SBCO: Self-Supervised, Verifier-Grounded Harness Optimization For Planning Agents

• URL: http://arxiv.org/abs/2608.10157v1
• Date: Mon, 10 Aug 2026 19:25:59 GMT
• Title: SBCO: Self-Supervised, Verifier-Grounded Harness Optimization For Planning Agents
• Abstract summary: Self-improving agents seek to reduce the human engineering effort behind AI systems by enabling them to evolve and self-improve their performance over time.<n>We introduce SBCO, a verifier-grounded harness in the same closed-loop, improve-from-experience family as the Gdel-machine methods, but self-supervised rather than self-referential.
• Score: 8.206010431605044
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-improving agents seek to reduce the human engineering effort behind AI systems by enabling them to evolve and self-improve their performance over time. Recently, methods like the Darwin Gödel Machine and the Huxley Gödel Machine have been proposed which enable open-ended, recursive self-improvement through self-reference where a coding agent edits its own code. Such self-referential self-improvement methods require that the competence required to perform the task coincides or aligns well with the competence required for self-modification which is the case for coding tasks. For domains or tasks, which do not satisfy the alignment needed, self-referential self-improvement is not available. In such cases, it is possible to adapt the above algorithms to other tasks by removing the self-referential aspect or introducing explicit self-modification of a meta-agent -- both computationally expensive, relying on population or self-modification search over many candidate agents. For planning tasks with explicit constraints, we propose a far cheaper alternative. We introduce SBCO (Self-supervised Block Coordinate Optimizer), a verifier-grounded harness optimizer in the same closed-loop, improve-from-experience family as the Gödel-machine methods, but self-supervised rather than self-referential. Given an agentic harness, SBCO learns a decomposed bank of verifiers and a harness policy via approximate block coordinate ascent, improving the agent's outputs from its own graded feedback---with a fixed meta-agent and no human labels. Across two domains SBCO matches or exceeds a customized self-modifying baseline while using 4-5.5 times less compute budget.

Related papers

• Self-Aware Recursively Self-Improving Agents for Personal Singularity: A Goal-, Scope-, Tool-, and Benchmark-Driven Multi-Agent Architecture [1.7259824817932294]
  Large language model (LLM) agents can plan, use tools, maintain memory, and execute long-horizon tasks.<n>This paper proposes Self-Aware Recursively Self-Improving (SARSI) agents that maintain a persistent self-model of identity, goals, capabilities, limitations, uncertainty, relationships, history, and developmental change.<n>We pair SARSI agents with personal singularity, a bounded human-AI co-development objective in which an agent ecosystem helps a user approach an expanding, user-defined feasible capability frontier.
  arXiv  Detail & Related papers  (2026-07-14T01:44:53Z)
• Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference [51.55077364626896]
  We introduce Retrospective Harness Optimization (RHO), a self-supervised method that optimize agent harness using only past trajectories.<n>RHO selects a diverse coreset of challenging tasks from past trajectories and re-solves them in parallel.<n>A single optimization round improves the pass rate on SWE-Bench Pro from 59% to 78% without any external grading.
  arXiv  Detail & Related papers  (2026-06-04T09:26:00Z)
• Evolutionary Ensemble of Agents [7.465452178698495]
  We introduce EvE, a decentralized framework that organizes coding agents into a live, co-evolving system for algorithmic discovery.<n>By maintaining two co-evolving populations, EvE evaluates agents through a synchronous race, updating their empirical Elo ratings.<n>Compared to variants driven by a fixed initial agent or even a frozen "best-evolved" agent, EvE uniquely avoids phase mismatch.
  arXiv  Detail & Related papers  (2026-05-09T15:56:10Z)
• Hyperagents [42.17044581555985]
  Self-improving AI systems aim to reduce reliance on human engineering.<n>Existing approaches to self-improvement rely on fixed, handcrafted meta-level mechanisms.<n>We extend the Darwin Gdel Machine to create DGM-Hyperagents.
  arXiv  Detail & Related papers  (2026-03-19T20:50:08Z)
• Towards Efficient Agents: A Co-Design of Inference Architecture and System [66.59916327634639]
  This paper presents AgentInfer, a unified framework for end-to-end agent acceleration.<n>We decompose the problem into four synergistic components: AgentCollab, AgentSched, AgentSAM, and AgentCompress.<n>Experiments on the BrowseComp-zh and DeepDiver benchmarks demonstrate that through the synergistic collaboration of these methods, AgentInfer reduces ineffective token consumption by over 50%.
  arXiv  Detail & Related papers  (2025-12-20T12:06:13Z)
• Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning [84.70211451226835]
  Large Language Model (LLM) Agents are constrained by a dependency on human-curated data.<n>We introduce Agent0, a fully autonomous framework that evolves high-performing agents without external data.<n>Agent0 substantially boosts reasoning capabilities, improving the Qwen3-8B-Base model by 18% on mathematical reasoning and 24% on general reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-11-20T05:01:57Z)
• Alita-G: Self-Evolving Generative Agent for Agent Generation [54.49365835457433]
  We present ALITA-G, a framework that transforms a general-purpose agent into a domain expert.<n>In this framework, a generalist agent executes a curated suite of target-domain tasks.<n>It attains strong gains while reducing computation costs.
  arXiv  Detail & Related papers  (2025-10-27T17:59:14Z)
• Huxley-Gödel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine [31.795598366502166]
  We identify a mismatch between the agent's self-improvement potential and its coding benchmark performance.<n>Inspired by Huxley's concept of clade, we propose a metric ($mathrmCMP$) that aggregates the benchmark performances of the descendants of an agent.<n>We introduce the Huxley-G"odel Machine (HGM), which, by estimating $mathrmCMP$ and using it as guidance, searches the tree of self-modifications.
  arXiv  Detail & Related papers  (2025-10-24T16:19:41Z)
• Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement [112.04307762405669]
  G"odel Agent is a self-evolving framework inspired by the G"odel machine.<n>G"odel Agent can achieve continuous self-improvement, surpassing manually crafted agents in performance, efficiency, and generalizability.
  arXiv  Detail & Related papers  (2024-10-06T10:49:40Z)
• REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback [61.54791065013767]
  A misalignment between the reward function and human preferences can lead to catastrophic outcomes in the real world.<n>Recent methods aim to mitigate misalignment by learning reward functions from human preferences.<n>We propose a novel concept of reward regularization within the robotic RLHF framework.
  arXiv  Detail & Related papers  (2023-12-22T04:56:37Z)

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.