← Back to all news
arXiv AI By Xinhua Miao, Yuanzhen Rong, Weiru Zhang, Xiaoyi Zeng

KARMA: Training-Free Knowledge-Atomic Harness Evolution for Industrial Advertising Agents

Read the original on arXiv AI →

KARMA is a training‑free framework that evolves six typed knowledge modules for industrial advertising agents while keeping model weights and harness code unchanged. It uses a deterministic Trace Verifier to map errors to candidate modules, a Critic to compare successful and failed trajectories, and an Evolver that applies atomic knowledge edits validated by a fixed gate. Evaluated on three LLM families across six e‑commerce domains, KARMA improves average hold‑out scores by 8.96 points (+29.7%) and enables transferable, inspectable knowledge adaptation.

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 arXiv AI.

Related stories

arXiv AI
Jul 7

EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer

arXiv:2607. 05202v1 Announce Type: new Abstract: Agent self-evolution in long-horizon LLM systems is largely procedural: useful experience is not merely stored information, but reusable procedures for searching, debugging, and verification.

By Xingze Gao, Chuanrui Hu, Hongda Chen, Pengfei Yao, Zhao Wang, Yi Bai, Zhengwei Wu, Yunyun Han, Xiaofeng Cong, Jie Gui, Yafeng Deng, Teng Li
llmsagentsbenchmarks
More like this →
arXiv AI
Oct 19

GLOBE: Evolving Structured Agentic Memory for E-commerce Product Optimization in Generative Search

GLOBE is an agentic framework designed to improve e‑commerce product listings for generative search by storing optimization knowledge in an evolving handbook of explicit, field‑scoped behaviors. In each episode, an Editor applies relevant behaviors, receives rank‑based feedback, and a Reflector converts this feedback into behavior updates. A Moderator removes redundant proposals, a Curator commits accepted changes, and harmful behaviors are deactivated, turning episodic feedback into a persistent, field‑scoped optimization memory that outperforms monolithic prompt optimization and remains effective on unseen product categories.

By Hyunseo Kim, Suil Choe, Sukkyoung So, Daeyeon Yi
agents
More like this →