Newest papers

HGM-Dual: Lineage-Aware Guided Agent Harness Optimization for Long-Horizon Planning

Sudipta Paul, Pengrui Quan, Aounon Kumar, Nicholas Tzou, Vivek Kulkarni, Srinivas Chappidi · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.30042 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

Harness evaluasi orang tua, yang meningkatkan petunjuk, alat, dan alur kerja orang tua, adalah cara yang semakin efektif untuk meningkatkan agen yang dibangun pada pembekuan atau kode tertutup LLM. Pendekatan terkemuka seperti Darwin--Godel Machine dan Huxley--Godel Machine (HGM) bergantung pada perbaikan diri recursive dan dikembangkan terutama untuk pengkodean, di mana kompetensi yang dibutuhkan untuk meningkatkan agen bertepatan dengan kompetensi yang ditingkatkan. Tugas perencanaan, di mana agen harus menghasilkan urutan panggilan alat yang bersama-sama memuaskan pembatasan interaksi, memecahkan keselarasan ini. Di sana, open-end self-modification secara berulang kali mengeksplorasi perubahan yang tidak efektif dan mengkonsumsi anggaran evaluasi relatif yang signifikan. Kami memperkenalkan HGM-Dual, kerangka

Machine translation (Meta M2M100); the English original follows.

Abstract

Harness optimization, which improves an agent's prompts, tools, and workflows, is an increasingly effective way to enhance agents built on frozen or closed-source LLMs. Leading approaches such as the Darwin--Godel Machine and the Huxley--Godel Machine (HGM) rely on recursive self-improvement and were developed mainly for coding, where the competence needed to improve the agent coincides with the competence being improved. Planning tasks, in which an agent must produce a sequence of tool calls that jointly satisfies interacting constraints, break this alignment. There, open-ended self-modification repeatedly explores ineffective changes and consumes substantial evaluation budgets. We introduce HGM-Dual, a diagnostic-guided framework for budget-efficient harness evolution for planning agents. First, HGM-Dual represents agent evolution as lineage-aware context. This context records what each ancestor changed, which behaviors improved or regressed, and which modifications were ineffective, giving the editor explicit edit-outcome attribution instead of an unstructured archive of past agents. Second, HGM-Dual introduces error-conditioned dual-path child generation. For each selected parent, it generates a general child that preserves open-ended exploration and specialized children that target the harness components most likely responsible for the parent's highest-ranked constraint violations. HGM-Dual outperforms the strongest baseline by up to 14.45% relative improvement in case accuracy while matching HGM variants' final performance with 2x-4x fewer evaluation budget.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Competence (human resources), Computer science, Context (archaeology), Artificial intelligence, Sequence (biology), Matching (statistics)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange