Model Detail
harness-1
—harness-1 is a large language model with 20B parameters released by pat-jj. The model is registered under the text-generation pipeline tag on Hugging Face.
harness-1 ships with 20B parameters. Total weight footprint is approximately 20.9 GB, which is the relevant figure when planning local-inference VRAM.
harness-1 is best fit for general-purpose chat and instruction-following workloads. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
arXiv:2606.02373v1 Announce Type: new Abstract: Search agents are often trained as policies over growing transcripts: the model must decide how to search while also remembering what it has seen, which evidence is useful, which constraints remain open, and which claims have actually been checked. We
Harness-Bench: Evaluating Agent Harnesses across Models and Realistic Workflows
arXiv:2605.27922v2 Announce Type: replace Abstract: LLM agents are increasingly deployed as executable systems that use tools, modify workspaces, and produce concrete artifacts. In such workflows, performance depends not only on the base model, but also on the harness: the system layer that manages
CoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness
arXiv:2610.21910v1 Announce Type: new Abstract: As Vision-Language Models (VLMs) advance, they are increasingly expected to perform spatiotemporal reasoning over motion, actions, and view changes beyond what the input images show. Video World Models (VWMs) provide a natural unified engine for visual
Knowledge Graphs as Files: An Agent Harness Where Tool Creation and Tool Use Co-Evolve
arXiv:2610.18616v2 Announce Type: replace-cross Abstract: Searching text-rich knowledge graphs requires following relations while examining textual evidence. Predefined graph interfaces constrain what evidence agents can access, even when they write code to combine tool calls or process retrieved su
TRACER: A Multimodal Harness for Patient Care in Hospitals
arXiv:2610.21266v1 Announce Type: cross Abstract: Continuous video and clinical records provide complementary information for understanding how patient behavior evolves over a hospital stay. A central challenge is how to represent behavior across the entire stay while preserving access to fine-grain
ToolBottleneckBench: Measuring Tool-Agent Performance under Controlled Pressures and Fixed Harness Budgets
arXiv:2610.21098v1 Announce Type: cross Abstract: The success score of a tool agent reflects both its model and the budgets of the harness that runs it. We present ToolBottleneckBench, a benchmark that measures tool-agent performance under controlled pressures and fixed harness budgets. Synthetic en
