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.
arXiv:2608. 13833v1 Announce Type: cross Abstract: Conversational advertising aims to deliver useful ads within multi-turn assistant interactions.
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.
arXiv:2606. 01311v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on reusable external skills to solve long-horizon interactive tasks.
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.
arXiv:2610.07792v1 Announce Type: cross Abstract: Large language model agents are increasingly deployed to perform complex tasks in real-world environments. However, the knowledge required for correc...
arXiv:2607. 17719v2 Announce Type: replace Abstract: User experience is a first-class objective in industrial e-commerce recommender systems (RS).
User experience is a first-class objective in industrial e-commerce recommender systems (RS). Post-ranking strategies, which govern diversity, similarity, and exposure over a ranked list, are widely deployed in industrial RS for their simplicity and low serving cost.
The paper introduces AMBER, an append‑only memory framework for language‑model agents that interact over long horizons. AMBER lets agents jointly learn to reason, act, and write free‑form memory, guaranteeing retention by construction and enabling end‑to‑end reinforcement learning without extensive curated data. Experiments on WebArena Lite show AMBER outperforms overwrite‑based memory by 4.09 percentage points in average success and improves task completion rates in repeated runs.
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. Yet current evaluations do not isolate this form of transfer.
arXiv:2607. 29241v1 Announce Type: cross Abstract: Optimizing modern recommender models still depends heavily on engineers manually iterating over architectural, objective, and training-strategy changes.
arXiv:2606. 10064v1 Announce Type: cross Abstract: Small-model agentic post-training is bottlenecked less by the algorithm than by the trajectory substrate it consumes.
arXiv:2606. 07412v1 Announce Type: cross Abstract: LLM-driven software engineering agents have become a central testbed for real-world language-model capability, yet their training remains limited by the availability of high-quality SWE tasks.