Atlas: Making Sense of Long Horizon Agent Trajectories
Overview & Synopsis
AI agents can now search literature, generate hypotheses, analyze datasets, and run experiments at a scale difficult for researchers to match. Yet scaling scientific execution does not automatically scale researchers' ability to make sense of what agents produce. When researchers return to a long-horizon run, they must evaluate work they did not monitor: what the agent produced, which decisions shaped those outputs, and whether those decisions served the research goal. We frame this post-run sensemaking as a representation problem across three linked levels: goal, decision, and artifact. From this framework we developed Atlas, an agentic workspace with a trajectory tree, which renders the run as a branching structure showing what the agent chose and set aside, and artifact projections over six representations. In a within-subjects study (N=14), participants reported higher decision transparency, artifact sensemaking, and goal connection with Atlas than with a standard baseline, together with substantially lower subjective workload.
arxiv.org)
← / → for pages • + / - for zoom • 0 to fit width
Powered by Mozilla PDF.js v3.11
Document Information
| Document Title | Atlas: Making Sense of Long Horizon Agent Trajectories |
|---|---|
| Author / Organization | Sangho Suh, Joseph Chee Chang, Pao Siangliulue, Amy X. Zhang, Matt Latzke, Jonathan Bragg, Doug Downey, Daniel S. Weld |
| Subject & Discipline | cs.HC |
| Categories | Science & Mathematics |
| Publication Year | 2026 |
| License / Rights | arXiv Open Access / Creative Commons |
| Resource Verification | Listed PDF (Verification Pending) |
| Original Host Website |
arXiv
(arxiv.org)
|
| File Format | application/pdf (Portable Document Format) |
| Language | EN |
| Catalog ID | DOC-265297 |
| Original Source Link | Visit Source Page on arxiv.org » |