ActiveSaddler introduces automated curriculum learning for harness optimization, treating the evolving training curriculum as a non‑stationary bandit problem. It identifies reusable failure patterns, estimates learning progress for each, and balances revisiting known weaknesses with exploring new scenarios, allowing the curriculum to co‑evolve with the harness. Experiments on GAIA2 and Terminal‑Bench 2.0 show consistent improvements in harness performance, with Pass@1 gains of 4.4 and 7.5 percentage points over fixed‑order baselines.
arXiv:2606. 03108v1 Announce Type: new Abstract: Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static.
COBRA‑Skills is a new framework that treats skill optimization for large language model agents as a budgeted sequential problem over a dynamically evolving candidate set. It uses contextual‑bandit prioritization to focus evaluations on promising or informative candidates and refines the skill population based on execution feedback. In experiments across six agent benchmarks and three target models, COBRA‑Skills outperforms existing methods, cuts optimization cost by 55–58 % compared to SkillOpt, and requires only 50 unique optimization examples per benchmark.
arXiv:2608. 05628v1 Announce Type: new Abstract: Although agent skills equip LLMs with reusable procedural knowledge, manual maintenance suffers from high costs, unscalability, and misalignment.
arXiv:2607. 22688v1 Announce Type: new Abstract: Post-training agents for automated AI research requires optimizing not only model parameters, but also the runtime harness that shapes how research trajectories are generated, evaluated, and learned from.
Although agent skills equip LLMs with reusable procedural knowledge, manual maintenance suffers from high costs, unscalability, and misalignment. Real-world deployments thus require autonomous, on-demand skill evolution at test time, constrained by limited interaction budgets and a lack of training or validation sets.
The paper introduces CHART, a curriculum that rotates harnesses during training to teach search agents parallel search strategies robustly across different harness configurations. Unlike static harness augmentation, CHART gradually consolidates behavior by graduating learned harnesses and replacing them, maintaining a reward gap that drives learning. Experiments show CHART enables agents to parallelize on 89% of held‑out harnesses, improves performance on a new QA task by 5.6pp, and benefits more from meta‑harness search than baselines.
arXiv:2608.23041v1 Announce Type: new Abstract: LLM agents remain unreliable on long-horizon tasks, where small local failures can compound over extended interactions and lead to overall task failure...
arXiv:2607. 12227v1 Announce Type: new Abstract: We revisit the evaluation of automatic harness evolution for LLM agents.
HarnessEvolve is a self‑evolving framework that improves agent harnesses—prompts, skills, tools, and execution logic—by learning from reference trajectories. It separates execution, evaluation, optimization, and gating into independent modules, addressing credit assignment failure, shortcut learning, and catastrophic forgetting. The approach uses reference trajectories to extract error signals, applies quality and performance gates to candidate updates, and validates updates on held‑out data, consistently outperforming state‑of‑the‑art baselines across diverse benchmarks.
EVOHARNESSBENCH is a new benchmark that tests how LLM-based agents handle changes in their tool, skill, and agent harnesses over time. It includes 17 deterministic harness streams with 802 tasks, 520 tools, 42 skills, and 62 agents, and evaluates agents in two settings: deployment evaluation and self‑evolving adaptation evaluation. The study finds that harness expansion can cause forgetting, adaptation gains are inconsistent, and preserving old competence does not always aid new capability adaptation, highlighting harness evolution as a distinct challenge for agent development.
The paper introduces a self‑evolving harness framework where a frozen language‑model agent first solves tasks and then edits its own harness based on run records. Using a 49‑line seed harness, the evolved harness improves average scores on in‑distribution benchmarks by 4.48 points and on out‑of‑distribution benchmarks by 12.64 points, surpassing Codex on the former and matching it on the latter. Continued evolution on a specific out‑of‑distribution benchmark further raises performance, and the study analyzes emergent mechanisms such as output truncation and history compaction.
arXiv:2607. 14004v1 Announce Type: new Abstract: Most reported gains from agent-optimization methods are one-shot: an agent is optimized against a fixed benchmark and the resulting improvement is reported as if it were a stable property of the method.