arXiv subjects

Yunbo Long

Publications and source records attributed to Yunbo Long.

At least 19 recordsLinked to original sources

arXiv2026

EmoDistill: Offline Emotion Skill Distillation for Language Model Agents in Adversarial Negotiation

Post-trained LLMs are often optimized to produce helpful, polite, and accommodating responses. In adversarial negotiation, however, such behavior can become a vulnerability: emotionally framed language may influence an agent's bargaining decisions in ways that conflict with its user's objectives. We therefore introduce EmoDistill, an offline framework for distilling emotional negotiation skills from LLM-LLM interactions into smaller language-model agents. Here, an emotional negotiation skill is a state-conditioned behavior that determines which explicit emotion to invoke in a bargaining state and how to realize that emotion as an effective negotiation utterance. EmoDistill learns these two components separately: an Implicit Q-Learning (IQL) selector learns which emotion to express in each bargaining state, while a LoRA-adapted 7B policy learns emotion-conditioned expression through Supervised Fine-Tuning (SFT) and Judge Policy Optimization (JPO). Across four emotion-sensitive negotiation domains, the full EmoDistill policy achieves competitive utility and improves over vanilla and IQL-only baselines in most settings. Emotion-free ablations show that removing the explicit emotion channel substantially reduces overall negotiation utility, while transfer experiments reveal partial, domain-dependent transfer and robustness to unseen LLM counterparties.

cs.CL↗

arXiv2026

Generating Logically Consistent Synthetic Supply Chain Data with LLM-Driven Knowledge Graph Reasoning

Synthetic data offers a promising solution to two persistent barriers in supply chain analytics: data scarcity and data privacy. However, for synthetic data to support operational simulation and decision-making, it must do more than reproduce the statistical distributions of real records, and also preserve the \emph{operational logic} that governs supply chain processes, including the temporal orderings, mathematical dependencies, hierarchical taxonomies, and conditional rules that make a record operationally plausible. We consider this logic as the ``physics'' of supply chain data. Existing tabular generative models are primarily optimized for distributional fidelity and downstream predictive utility, and therefore often generate records that appear statistically realistic but violate fundamental operational constraints. This paper introduces \textbf{\textit{TabKG}}, a knowledge-graph-guided framework for logically consistent synthetic supply chain tabular data generation. TabKG constructs a \textbf{\textit{Column Relationship Knowledge Graph (CR-KG)}} to represent data operational dependencies. It uses a multi-LLM ensemble with majority voting to propose candidate relationships from column metadata, validates these relationships against real data to remove hallucinated or unsupported edges, and then uses the validated CR-KG to guide generation. Specifically, TabKG compresses the original table into independent columns, generates these columns using a latent diffusion model, and deterministically reconstructs dependent columns according to the validated relationships, enforcing logical consistency by construction with respect to the discovered operational rules.

cs.CL↗

arXiv2026

Helicase: Uncertainty-Guided Supply Chain Knowledge Graph Construction with Autonomous Multi-Agent LLMs

LLM-based multi-agent systems have been widely adopted for knowledge retrieval and report generation, synthesizing known information through web search and textual reasoning. However, many critical information tasks in supply chains are not simple one-shot queries: they are structural inference problems requiring multi-hop reasoning across complex, fragmented web resources. Questions such as \textit{``Which Tesla components use lithium from Australian mines?''} have no answer in any single document; answers must be computationally synthesized through the autonomous construction and analysis of dynamic knowledge graphs assembled from fragmented, heterogeneous sources. Moreover, such discovery processes must be uncertainty-aware: decisions depend not only on answers but on calibrated confidence in their reliability, traceable to source quality and reasoning consistency. To address this capability gap, we propose \textit{Helicase}, an autonomous multi-agent LLM system for uncertainty-guided supply chain knowledge graph construction. \textit{Helicase} decomposes high-level supply-chain queries into executable investigation plans, coordinates specialized web-search, reasoning, and coding agents through iterative verification loops, and incrementally constructs query-specific supply chain knowledge graphs with per-fact uncertainty annotations. Its three-layer uncertainty framework tracks uncertainty at the action, trajectory, and memory layers, enabling both structural inference and calibrated confidence assessment. To evaluate autonomous reasoning across the full complexity spectrum, we introduce SCQA (Supply Chain Query Assessment), a benchmark of 80 supply chain queries organized into four quadrants spanning single-hop to multi-hop inference under both high and low data visibility.

cs.AI↗

arXiv2026

VeriTrace: Evolving Mental Models for Deep Research Agents

Deep research agents face vast, interdependent, and pervasively uncertain information. Existing systems explore what evolving intermediate representations should look like, but leave their evolution to the LLM's implicit reasoning. Without explicit regulation, the intermediate layer is easily contaminated by mixed-quality information, and errors propagate along its dependencies, so model scale often ends up substituting for absent regulation. We argue that an agent's mental model should instead evolve through explicit feedback that continuously aligns task understanding with reality, and identify three regulatory loops: interpretive update, deviation feedback, and schema revision. We realise this in VeriTrace, a cognitive-graph framework that explicitly implements the three loops. Using matched Qwen3.5-27B backbones, VeriTrace improves over the strongest matched baseline by an average of 4.82 pp on DeepResearch Bench (DRB) Insight (1.83 pp Overall) and by 5.9 pp Overall win rate on DeepConsult. With Config-DeepSeek, it achieves the strongest reproducible open-source result on DRB.

cs.AI↗

arXiv2026

Self-Policy Distillation via Capability-Selective Subspace Projection

Self-distillation bootstraps large language models (LLMs) by training on their own generations. However, existing methods either rely on external signals to curate self-generated outputs (e.g., correctness filtering, execution feedback, and reward search), which are costly and unavailable for the best-performing frontier models, or skip curation entirely and train on all raw outputs, an approach that is often domain-specific and hard to generalize. Both also share a deeper weakness that self-generated outputs entangle task-relevant capability with others, such as stylistic patterns, formatting artifacts, and model-specific errors, diluting the signal for the specific capability one aims to improve. In this paper, we propose Self-Policy Distillation (SPD), which achieves generalizable, capability selective without any external signal. Specifically, SPD extracts a low-rank capability subspace from the model's own gradients on correctness-defining tokens, projects key-value (KV) activations into this subspace during self-generation, and fine-tunes on the resulting raw outputs with standard next-token prediction loss. Through extensive experiments across code generation, mathematical reasoning, and multiple-choice QA, we show that SPD achieves up to 13% improvement over state-of-the-art self-distillation methods without external signals and up to 16% improvement over pre-trained baselines. Notably, SPD demonstrates superior generalizability, achieving 15% better performance under out-of-domain generalization settings.

cs.CL↗

arXiv2026

Self-Evolving Multi-Agent Systems via Decentralized Memory

Self-evolving multi-agent systems (MAS) have emerged as a promising route to LLM agents that continually improve from experience, with persistent memory at their foundation. However, existing designs almost exclusively adopt a centralized repository shared across agents, incurring communication and coordination overhead, raising privacy concerns, and collapsing agent diversity. We propose DecentMem, a decentralized memory framework in which each agent maintains its own dual-pool memory -- an exploitation pool of consolidated past trajectories and an exploration pool of LLM-generated candidates for unseen contexts. The two pools are reweighted online based on stage-wise feedback from an LLM-as-a-judge. Theoretically, we prove that this design guarantees global reachability of the solution space and achieves $O(\log T)$ cumulative regret, matching the stochastic bandit lower bound up to constants. In practice, across three MAS frameworks (AutoGen, DyLAN, AgentNet), three Qwen3 backbones (4B/8B/14B), two Gemma4 backbones (E2B/E4B) and five benchmarks spanning math, code, QA, and embodied tasks, DecentMem improves average accuracy by up to 23.8% over the strongest centralized memory baseline and by up to 52.5% over the no-memory baseline, while reducing token usage by up to 49%.

cs.MA↗

arXiv2026

Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training

Tabular language models can generate synthetic tables by modeling rows as token sequences, but they are typically trained once with supervised fine-tuning and then used as static synthesizers. This is limiting because next-token likelihood does not directly optimize the distributional, utility, and indistinguishability properties used to evaluate synthetic data. We study iterative reward-guided post-training for tabular language models through a generate--score--align protocol, where a generator samples synthetic rows, a task-specified reward ranks them, and the model is updated relative to a fixed supervised reference. Within this protocol, we propose \textbf{TabGRAA} (\textbf{Tab}ular \textbf{G}roup-\textbf{R}elative \textbf{A}dvantage \textbf{A}lignment), a group-relative alignment method that compares high- and low-reward generated groups using group-averaged policy/reference log-ratios rather than one-to-one preference pairs. Across five mixed-type benchmarks, TabGRAA improves a GReaT backbone beyond additional supervised fine-tuning and achieves the strongest average trade-off among adapted DPO, KTO, and NPO baselines on fidelity and downstream utility, while maintaining empirical privacy diagnostics near the supervised baseline. Ablations show that the gains depend on meaningful reward ranking and stable group-level updates rather than extra training alone. Reward-substitution and scorer-separation studies further show that the post-training loop can use both classifier-based and classifier-free rewards, and that proper scorer separation is important for preserving the fidelity--utility--privacy trade-off. These results position TabGRAA as a self-improving post-training method for tabular language-model generators, complementary to strong static tabular synthesizers.

cs.LG↗

arXiv2026

Hidden in Plain Sight: Visual-to-Symbolic Analytical Solution Inference from Field Visualizations

Recovering analytical solutions of physical fields from visual observations is a fundamental yet underexplored capability for AI-assisted scientific reasoning. We study visual-to-symbolic analytical solution inference (ViSA) for two-dimensional linear steady-state fields: given field visualizations (and first-order derivatives) plus minimal auxiliary metadata, the model must output a single executable SymPy expression with fully instantiated numeric constants. We introduce ViSA-R2 and align it with a self-verifying, solution-centric chain-of-thought pipeline that follows a physicist-like pathway: structural pattern recognition solution-family (ansatz) hypothesis parameter derivation consistency verification. We also release ViSA-Bench, a VLM-ready synthetic benchmark covering 30 linear steady-state scenarios with verifiable analytical/symbolic annotations, and evaluate predictions by numerical accuracy, expression-structure similarity, and character-level accuracy. Using an 8B open-weight Qwen3-VL backbone, ViSA-R2 outperforms strong open-source baselines and the evaluated closed-source frontier VLMs under a standardized protocol.

cs.AI↗

arXiv2026

EmoMAS: Emotion-Aware Multi-Agent System for High-Stakes Edge-Deployable Negotiation with Bayesian Orchestration

Large language models (LLMs) has been widely used for automated negotiation, but their high computational cost and privacy risks limit deployment in privacy-sensitive, on-device settings such as mobile assistants or rescue robots. Small language models (SLMs) offer a viable alternative, yet struggle with the complex emotional dynamics of high-stakes negotiation. We introduces EmoMAS, a Bayesian multi-agent framework that transforms emotional decision-making from reactive to strategic. EmoMAS leverages a Bayesian orchestrator to coordinate three specialized agents: game-theoretic, reinforcement learning, and psychological coherence models. The system fuses their real-time insights to optimize emotional state transitions while continuously updating agent reliability based on negotiation feedback. This mixture-of-agents architecture enables online strategy learning without pre-training. We further introduce four high-stakes, edge-deployable negotiation benchmarks across debt, healthcare, emergency response, and educational domains. Through extensive agent-to-agent simulations across all benchmarks, both SLMs and LLMs equipped with EmoMAS consistently surpass all baseline models in negotiation performance while balancing ethical behavior. These results show that strategic emotional intelligence is also the key driver of negotiation success. By treating emotional expression as a strategic variable within a Bayesian multi-agent optimization framework, EmoMAS establishes a new paradigm for effective, private, and adaptive negotiation AI suitable for high-stakes edge deployment.

cs.AI↗

arXiv2026

AI-Supervisor: Autonomous AI Research Supervision via a Persistent Research World Model

Existing automated research systems operate as stateless, linear pipelines -- generating outputs without maintaining any persistent understanding of the research landscape they navigate. They process papers sequentially, propose ideas without structured gap analysis, and lack mechanisms for agents to verify, challenge, or refine each other's findings. We present \textbf{AI-Supervisor}, a multi-agent orchestration framework where specialized agents provide end-to-end AI research supervision driven by human interests -- from literature review through gap discovery, method development, evaluation, and paper writing -- through autonomous exploration and self-correcting updates of research knowledge. Unlike sequential pipelines, AI-Supervisor maintains a continuously evolving \emph{Research World Model}, implemented as a Knowledge Graph, that captures methods, benchmarks, known limitations, and unexplored gaps, serving as shared memory across all agents and enabling agents to explore and build upon a structured understanding of the research landscape. The framework introduces three architectural contributions: (1) \emph{structured gap discovery} that decomposes methods into core modules, validates their performance across benchmarks, and maps the specific gaps each module creates; (2) \emph{self-correcting discovery loops} that probe why modules succeed on certain problems and fail on others, whether benchmarks carry hidden biases, and whether evaluation protocols remain adequate for emerging challenges; and (3) \emph{self-improving development loops} governed by cross-domain mechanism search that iteratively targets failing modules by finding solutions from other scientific fields. All agents operate under a \emph{consensus mechanism} where independent findings are corroborated before being committed to the Research World Model.

cs.AI↗

arXiv2025

Topological Federated Clustering via Gravitational Potential Fields under Local Differential Privacy

Clustering non-independent and identically distributed (non-IID) data under local differential privacy (LDP) in federated settings presents a critical challenge: preserving privacy while maintaining accuracy without iterative communication. Existing one-shot methods rely on unstable pairwise centroid distances or neighborhood rankings, degrading severely under strong LDP noise and data heterogeneity. We present Gravitational Federated Clustering (GFC), a novel approach to privacy-preserving federated clustering that overcomes the limitations of distance-based methods under varying LDP. Addressing the critical challenge of clustering non-IID data with diverse privacy guarantees, GFC transforms privatized client centroids into a global gravitational potential field where true cluster centers emerge as topologically persistent singularities. Our framework introduces two key innovations: (1) a client-side compactness-aware perturbation mechanism that encodes local cluster geometry as "mass" values, and (2) a server-side topological aggregation phase that extracts stable centroids through persistent homology analysis of the potential field's superlevel sets. Theoretically, we establish a closed-form bound between the privacy budget $\epsilon$ and centroid estimation error, proving the potential field's Lipschitz smoothing properties exponentially suppress noise in high-density regions. Empirically, GFC outperforms state-of-the-art methods on ten benchmarks, especially under strong LDP constraints ($\epsilon < 1$), while maintaining comparable performance at lower privacy budgets. By reformulating federated clustering as a topological persistence problem in a synthetic physics-inspired space, GFC achieves unprecedented privacy-accuracy trade-offs without iterative communication, providing a new perspective for privacy-preserving distributed learning.

cs.LG↗

arXiv2025

EQ-Negotiator: Dynamic Emotional Personas Empower Small Language Models for Edge-Deployable Credit Negotiation

The deployment of large language models (LLMs) in automated negotiation has set a high performance benchmark, but their computational cost and data privacy requirements render them unsuitable for many privacy-sensitive, on-device applications such as mobile assistants, embodied AI agents or private client interactions. While small language models (SLMs) offer a practical alternative, they suffer from a significant performance gap compared to LLMs in playing emotionally charged complex personas, especially for credit negotiation. This paper introduces EQ-Negotiator, a novel framework that bridges this capability gap using emotional personas. Its core is a reasoning system that integrates game theory with a Hidden Markov Model(HMM) to learn and track debtor emotional states online, without pre-training. This allows EQ-Negotiator to equip SLMs with the strategic intelligence to counter manipulation while de-escalating conflict and upholding ethical standards. Through extensive agent-to-agent simulations across diverse credit negotiation scenarios, including adversarial debtor strategies like cheating, threatening, and playing the victim, we show that a 7B parameter language model with EQ-Negotiator achieves better debt recovery and negotiation efficiency than baseline LLMs more than 10 times its size. This work advances persona modeling from descriptive character profiles to dynamic emotional architectures that operate within privacy constraints. Besides, this paper establishes that strategic emotional intelligence, not raw model scale, is the critical factor for success in automated negotiation, paving the way for effective, ethical, and privacy-preserving AI negotiators that can operate on the edge.

cs.CL↗

arXiv2025

EvoEmo: Towards Evolved Emotional Policies for Adversarial LLM Agents in Multi-Turn Price Negotiation

Recent research on Chain-of-Thought (CoT) reasoning in Large Language Models (LLMs) has demonstrated that agents can engage in \textit{complex}, \textit{multi-turn} negotiations, opening new avenues for agentic AI. However, existing LLM agents largely overlook the functional role of emotions in such negotiations, instead generating passive, preference-driven emotional responses that make them vulnerable to manipulation and strategic exploitation by adversarial counterparts. To address this gap, we present EvoEmo, an evolutionary reinforcement learning framework that optimizes dynamic emotional expression in negotiations. EvoEmo models emotional state transitions as a Markov Decision Process and employs population-based genetic optimization to evolve high-reward emotion policies across diverse negotiation scenarios. We further propose an evaluation framework with two baselines -- vanilla strategies and fixed-emotion strategies -- for benchmarking emotion-aware negotiation. Extensive experiments and ablation studies show that EvoEmo consistently outperforms both baselines, achieving higher success rates, higher efficiency, and increased buyer savings. This findings highlight the importance of adaptive emotional expression in enabling more effective LLM agents for multi-turn negotiation. The code is available at \href{https://github.com/Yunbo-max/EvoEmo}{\textcolor{red}{https://github.com/Yunbo-max/EvoEmo}}.

cs.AI↗

arXiv2025

SynDelay: A Synthetic Dataset for Delivery Delay Prediction

Artificial intelligence (AI) is transforming supply chain management, yet progress in predictive tasks -- such as delivery delay prediction -- remains constrained by the scarcity of high-quality, openly available datasets. Existing datasets are often proprietary, small, or inconsistently maintained, hindering reproducibility and benchmarking. We present SynDelay, a synthetic dataset designed for delivery delay prediction. Generated using an advanced generative model trained on real-world data, SynDelay preserves realistic delivery patterns while ensuring privacy. Although not entirely free of noise or inconsistencies, it provides a challenging and practical testbed for advancing predictive modelling. To support adoption, we provide baseline results and evaluation metrics as initial benchmarks, serving as reference points rather than state-of-the-art claims. SynDelay is publicly available through the Supply Chain Data Hub, an open initiative promoting dataset sharing and benchmarking in supply chain AI. We encourage the community to contribute datasets, models, and evaluation practices to advance research in this area. All code is openly accessible at https://supplychaindatahub.org.

cs.AI↗

arXiv2025

EmoDebt: Bayesian-Optimized Emotional Intelligence for Strategic Agent-to-Agent Debt Recovery

The emergence of autonomous Large Language Model (LLM) agents has created a new ecosystem of strategic, agent-to-agent interactions. However, a critical challenge remains unaddressed: in high-stakes, emotion-sensitive domains like debt collection, LLM agents pre-trained on human dialogue are vulnerable to exploitation by adversarial counterparts who simulate negative emotions to derail negotiations. To fill this gap, we first contribute a novel dataset of simulated debt recovery scenarios and a multi-agent simulation framework. Within this framework, we introduce EmoDebt, an LLM agent architected for robust performance. Its core innovation is a Bayesian-optimized emotional intelligence engine that reframes a model's ability to express emotion in negotiation as a sequential decision-making problem. Through online learning, this engine continuously tunes EmoDebt's emotional transition policies, discovering optimal counter-strategies against specific debtor tactics. Extensive experiments on our proposed benchmark demonstrate that EmoDebt achieves significant strategic robustness, substantially outperforming non-adaptive and emotion-agnostic baselines across key performance metrics, including success rate and operational efficiency. By introducing both a critical benchmark and a robustly adaptive agent, this work establishes a new foundation for deploying strategically robust LLM agents in adversarial, emotion-sensitive debt interactions. The code is available at \textcolor{blue}{https://github.com/Yunbo-max/EmoDebt}.

cs.CL↗

arXiv2025

Efficient and Privacy-Preserved Link Prediction via Condensed Graphs

Link prediction is crucial for uncovering hidden connections within complex networks, enabling applications such as identifying potential customers and products. However, this research faces significant challenges, including concerns about data privacy, as well as high computational and storage costs, especially when dealing with large-scale networks. Condensed graphs, which are much smaller than the original graphs while retaining essential information, has become an effective solution to both maintain data utility and preserve privacy. Existing methods, however, initialize synthetic graphs through random node selection without considering node connectivity, and are mainly designed for node classification tasks. As a result, their potential for privacy-preserving link prediction remains largely unexplored. We introduce HyDRO\textsuperscript{+}, a graph condensation method guided by algebraic Jaccard similarity, which leverages local connectivity information to optimize condensed graph structures. Extensive experiments on four real-world networks show that our method outperforms state-of-the-art methods and even the original networks in balancing link prediction accuracy and privacy preservation. Moreover, our method achieves nearly 20* faster training and reduces storage requirements by 452*, as demonstrated on the Computers dataset, compared to link prediction on the original networks. This work represents the first attempt to leverage condensed graphs for privacy-preserving link prediction information sharing in real-world complex networks. It offers a promising pathway for preserving link prediction information while safeguarding privacy, advancing the use of graph condensation in large-scale networks with privacy concerns.

cs.LG↗

arXiv2025

PA-CFL: Privacy-Adaptive Clustered Federated Learning for Transformer-Based Sales Forecasting on Heterogeneous Retail Data

Federated learning (FL) enables retailers to share model parameters for demand forecasting while maintaining privacy. However, heterogeneous data across diverse regions, driven by factors such as varying consumer behavior, poses challenges to the effectiveness of federated learning. To tackle this challenge, we propose Privacy-Adaptive Clustered Federated Learning (PA-CFL) tailored for demand forecasting on heterogeneous retail data. By leveraging differential privacy and feature importance distribution, PA-CFL groups retailers into distinct ``bubbles'', each forming its own federated learning system to effectively isolate data heterogeneity. Within each bubble, Transformer models are designed to predict local sales for each client. Our experiments demonstrate that PA-CFL significantly surpasses FedAvg and outperforms local learning in demand forecasting performance across all participating clients. Compared to local learning, PA-CFL achieves a 5.4% improvement in R^2, a 69% reduction in RMSE, and a 45% decrease in MAE. Our approach enables effective FL through adaptive adjustments to diverse noise levels and the range of clients participating in each bubble. By grouping participants and proactively filtering out high-risk clients, PA-CFL mitigates potential threats to the FL system. The findings demonstrate PA-CFL's ability to enhance federated learning in time series prediction tasks with heterogeneous data, achieving a balance between forecasting accuracy and privacy preservation in retail applications. Additionally, PA-CFL's capability to detect and neutralize poisoned data from clients enhances the system's robustness and reliability.

cs.LG↗

arXiv2025

LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusion

Synthetic tabular data are increasingly being used to replace real data, serving as an effective solution that simultaneously protects privacy and addresses data scarcity. However, in addition to preserving global statistical properties, synthetic datasets must also maintain domain-specific logical consistency**-**especially in complex systems like supply chains, where fields such as shipment dates, locations, and product categories must remain logically consistent for real-world usability. Existing generative models often overlook these inter-column relationships, leading to unreliable synthetic tabular data in real-world applications. To address these challenges, we propose LLM-TabLogic, a novel approach that leverages Large Language Model reasoning to capture and compress the complex logical relationships among tabular columns, while these conditional constraints are passed into a Score-based Diffusion model for data generation in latent space. Through extensive experiments on real-world industrial datasets, we evaluate LLM-TabLogic for column reasoning and data generation, comparing it with five baselines including SMOTE and state-of-the-art generative models. Our results show that LLM-TabLogic demonstrates strong generalization in logical inference, achieving over 90% accuracy on unseen tables. Furthermore, our method outperforms all baselines in data generation by fully preserving inter-column relationships while maintaining the best balance between data fidelity, utility, and privacy. This study presents the first method to effectively preserve inter-column relationships in synthetic tabular data generation without requiring domain knowledge, offering new insights for creating logically consistent real-world tabular data. The code is available at https://github.com/Yunbo-max/TabKG.

cs.LG↗