LLM Agents Harnesses are hand-designed and stay fixed, so agents accumulate experience but never learn how to use it: which memories to retrieve, when retrieved evidence is misleading, and when the retrieval strategy itself should change. We introduce Agent Evolving Learning (AEL), a two-timescale framework that evolves the harness, recasting memory use as online policy selection. A fast Thompson Sampling bandit selects among memory-retrieval policies episode by episode, while slow LLM reflection follows a diagnose-before-prescribe principle: it first explains why performance degraded, then injects a targeted new retrieval policy as a bandit arm when the current pool plateaus. AEL outperforms ten self-improving and nonLLM baselines on a sequential portfolio benchmark, lifting Sharpe by 27% over the strongest memory-only variant with the lowest variance among all stochastic methods, and generalizes to a support-ticket routing stream, where it improves accuracy by 18% over reflectionfree Thompson Sampling and by 51% over the best prior baseline. Mechanism studies further show that the gains are causal: reflection helps precisely when regimes demand different retrieval behavior, and is provably no-harm/nogain when the best policy is stable.

Large Language Models (LLMs) are exhibiting emergent human-like abilities and are envisioned as the tool for simulating an individual’s communication patterns, behaviors, and personality traits. However, current evaluations of LLM-based persona simulation remain limited: most rely on synthetic dialogues and lack fine-grained analysis of the capability for persona simulation. To address these limitations, we introduce TwinVoice, a comprehensive benchmark for assessing persona simulation across diverse real-world contexts. TwinVoice encompasses three dimensions: Social Persona (public social interactions), Interpersonal Persona (private dialogues), and Narrative Persona (role-based expression). It further decomposes the evaluation into six fundamental capabilities, including opinion consistency, memory recall, logical reasoning, lexical fidelity, persona tone, and syntactic style. Experimental results reveal that while advanced models achieve moderate accuracy in persona simulation, they still fall short of capabilities such as syntactic style and memory recall. Our data, code, and evaluation results are available.

Text-Attributed Graphs (TAGs), where each node is associated with text descriptions, are ubiquitous in real-world scenarios. They typically exhibit distinctive structure and domain-specific knowledge, motivating the development of Graph Foundation Models (GFMs) that generalize across diverse graphs and tasks. Despite large efforts to integrate Large Language Models (LLMs) and Graph Neural Networks (GNNs) for TAGs, most approaches suffer from decoupled architectures with two-stage alignment, limiting their synergistic potential. Even worse, existing methods assign out-of-vocabulary (OOV) tokens to graph nodes, leading to graph-specific semantics, token explosion, and incompatibility with task-oriented prompt templates, which hinders cross-graph and cross-task transferability. To address these challenges, we propose PromptGFM, a versatile GFM for TAGs grounded in graph vocabulary learning. PromptGFM comprises two key components: (a) a graph understanding module, which explicitly prompts LLMs to replicate the fine-grained GNN workflow within the text space, facilitating seamless GNN-LLM integration and elegant graph-text alignment; and (b) a graph inference module, which establishes a language-based graph vocabulary to ensure expressiveness, transferability, and scalability, enabling readable instructions for joint LLM fine-tuning across graphs and tasks. Extensive experiments demonstrate the superiority of PromptGFM, highlighting its strong transferability across diverse graphs and tasks and its adaptability to auxiliary pre-training tasks. The code is available at https://github.com/agiresearch/PromptGFM.

Traditional recommender systems usually take the user-platform paradigm, where users are directly exposed under the control of the platform’s recommendation algorithms. However, the defect of recommendation algorithms may put users in very vulnerable positions under this paradigm. First, many sophisticated models are often designed with commercial objectives in mind, focusing on the platform’s benefits, which may hinder their ability to protect and capture users’ true interests. Second, these models are typically optimized using data from all users, which may overlook individual user’s preferences. Due to these shortcomings, users may experience several disadvantages under the traditional user-platform direct exposure paradigm, such as lack of control over the recommender system, potential manipulation by the platform, echo chamber effects, or lack of personalization for less active users due to the dominance of active users during collaborative learning. Therefore, there is an urgent need to develop a new paradigm to protect user interests and alleviate these issues. Recently, some researchers have introduced LLM agents to simulate user behaviors, these approaches primarily aim to optimize platform-side performance, leaving core issues in recommender systems unresolved. To address these limitations, we propose a new user-agent-platform paradigm, where agent serves as the protective shield between user and recommender system that enables indirect exposure. To this end, we first construct four recommendation datasets, denoted as InstructRec, along with user instructions for each record. To understand user’s intention, we design an Instruction-aware Agent capable of using tools to acquire knowledge from external environments. Moreover, we introduce an Individual Instruction-aware Agent, which incorporates a dynamic memory mechanism to optimize from individual feedback. Results on four datasets demonstrate that consistently achieves an average improvement of 16.6% over SOTA baselines across ranking metrics. Moreover, iAgent mitigates echo chamber effects and effectively alleviates the model bias in disadvantaged users (less-active), serving as a shield between user and recommender systems.

Effectively encoding layout information is a central problem in structured document understanding. Most existing methods rely heavily on millions of trainable parameters to learn the layout features of each word from Cartesian coordinates. However, two unresolved questions remain: (1) Is the Cartesian coordinate system the optimal choice for layout modeling? (2) Are massive learnable parameters truly necessary for layout representation? In this paper, we address these questions by proposing Layout Attention with Gaussian Biases (LAGaBi): Firstly, we find that polar coordinates provide a superior choice over Cartesian coordinates as they offer a measurement of both distance and angle between word pairs, capturing relative positions more effectively. Furthermore, by feeding the distances and angles into 2-D Gaussian kernels, we model intuitive inductive layout biases, i.e., the words closer within a document should receive more attention, which will act as the attention biases to revise the textual attention distribution. LAGaBi is model-agnostic and language-independent, which can be applied to a range of transformer-based models, such as the text pre-training models from the BERT series and the LayoutLM series that incorporate visual features. Experimental results on three widely used benchmarks demonstrate that, despite reducing the number of layout parameters from millions to 48, LAGaBi achieves competitive or even superior performance.