arXiv:2611. 02079v1 Announce Type: cross Abstract: Harness optimization can substantially improve LLM agents without modifying model weights, but existing methods primarily optimize response quality.
arXiv:2608. 06301v1 Announce Type: new Abstract: As LLMs are increasingly deployed within agentic systems, their capabilities depend not only on the model weights but also on the harness: the prompts, tools, control flow, memory, and orchestration code surrounding them.
arXiv:2609.05992v1 Announce Type: new Abstract: As LLM-based agents continue to advance, their evaluation has become increasingly multifaceted: a capable agent must not only achieve high task complet...
arXiv:2610.26770v2 Announce Type: replace Abstract: Harness development plays a crucial role in building capable AI agents. Recent approaches improve harnesses through recursive self-improvement (RSI...
arXiv:2609.05736v2 Announce Type: new Abstract: LLM tool agents can be improved without retraining by modifying the runtime harness around a fixed model: prompts, tool interfaces, middleware, state h...
arXiv:2605.19330v2 Announce Type: replace-cross Abstract: LLM agents organize behavior through skills -- structured natural-language specifications that govern how an agent reasons, retrieves, and re...
arXiv:2607. 27083v1 Announce Type: new Abstract: As LLM agents increasingly depend on diverse external services such as search engines, databases, and connectors, agent harnesses face a fundamental tool-selection challenge: acquiring too few tools leaves the task under-informed, while too many adds cost, context load, and privacy exposure.
arXiv:2607. 12227v1 Announce Type: new Abstract: We revisit the evaluation of automatic harness evolution for LLM agents.
arXiv:2609.13396v1 Announce Type: new Abstract: Multi-objective Bayesian optimisation (MOBO) is a sample-efficient approach for optimising expensive black-box functions with multiple objectives. In M...
arXiv:2608. 08466v1 Announce Type: new Abstract: Modern LLM agents are often improved by modifying prompts, tools, or workflows manually, while the executable scaffold surrounding the model---the \emph{harness}---is typically treated as a fixed artifact after deployment.
arXiv:2608. 20169v1 Announce Type: cross Abstract: We present a novel approach to efficient LLM agent harness optimization through adaptive validation task selection.
arXiv:2610.18572v1 Announce Type: new Abstract: Automated post-training transforms pre-trained large language models (LLMs) into models capable of handling diverse domains by automatically constructi...
The paper introduces WHALE, a method that alternates between updating a language model’s weights and searching for a better harness (the code that manages context and control flow). By iteratively fine‑tuning the model under the current harness and then optimizing the harness under the updated model, WHALE improves performance across search QA, math reasoning, and chess puzzles, outperforming weight‑only, harness‑only, and Fast‑Slow Training by 4.15–24.38 percentage points in mean@8 accuracy. The approach uses either fixed phase lengths or an adaptive patience rule to decide when to switch phases, and the authors provide code on GitHub.