tasks while providing a composable and adaptive harness design.
Related papers
- EASy: Towards Efficient LLM-Based Agentic System [54.10819421625103]
We propose EASy, a trainable agentic framework that jointly optimize task performance and computational efficiency through reinforcement learning.<n> EASy equips an LLM-based orchestrator with explicit knowledge of the capability and cost profiles of heterogeneous executors, enabling context-sensitive coordination beyond performance-only routing.<n>It further introduces a milestone-plan-act workflow that decomposes complex tasks into manageable milestones, constructs dependency-aware execution graphs, assigns suitable executors, and parallelizes independent steps while adapting subsequent decisions to intermediate outcomes.
arXiv Detail & Related papers (2026-08-05T08:50:36Z) - 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) - Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering [50.72456732323037]
We propose textbfSwarm Skills, a portable specification that extends the Anthropic Skills standard with multi-agent semantics.<n>Swarm Skills turns multi-agent into first-class, distributable assets that consist of roles, execution bounds, and a built-in semantic structure for self-evolution.<n>We show how Swarm Skills achieves zero-adapter cross-agent portability via progressive disclosure, enabling agent teams to self-evolve their coordination strategies without framework lock-in.
arXiv Detail & Related papers (2026-05-11T06:26:58Z) - Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts [22.323342919724492]
HERA is a hierarchical framework that jointly evolves multi-agent orchestration and role-specific agent prompts.<n> HERA achieves an average improvement of 38.69% over recent baselines.<n>Topological analyses reveal emergent self-organization, where sparse exploration yields compact, high-utility multi-agent networks.
arXiv Detail & Related papers (2026-04-01T13:45:52Z) - Effective Strategies for Asynchronous Software Engineering Agents [52.76455094324273]
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).
arXiv Detail & Related papers (2026-03-23T02:26:35Z) - K^2-Agent: Co-Evolving Know-What and Know-How for Hierarchical Mobile Device Control [73.50217471850658]
K2-Agent is a hierarchical framework that models human-like cognition by knowing and co-evolving declarative (what) and procedural (how) knowledge for planning and execution.<n>On the challenging AndroidWorld benchmark, K2-Agent achieves a 76.1% success rate using only raw and open-source backbones.
arXiv Detail & Related papers (2026-02-28T14:33:14Z) - Towards Self-Evolving Benchmarks: Synthesizing Agent Trajectories via Test-Time Exploration under Validate-by-Reproduce Paradigm [60.36837655498119]
We propose a Trajectory-based validated-by-Reproducing Agent-benchmark Complexity Evolution framework.<n>This framework takes an original task from an existing benchmark and encourages agents to evolve it into a new task with higher difficulty.<n>Experiments on the GAIA benchmark demonstrate that the TRACE framework consistently enhances task complexity while improving the reliability of correctness.
arXiv Detail & Related papers (2025-10-01T01:52:52Z) - 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) - Collaboration Dynamics and Reliability Challenges of Multi-Agent LLM Systems in Finite Element Analysis [3.437656066916039]
How interagent dynamics influence reasoning quality and verification reliability remains unclear.<n>We study these mechanisms using an AutoGen-based multi-agent framework for linear-elastic Finite Element Analysis (FEA)<n>From 1,120 controlled trials, we find that collaboration effectiveness depends more on functional complementarity than team size.
arXiv Detail & Related papers (2024-08-23T23:11:08Z) - TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation [41.21899915378596]
We propose a multi-agent framework based on dynamic Task Decomposition and Agent Generation (TDAG)<n>This framework dynamically decomposes complex tasks into smaller subtasks and assigns each to a specifically generated subagent.<n>ItineraryBench is designed to assess agents' abilities in memory, planning, and tool usage across tasks of varying complexity.
arXiv Detail & Related papers (2024-02-15T18:27:37Z)
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.