Hugging Face Trending Papers

ReTrace: Distilling Tool-Using Agents into Planner-Free Workflows

Read the original on Hugging Face Trending Papers →

ReTrace transforms standard operating procedures (SOPs) and logged agent runs into reusable workflows that use code, rather than an LLM, to select the next step. By extracting conditions from agent reasoning and merging them into a compact rule document, ReTrace produces executable workflows that can be compiled for various orchestration platforms. In experiments, ReTrace achieves high completion rates and significant cost and latency reductions compared to the original LLM agent, especially after repair rounds on training failures.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

arXiv AI
4d ago

ReTrace: Distilling Tool-Using Agents into Planner-Free Workflows

ReTrace converts a standard operating procedure (SOP) and a handful of logged agent runs into a reusable, planner‑free workflow that uses code, not an LLM, to select the next step. By extracting the conditions behind each tool call and merging them into a compact rule document, ReTrace produces an executable workflow that can be compiled for various orchestration platforms. In tests, ReTrace achieves high completion rates (up to 93.8 %) with significantly lower cost and faster execution (1.3 s vs. 170 s) compared to the original LLM agent.

By Kaiyuan Hou, Yang Ping Kuo, Indranil Bhattacharya, Rohith Nama, Arushi Gupta, Carlos D. Castillo, Prathap Ramachandra, Xiaofan Jiang, Francesco Carbone
Hugging Face Trending Papers
Oct 27

Does Your Generalist Skill Optimizer Really Incentivize Agentic Tasks? Rethinking Skill Optimization via Bipartite Attribution

The paper introduces BiPA, a method to evaluate skill optimizers that rewrite natural‑language procedures for agents performing long‑horizon tasks. BiPA replays the optimizer’s acceptance rule on identical candidates to isolate selection effects and records each episode as a bipartite graph of turns and read text, revealing that learned skills only marginally outperform hand‑written seeds and that many gains vanish on test data. The study finds optimizers add extra input tokens and turns, and proposes four design principles for more reliable skill editing.

arXiv AI
Oct 28

Does Your Generalist Skill Optimizer Really Incentivize Agentic Tasks? Rethinking Skill Optimization via Bipartite Attribution

The paper introduces BiPA, a method for evaluating skill optimizers that rewrite natural‑language procedures for agents. By replaying the optimizer’s acceptance rule on identical candidates and recording episodes as bipartite graphs of turns and read text, BiPA isolates the effect of selection from the cost of added input tokens. Experiments on three optimizers, three benchmarks, and two models show that learned skills perform only marginally better than hand‑written seeds, and that apparent dev‑set gains often disappear on test, revealing that optimizers tend to add redundant rules that increase token usage.

By Jiawei Zhou, Bo Peng, Yuxuan Huang, Ming Zhang, Youbang Sun, Xiang Wang, Chaochao Lu
arXiv AI
Oct 2

Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization

The paper introduces InFlowOp, a label‑free optimization framework that assigns costs to each decision in a multi‑agent workflow, balancing agent competence against execution time. It determines task granularity and agent assignment before execution and corrects faults during execution using the same cost metric. The authors also present Braid, a benchmark for multi‑agent coordination, and show that InFlowOp outperforms single‑agent baselines by up to 11.97% across various domains.

By Xuehang Guo, Haoyu Wang, Shengyu Chen, Zach Chen, Wei Cheng, Qingyun Wang, Haifeng Chen