Chenyu Zhou

Agentic memory - conditioning large language and vision-language models on past cases, external knowledge, or meta-experiences - has become a key mechanism for improving inference-time reasoning. However, existing approaches largely rely on heuristic retrieval or expensive LLM-based reranking, and do not explicitly learn how to compose memory for a given query. To address these limitations, we propose MemDecoder, a learned framework for adaptive agentic memory selection. MemDecoder formulates memory composition as an autoregressive index decoding problem over a retrieved candidate set, using a lightweight Transformer encoder-decoder to generate an ordered sequence of memory elements. This design enables efficient, task-aware few-shot reasoning without generating textual demonstrations. MemDecoder can be trained via supervised fine-tuning and reinforcement learning with verifiable rewards. We further introduce a ranking-aware variant of Group Relative Policy Optimization that exploits pairwise comparisons within response groups to provide richer learning signals. Experiments across visual question answering, mathematical reasoning, and scientific question answering benchmarks show that MemDecoder consistently outperforms prior agentic memory selection methods, demonstrating the benefits of the architectural design and learning algorithm of MemDecoder.

Optimization modeling underpins real-world decision-making in logistics, manufacturing, energy, and public services, but reliably solving such problems from natural-language requirements remains challenging for current large language models (LLMs). In this paper, we propose Agora-Opt, a modular agentic framework for optimization modeling that combines decentralized debate with a read-write memory bank. Agora-Opt allows multiple agent teams to independently produce end-to-end solutions and reconcile them through an outcome-grounded debate protocol, while memory stores solver-verified artifacts and past disagreement resolutions to support training-free improvement over time. This design is flexible across both backbones and methods: it reduces base-model lock-in, transfers across different LLM families, and can be layered onto existing pipelines with minimal coupling. Across public benchmarks, Agora-Opt achieves the strongest overall performance among all compared methods, outperforming strong zero-shot LLMs, training-centric approaches, and prior agentic baselines. Further analyses show robust gains across backbone choices and component variants, and demonstrate that decentralized debate offers a structural advantage over centralized selection by enabling agents to refine candidate solutions through interaction and even recover correct formulations when all initial candidates are flawed. These results suggest that reliable optimization modeling benefits from combining collaborative cross-checking with reusable experience, and position Agora-Opt as a practical and extensible foundation for trustworthy optimization modeling assistance.

LLM agent development increasingly relies on reorganizing runtime infrastructure rather than modifying model weights. We present a framework analyzing four externalization dimensions: memory stores persist state over time, skills encapsulate procedural knowledge, protocols structure interactions, and harness engineering coordinates these elements into reliable execution. We trace progress from weights to context to harness design, examining trade-offs between parametric and externalized capabilities while discussing evaluation challenges and the co-evolution of models with external infrastructure.

Large Language Models (LLMs) have shown promising capabilities for solving Operations Research (OR) problems. While reinforcement learning serves as a powerful paradigm for LLM training on OR problems, existing works generally face two key limitations. First, outcome reward suffers from the credit assignment problem, where correct final answers can reinforce flawed reasoning. Second, conventional discriminative process supervision is myopic, failing to evaluate the interdependent steps of OR modeling holistically. To this end, we introduce StepORLM, a novel self-evolving framework with generative process supervision. At its core, StepORLM features a co-evolutionary loop where a policy model and a generative process reward model (GenPRM) iteratively improve on each other. This loop is driven by a dual-feedback mechanism: definitive, outcome-based verification from an external solver, and nuanced, holistic process evaluation from the GenPRM. The combined signal is used to align the policy via Weighted Direct Preference Optimization (W-DPO) and simultaneously refine the GenPRM. Our resulting 8B-parameter StepORLM establishes a new state-of-the-art across six benchmarks, significantly outperforming vastly larger generalist models, agentic methods, and specialized baselines. Moreover, the co-evolved GenPRM is able to act as a powerful and universally applicable process verifier, substantially boosting the inference scaling performance of both our own model and other existing LLMs.

Dynamic programming (DP) is a fundamental method in operations research, but formulating DP models has traditionally required expert knowledge of both the problem context and DP techniques. Large Language Models (LLMs) offer the potential to automate this process. However, DP problems pose unique challenges due to their inherently stochastic transitions and the limited availability of training data. These factors make it difficult to directly apply existing LLM-based models or frameworks developed for other optimization problems, such as linear or integer programming. We introduce DP-Bench, the first benchmark covering a wide range of textbook-level DP problems to enable systematic evaluation. We present Dynamic Programming Language Model (DPLM), a 7B-parameter specialized model that achieves performance comparable to state-of-the-art LLMs like OpenAI’s o1 and DeepSeek-R1, and surpasses them on hard problems. Central to DPLM’s effectiveness is DualReflect, our novel synthetic data generation pipeline, designed to scale up training data from a limited set of initial examples. DualReflect combines forward generation for diversity and backward generation for reliability. Our results reveal a key insight: backward generation is favored in low-data regimes for its strong correctness guarantees, while forward generation, though lacking such guarantees, becomes increasingly valuable at scale for introducing diverse formulations. This trade-off highlights the complementary strengths of both approaches and the importance of combining them.

In the rapidly evolving Web3 world, non-fungible token (NFT) communities are reshaping the formation, distribution, and activation of social capital in ways distinct from traditional models. However, despite their growing impact on societal prosperity, a comprehensive understanding of social capital dynamics within Web3 NFT communities remains limited. This study explores the Mfers community, a key example within Web3 NFT ecosystems. By analyzing social media and blockchain data and using a Delphi method-based human-large language model (LLM) collaboration, we uncovered unique social capital patterns across six dimensions. Our findings highlight a compelling blend of decentralization, inclusion, trust, and empowerment but also raise critical questions about wealth inequality, content quality, and ethical challenges. Based on the findings, we discussed the uniqueness of social capital in Web3 NFT communities, the tension between technical and power decentralization, and the multidimensional nature of societal prosperity. We also suggested directions for future research on decentralized online communities in the CSCW field. This study provides a systematic perspective on social capital in Web3 NFT communities and introduces an innovative human-LLM collaborative analysis, offering insights into the design and governance of benign decentralized online communities.

As Web3 projects leverage airdrops to incentivize participation, airdrop hunters tactically amass wallet addresses to capitalize on token giveaways. This poses challenges to the decentralization goal. Current detection approaches tailored for cryptocurrencies overlook non-fungible tokens (NFTs) nuances. We introduce ARTEMIS, an optimized graph neural network system for identifying airdrop hunters in NFT transactions. ARTEMIS captures NFT airdrop hunters through: (1) a multimodal module extracting visual and textual insights from NFT metadata using Transformer models; (2) a tailored node aggregation function chaining NFT transaction sequences, retaining behavioral insights; (3) engineered features based on market manipulation theories detecting anomalous trading. Evaluated on decentralized exchange Blur’s data, ARTEMIS significantly outperforms baselines in pinpointing hunters. This pioneering computational solution for an emergent Web3 phenomenon has broad applicability for blockchain anomaly detection. The data and code for the paper are accessible at the following link: doi.org/10.5281/zenodo.10676801.

Blockchain, pivotal in shaping the metaverse and Web3, often draws criticism for high energy consumption and carbon emission. The rise of sustainability-focused blockchains, especially when intersecting with innovative wireless technologies, revises this predicament. To understand blockchain’s role in sustainability, we propose a three-layers structure encapsulating four green utilities: Recording and Tracking, Wide Verification, Value Trading, and Concept Disseminating. Nori, a decentralized voluntary carbon offset project, serves as our case, illuminating these utilities. Our research unveils unique insights into the on-chain carbon market participants, affect factors of the market, value propositions of NFT-based carbon credits, and the role of social media to spread the concept of carbon offset. We argue that blockchain’s contribution to sustainability is significant, with carbon offsetting potentially evolving as a new standard within the blockchain sector.