ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

• URL: http://arxiv.org/abs/2609.14857v1
• Date: Mon, 14 Sep 2026 00:10:45 GMT
• Title: ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
• Abstract summary: We propose a benchmark-disjoint, contrastive, and modular framework for generalizable harness evolution.<n> ModularRSI contrasts successful and failed trajectories for the same task and aggregates evidence across tasks to identify recurring behavioral deficiencies.<n>It decomposes the evolvable harness into five functional modules: Agent Loop, Tool Use, Observation Management, Context Management, and Task Completion Detection.
• Score: 46.36989489677189
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enabling agents to improve execution mechanisms from experience. However, generalizable harness RSI remains challenging. First, evolving harnesses on evaluation benchmarks or their subsets makes it difficult to distinguish reusable improvements from benchmark-specific adaptation. Second, single-trajectory updates can conflate systematic harness deficiencies with instance-specific reasoning and solution details, producing modifications that transfer poorly to unseen tasks. Third, localizing recurring behavioral deficiencies within monolithic harnesses is difficult, while whole-harness optimization can entangle unrelated mechanisms and complicate attribution and validation. We propose ModularRSI, a benchmark-disjoint, contrastive, and modular framework for generalizable harness evolution. ModularRSI contrasts successful and failed trajectories for the same task and aggregates evidence across tasks to identify recurring behavioral deficiencies. It decomposes the evolvable harness into five functional modules: Agent Loop, Tool Use, Observation Management, Context Management, and Task Completion Detection. Each module evolves independently within a restricted modification scope, followed by an integration stage that combines the evolved modules into a unified harness and resolves potential conflicts. To support benchmark-disjoint evolution, we curate 2,000 executable evolution tasks from external sources that are disjoint from downstream evaluation benchmarks. Experiments on TB2.0 and SWE-Bench Verified show consistent improvements on unseen in-domain and cross-domain tasks, with the evolved harness also transferring across different foundation models.

Related papers

• Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents [25.41577484327689]
  Self-evolving runtime harnesses can substantially improve the capabilities of large language model (LLM) agents.<n>Existing harness evolution methods rely on iterative search, repeatedly evaluating and revising candidate harnesses.<n>We propose Ecdysis, an efficient and effective framework that distinguishes model-specific accommodation from systematic harness deficiencies.
  arXiv  Detail & Related papers  (2026-09-10T15:09:08Z)
• MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves [65.60481414910728]
  Recursive self-improvement lets a system improve the model-building machinery from its own failures, so every later model inherits the gain.<n>Yet RSI has been validated almost exclusively on coding and formal benchmarks such as science QA and mathematics.<n>We argue RSI must next operate across real, diverse scientific, engineering, and meta-scientific domains, not where formal evaluation is merely tractable.<n>We present MetaRSI-v1, where improvement is the scheduled composition of three typed operators over one unified paradigm.
  arXiv  Detail & Related papers  (2026-09-06T05:15:31Z)
• MOAE: Multi-Objective Agent Evolution with Pareto-Preserving Search [5.257073134713488]
  Multi-Objective Agent Evolution organizes iterative in-context refinement as a Pareto-preserving evolutionary search over complete agent rollouts.<n>We show that MOAE consistently improves task performance and trajectory quality while maintaining strong safety under matched rollout budgets.
  arXiv  Detail & Related papers  (2026-09-05T09:31:34Z)
• ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning [74.19730275669227]
  ARISE-RL is a novel full-cycle self-evolution framework for training open-ended agents.<n>We present Reward-Gated Self-Evolution Distillation (RG-SED), which distills a memory-augmented variant of the same policy back into itself.<n>We also present ECR-Bench, an expert-calibrated rubric benchmark suite covering single-tool deep research and multi-tool travel planning.
  arXiv  Detail & Related papers  (2026-09-01T10:54:13Z)
• HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution [11.431479238875712]
  We introduce HarnessEvolve, a self-evolving framework that learns from reference trajectories to achieve reliable agent self-evolution.<n>We conduct extensive experiments on several benchmarks spanning open-domain and enterprise scenarios, using different models and agent frameworks.<n>Results demonstrate that HarnessEvolve consistently outperforms state-of-the-art baselines across all benchmarks and settings.
  arXiv  Detail & Related papers  (2026-09-01T07:31:18Z)
• StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments [9.081306845678679]
  We present StarHarness, a framework for evolving environment-specific agent harnesses while keeping model weights fixed.<n>The evolved harness can include prompt and task framing, tool interfaces, skills, MCP-backed providers, subagent structure, and agent-loop configuration.
  arXiv  Detail & Related papers  (2026-08-25T16:48:05Z)
• Evo-Bench: Can Language Models Improve Agent Harness? [44.72089415085898]
  Evo-Bench is the first benchmark designed to evaluate models' intrinsic harness-evolving capabilities across Search, Office, and General agent domains.<n>Top models achieve massive absolute gains reaching 16.6 points, closely approaching state-of-the-art human-engineered baselines.
  arXiv  Detail & Related papers  (2026-08-10T03:49:28Z)
• Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses [57.20181537213498]
  Agentic Harness Engineering (AHE) is a closed loop that automates harness engineering.<n>AHE addresses challenges through three matched observability pillars.<n>Ten AHE lift pass@1 on Terminal-Bench 2 from 69.7% to 77.0%, surpassing the human-designed harness Codex-CLI.<n>On SWE-bench-verified it tops aggregate success at 12% fewer tokens than the seed, and on Terminal-Bench 2 it yields +5.1 to +10.1pp cross-family gains.
  arXiv  Detail & Related papers  (2026-04-28T16:55:02Z)
• AgentV-RL: Scaling Reward Modeling with Agentic Verifier [63.55502685076245]
  Verifiers have been demonstrated to enhance LLM reasoning via test-time scaling (TTS)<n>We propose Agentic Verifier, a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process.<n>We show that Agentic Verifier yields consistent performance gains under both parallel and sequential TTS.
  arXiv  Detail & Related papers  (2026-04-17T12:27:36Z)
• 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)
• Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories [58.988535279557546]
  We introduce textbf sycophancy Mitigation through Adaptive Reasoning Trajectories.<n>We show that SMART significantly reduces sycophantic behavior while preserving strong performance on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2025-09-20T17:09:14Z)

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.