Metraipolis › archive › dc_ff04e221a647
Causal Improvement Graph for Agentic Harness Optimization — arXiv:2610.05039
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.05039
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:28:13.097Z
- SHA-256 of the archived text
3bceca325cb9b6adfbee28c4d86c16d7bc9bc4269204fd7839cd81f0311d2d45- Stable URL of this page
https://metraipolis.com/documento/dc_ff04e221a647
How to cite
Causal Improvement Graph for Agentic Harness Optimization — arXiv:2610.05039 — arXiv, https://arxiv.org/abs/2610.05039 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff04e221a647 (Metraipolis archive dc_ff04e221a647, sha256 3bceca325cb9b6adfbee28c4d86c16d7bc9bc4269204fd7839cd81f0311d2d45)
BibTeX
@misc{dcff04e221a647,
title = {Causal Improvement Graph for Agentic Harness Optimization — arXiv:2610.05039},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.05039},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff04e221a647; sha256 3bceca325cb9b6adfbee28c4d86c16d7bc9bc4269204fd7839cd81f0311d2d45},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05039. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Agentic Harness is the runtime that constructs task context and controls execution flow, thereby shaping overall agent performance. Given a fixed model and external evaluation, automated Harness optimization seeks to improve this runtime through an iterative proposal--evaluation loop to better solve target tasks. Existing meta-harness methods mainly adopt proposer-centric discovery, in which an LLM-based proposer integrates accumulated experimental findings to determine subsequent Harness revisions. This places the burden of maintaining the evolving improvement state on the proposer as history expands and its underlying experimental logic becomes harder to discern. In this paper, we introduce the Causal Improvement Graph (CIG), a graph-governed meta-harness framework that externalizes the evolving improvement state in a persistent graph, allowing prior findings to directly govern subsequent Harness optimization through local proposer operations. CIG grows and links Evidence, Hypothesis, Intervention, and Outcome nodes to represent what was observed, how it may be explained, how to test that explanation, and what the evaluation reveals. Their structural relations preserve how the improvement state changes across iterations, allowing local proposers to build directly on relations among prior findings rather than recover them from raw history. Across various agent tasks, CIG discovers stronger Harnesses than previous meta-harness baselines and remains robust to the choice of task solver and proposer. Structural ablations further support the design of an explicit improvement state with graph-governed evolution. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.05039 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T05:24:20.296Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).