The paper introduces RiseHarness, a framework that iteratively refines agent harnesses while keeping model weights fixed. It uses successful and failed runs under the same configuration to analyze failures, combining agent trajectories with runtime monitor traces to understand interactions between model actions and execution components. The framework then searches other harness frameworks for relevant implementations, adapts them, and validates changes through behavioral checks and repeated task evaluation, ultimately integrating mechanisms from multiple frameworks to improve reliability across tasks.
arXiv:2609.14857v1 Announce Type: new Abstract: Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enabling agents to improve executio...
The paper surveys AI agents that operate primarily through command-line terminals, defining them as systems whose main action loop involves executing terminal commands, receiving textual feedback, and interacting with a stateful environment. It introduces a seven‑dimensional terminal competence profile to link system architecture, learning, and evaluation, and highlights how behavior is jointly shaped by the model, interface, harness, runtime, and environment. The authors argue for explicit reporting of system and runtime conditions, supported by replayable traces and process‑level evidence, to better understand and benchmark terminal‑mediated agency.
Harness-Bench is a diagnostic benchmark that evaluates how different harness configurations affect LLM agent performance in realistic workflows. It tests 106 sandboxed offline tasks across multiple model backends, recording artifacts, execution traces, and usage statistics to analyze completion, process quality, efficiency, and failure behavior. The study finds significant variation in outcomes across model-harness pairings, indicating that agent capability should be reported at the configuration level rather than solely by the base model.
The paper introduces a framework for evaluating large‑language‑model agents by focusing on the interaction between the model and its execution harness. It defines five complementary metrics—Valid Completion Rate, Model‑Harness Fit, Cross‑Model Fit, Interaction Residuals, and Token Load—to assess how reliably agents finish tasks, how well harnesses support specific models, and the overall suitability across models. Using these metrics, the authors evaluate four general‑purpose harnesses and two native systems on six benchmarks, finding that harness rankings differ by model and task and that some harnesses consistently achieve high valid completion rates.
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.
arXiv:2610.00948v1 Announce Type: cross Abstract: The executable harness surrounding a GUI model determines how observations are assembled, actions are executed, and verification, recovery, and termi...
arXiv:2606. 17546v1 Announce Type: new Abstract: Self-evolving LLM-based agents improve mainly by changing their agent harness: the structured execution layer around a base model, including prompts, memory, tools, middleware, runtime state, and the model-tool interaction loop.
arXiv:2608. 05013v1 Announce Type: cross Abstract: LLM agents are increasingly applied to open-ended everyday requests that span work, study, and life.
Mid‑Harness proposes a test‑time compute strategy that samples and verifies candidate actions before execution, keeping the underlying generator and harness unchanged. Experiments show that with a strong verifier, sampling more actions significantly boosts success rates—e.g., a GPT‑5.6 verifier raises Pass@1 from 50.00 % to 68.03 % on TerminalBench‑Lite using eight samples. The approach also improves performance across various models, benchmarks, and harnesses, demonstrating that action scaling is a promising target for enhancing terminal agent reliability.
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.
arXiv:2606. 09498v3 Announce Type: replace Abstract: The performance of LLM-based agents is jointly shaped by their base models and the harnesses that mediate their interaction with the environment.
The study investigates how individual components of a coding harness—planning, action space, and context management—affect autonomous coding agents’ performance. By fixing the execution loop and varying these components across 176 settings on SWE‑Bench Verified and Terminal‑Bench 2.1, the authors find that context management is most valuable when context windows are tight, staging rule‑based elision before LLM summarization yields the best efficiency, planning serves as an accuracy scaffold for weaker models and a cost saver for stronger ones, and predefined tools help models with limited bash skills while bash‑capable models benefit from a bash‑only interface. Trajectory‑level analysis shows that context management lengthens execution paths, planning alters where trajectories terminate, and the action space determines code granularity, offering a modular framework for future harness design.