arXiv subjects

Jiaxiang Chen

Publications and source records attributed to Jiaxiang Chen.

18 recordsLinked to original sources

arXiv2026

MetaPS: Adaptive Programmatic Strategy Selection for Market Agents

No single market strategy always wins: momentum, mean reversion, risk control,and event-driven rules can each succeed or fail as market conditions change.Rather than asking large language models to directly generate market actions,we study an executable decision paradigm where an agent selects from a library of programmatic strategies, each implemented as a code module mapping market observations to actions.We propose \textbf{MetaPS}, a simulation-guided framework for adaptive programmatic strategy selection. MetaPS rolls out candidate strategies in simulated or backtested markets, identifies states where particular strategies lead to better future outcomes, and converts these state--strategy pairs into supervised fine-tuning data. During inference, the simulator is no longer queried: MetaPS observes only the current market state and candidate strategy context, selects a suitable strategy program, and the selected program produces the final action. Experiments on multi-stock trading and a controlled goods-exchange sandbox show that MetaPS consistently improves across model scales from 0.8B to 9B parameters. It outperforms fixed-strategy baselines, direct decision-making agents, and prompted API-based LLM agents; in several settings, compact fine-tuned models even surpass stronger API models. These results demonstrate that market simulations can provide scalable and targeted supervision for learning adaptive, interpretable, and executable strategy selection.

cs.AI↗

arXiv2026

IterInject: Indirect Prompt Injection Against LLM Agents via Feedback-Guided Iterative Optimization

LLM-based agents are increasingly deployed for complex tasks requiring planning, tool use, and interaction with external services. Their reliance on untrusted external content exposes them to indirect prompt injection (IPI), in which adversarial instructions embedded in retrieved data hijack agent behavior. Existing attacks rely on static payloads that cannot adapt to agent-specific defenses; even recent adaptive methods lack structured feedback to guide optimization. We introduce \oursys, a feedback-guided iterative framework that closes the loop between injection, diagnosis, and refinement: a rule-based diagnoser produces structured outcome labels with behavioral descriptions, and an LLM-based optimizer refines payloads conditioned on the full optimization history. A synthesis step generates new disguise seeds from failure patterns, enabling the strategy space to self-evolve. On AgentDojo and InjectAgent, \oursys substantially outperforms static baselines and existing adaptive methods across four victim models. Extension experiments on Claude Code, a production-grade coding agent with layered defenses, show that optimized payloads achieve full success on 5 of 9 targets; even those that resist full exploitation exhibit measurable improvement from iterative refinement. We further present a mechanistic analysis of IPI, identifying an attention-mediated threshold mechanism in mid-to-late layers; three causal interventions validate this finding and point to concrete defense directions.

cs.LG↗

arXiv2026

DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding

Preference-based alignment methods (e.g., RLHF, DPO) typically optimize a single scalar objective, implicitly averaging over heterogeneous human preferences. In practice, systematic annotator and user-group disagreement makes mean-reward maximization brittle and susceptible to proxy over-optimization. We propose **Disagreement-Aware Alignment via Risk-Constrained Decoding (DARC)**, a retraining-free inference-time method that frames response selection as distributionally robust, risk-sensitive decision making. Given multiple preference samples or scalable disagreement proxies, DARC reranks candidates by maximizing a *KL-robust (entropic)* satisfaction objective, and provides simple deployment controls that cap or penalize the corresponding entropic risk premium relative to the mean, enabling explicit risk budgets without retraining. We provide theoretical characterization linking this decoding rule to principled pessimism and KL-based distributionally robust optimization. Experiments on alignment benchmarks show that DARC reduces disagreement and tail risk while maintaining competitive average quality under noisy, heterogeneous feedback.

cs.LG↗

arXiv2026

Spin State versus Potential of Zero Charge as Predictors of Density-Dependent Oxygen Reduction in M-N-C Electrocatalysts

Metal-site density strongly influences oxygen reduction activity and selectivity in M-N-C electrocatalysts, but the descriptors that predict these trends remain under debate. Here, we compare spin state and the potential of zero charge as predictors of density-dependent oxygen reduction behavior in Fe-N-C and Co-N-C catalysts. Using constrained-magnetization calculations combined with Landau analysis, we find that the ground-state magnetic moments vary only weakly across a broad range of metal-site densities, suggesting that magnetic descriptors alone cannot account for the pronounced performance changes. In contrast, explicit-solvent simulations reveal systematic density-dependent shifts in PZC, which alter the interfacial electric field and thereby modulate field-sensitive adsorption energetics of ORR intermediates. Incorporating these PZC shifts into a pH-field-coupled microkinetic model captures the density-dependent activity trends and reproduces the experimentally observed increase in two-electron selectivity at lower site densities under acidic conditions. Experimental PZC measurements further support the predicted trend. Together, these results show that PZC is a more effective predictor than spin state for density-dependent oxygen reduction activity and selectivity in M-N-C electrocatalysts.

cond-mat.mtrl-sci↗

arXiv2026

Guideline Forest: Retrieval-Augmented Reasoning with Branching Experience-Induced Guidelines

Retrieval-augmented generation (RAG) has been widely adopted to ground large language models (LLMs) in external knowledge, yet it remains largely underexplored for improving reasoning. Existing methods either rely on online exploration during inference or heuristic supervision over reasoning trajectories, but they fail to effectively accumulate and reuse past reasoning experience. We propose Guideline Forest, a retrieval-augmented reasoning framework that explicitly leverages experience to guide multi-step reasoning. The framework stores high-quality, label-consistent reasoning traces as reusable memory, retrieves relevant experiences for new problems, and induces them into structured guidelines that steer reasoning and enable controlled branching and aggregation. Experiments on mathematical (GSM8K, MATH-500) and programming (MBPP, HumanEval) benchmarks demonstrate consistent improvements over strong reasoning baselines, including CoT, ReAct, ToT, FoT, and AFlow. Further analyses show that experience retrieval, guideline-induced diversity, and stepwise aggregation are key to the framework's effectiveness. Beyond single-model reasoning, Guideline Forest generalizes to enhance diverse reasoning paradigms and supports multi-model collaboration, highlighting its flexibility and scalability.

cs.AI↗

arXiv2026

FinEvo: From Isolated Backtests to Ecological Market Games for Multi-Agent Financial Strategy Evolution

Conventional financial strategy evaluation relies on isolated backtests in static environments. Such evaluations assess each policy independently, overlook correlations and interactions, and fail to explain why strategies ultimately persist or vanish in evolving markets. We shift to an ecological perspective, where trading strategies are modeled as adaptive agents that interact and learn within a shared market. Instead of proposing a new strategy, we present FinEvo, an ecological game formalism for studying the evolutionary dynamics of multi-agent financial strategies. At the individual level, heterogeneous ML-based traders-rule-based, deep learning, reinforcement learning, and large language model (LLM) agents-adapt using signals such as historical prices and external news. At the population level, strategy distributions evolve through three designed mechanisms-selection, innovation, and environmental perturbation-capturing the dynamic forces of real markets. Together, these two layers of adaptation link evolutionary game theory with modern learning dynamics, providing a principled environment for studying strategic behavior. Experiments with external shocks and real-world news streams show that FinEvo is both stable for reproducibility and expressive in revealing context-dependent outcomes. Strategies may dominate, collapse, or form coalitions depending on their competitors-patterns invisible to static backtests. By reframing strategy evaluation as an ecological game formalism, FinEvo provides a unified, mechanism-level protocol for analyzing robustness, adaptation, and emergent dynamics in multi-agent financial markets, and may offer a means to explore the potential impact of macroeconomic policies and financial regulations on price evolution and equilibrium.

physics.soc-ph↗

arXiv2025

Phantom Menace: Exploring and Enhancing the Robustness of VLA Models Against Physical Sensor Attacks

Vision-Language-Action (VLA) models revolutionize robotic systems by enabling end-to-end perception-to-action pipelines that integrate multiple sensory modalities, such as visual signals processed by cameras and auditory signals captured by microphones. This multi-modality integration allows VLA models to interpret complex, real-world environments using diverse sensor data streams. Given the fact that VLA-based systems heavily rely on the sensory input, the security of VLA models against physical-world sensor attacks remains critically underexplored. To address this gap, we present the first systematic study of physical sensor attacks against VLAs, quantifying the influence of sensor attacks and investigating the defenses for VLA models. We introduce a novel "Real-Sim-Real" framework that automatically simulates physics-based sensor attack vectors, including six attacks targeting cameras and two targeting microphones, and validates them on real robotic systems. Through large-scale evaluations across various VLA architectures and tasks under varying attack parameters, we demonstrate significant vulnerabilities, with susceptibility patterns that reveal critical dependencies on task types and model designs. We further develop an adversarial-training-based defense that enhances VLA robustness against out-of-distribution physical perturbations caused by sensor attacks while preserving model performance. Our findings expose an urgent need for standardized robustness benchmarks and mitigation strategies to secure VLA deployments in safety-critical environments.

cs.RO↗

arXiv2025

FinHEAR: Human Expertise and Adaptive Risk-Aware Temporal Reasoning for Financial Decision-Making

Financial decision-making presents unique challenges for language models, demanding temporal reasoning, adaptive risk assessment, and responsiveness to dynamic events. While large language models (LLMs) show strong general reasoning capabilities, they often fail to capture behavioral patterns central to human financial decisions-such as expert reliance under information asymmetry, loss-averse sensitivity, and feedback-driven temporal adjustment. We propose FinHEAR, a multi-agent framework for Human Expertise and Adaptive Risk-aware reasoning. FinHEAR orchestrates specialized LLM-based agents to analyze historical trends, interpret current events, and retrieve expert-informed precedents within an event-centric pipeline. Grounded in behavioral economics, it incorporates expert-guided retrieval, confidence-adjusted position sizing, and outcome-based refinement to enhance interpretability and robustness. Empirical results on curated financial datasets show that FinHEAR consistently outperforms strong baselines across trend prediction and trading tasks, achieving higher accuracy and better risk-adjusted returns.

cs.LG↗

arXiv2025

From Implicit Exploration to Structured Reasoning: Leveraging Guideline and Refinement for LLMs

Large language models (LLMs) have advanced general-purpose reasoning, showing strong performance across diverse tasks. However, existing methods often rely on implicit exploration, where the model follows stochastic and unguided reasoning paths-like walking without a map. This leads to unstable reasoning paths, lack of error correction, and limited learning from past experience. To address these issues, we propose a framework that shifts from implicit exploration to structured reasoning through guideline and refinement. First, we extract structured reasoning patterns from successful trajectories and reflective signals from failures. During inference, the model follows these guidelines step-by-step, with refinement applied after each step to correct errors and stabilize the reasoning process. Experiments on BBH and four additional benchmarks (GSM8K, MATH-500, MBPP, HumanEval) show that our method consistently outperforms strong baselines across diverse reasoning tasks. Structured reasoning with stepwise execution and refinement improves stability and generalization, while guidelines transfer well across domains and flexibly support cross-model collaboration, matching or surpassing supervised fine-tuning in effectiveness and scalability.

cs.AI↗

arXiv2025

The study of 4H-SiC LGAD after proton radiation

Silicon carbide (SiC) is a promising material for radiation monitoring in harsh environments, due to its low dark current, high breakdown voltage, high thermal conductivity, and radiation hardness.~This work investigates a SiC-based Low-Gain Avalanche Detector (LGAD), named SICAR, with a gain factor of~2 to 3, under 80 MeV proton irradiation up to $1\times 10^{14}$~$n_{eq}/cm^{2}$. Electrical characterization via I-V, C-V, and $α$ particle injection reveals an increase in threshold voltage and a 2 to 4 order of magnitude reduction in leakage current, while charge collection efficiency decreases by about 50\%. X-ray diffraction (XRD) and capacitance deep-level transient spectroscopy (C-DLTS) were employed to characterize the lattice structure and deep-level defects before and after irradiation. Deep-level defect characteristics were integrated into TCAD simulations to develop an electrical degradation model for SiC LGADs. A linear defect-flux relationship is established in the model, showing agreement with experimental results.

physics.ins-det↗

arXiv2025

SlimRAG: Retrieval without Graphs via Entity-Aware Context Selection

Retrieval-Augmented Generation (RAG) enhances language models by incorporating external knowledge at inference time. However, graph-based RAG systems often suffer from structural overhead and imprecise retrieval: they require costly pipelines for entity linking and relation extraction, yet frequently return subgraphs filled with loosely related or tangential content. This stems from a fundamental flaw -- semantic similarity does not imply semantic relevance. We introduce SlimRAG, a lightweight framework for retrieval without graphs. SlimRAG replaces structure-heavy components with a simple yet effective entity-aware mechanism. At indexing time, it constructs a compact entity-to-chunk table based on semantic embeddings. At query time, it identifies salient entities, retrieves and scores associated chunks, and assembles a concise, contextually relevant input -- without graph traversal or edge construction. To quantify retrieval efficiency, we propose Relative Index Token Utilization (RITU), a metric measuring the compactness of retrieved content. Experiments across multiple QA benchmarks show that SlimRAG outperforms strong flat and graph-based baselines in accuracy while reducing index size and RITU (e.g., 16.31 vs. 56+), highlighting the value of structure-free, entity-centric context selection. The code will be released soon. https://github.com/continue-ai-company/SlimRAG

cs.IR↗

arXiv2025

AI2Agent: An End-to-End Framework for Deploying AI Projects as Autonomous Agents

As AI technology advances, it is driving innovation across industries, increasing the demand for scalable AI project deployment. However, deployment remains a critical challenge due to complex environment configurations, dependency conflicts, cross-platform adaptation, and debugging difficulties, which hinder automation and adoption. This paper introduces AI2Agent, an end-to-end framework that automates AI project deployment through guideline-driven execution, self-adaptive debugging, and case \& solution accumulation. AI2Agent dynamically analyzes deployment challenges, learns from past cases, and iteratively refines its approach, significantly reducing human intervention. To evaluate its effectiveness, we conducted experiments on 30 AI deployment cases, covering TTS, text-to-image generation, image editing, and other AI applications. Results show that AI2Agent significantly reduces deployment time and improves success rates. The code and demo video are now publicly accessible.

cs.AI↗

arXiv2025

Why Do Weak-Binding M-N-C Single-Atom Catalysts Possess Anomalously High Oxygen Reduction Activity?

Single-atom catalysts (SACs) with metal-nitrogen-carbon (M-N-C) structures are widely recognized as promising candidates in oxygen reduction reactions (ORR). According to the classical Sabatier principle, optimal 3d metal catalysts, such as Fe/Co-N-C, achieve superior catalytic performance due to the moderate binding strength. However, the substantial ORR activity demonstrated by weakly binding M-N-C catalysts such as NiCu-N-C challenges current understandings, emphasizing the need to explore new underlying mechanisms. In this work, we integrated a pH-field coupled microkinetic model with detailed experimental electron state analyses to verify a novel key step in the ORR reaction pathway of weak-binding SACs-the oxygen adsorption at the metal-N bridge site. This step significantly altered the adsorption scaling relations, electric field responses, and solvation effects, further impacting the key kinetic reaction barrier from HOO* to O* and pH-dependent performance. Synchrotron spectra analysis further provides evidence for the new weak-binding M-N-C model, showing an increase in electron density on the anti-bonding pi orbitals of N atoms in weak-binding M-N-C catalysts and confirming the presence of N-O bonds. These findings redefine the understanding of weak-binding M-N-C catalyst behavior, opening up new perspectives for their application in clean energy.

physics.chem-ph↗

arXiv2024

Can we only use guideline instead of shot in prompt?

Currently, prompting techniques can be mainly divided into two categories:1)shot method implicitly inspires the model to answer the question by mimicing the steps in the given example, e.g., the few-shot CoT. 2) Guideline method explicitly instructs the model to reason by following guidelines, which contains succinct and concise task-specific knowledge. Shot method is prone to difficulties in terms of selection of shots type, the number of shots, and the design of the reasoning steps, so a question arises: can we only use guideline instead of shot in the prompt? To this end, we propose the FGT framework to automatically learn task-specific guidelines from dataset consisting of Feedback, Guideline, and Tree-gather agents. First, the feedback agent is designed to evaluate the outcomes, both right and wrong, of each Q&A to gather insights guiding more effective optimization strategies. Next, the guideline agent is tasked with deriving guidelines from each piece of feedback and storing them in local memory. Lastly, the tree-gather agent aggregates all guidelines hierarchically through a tree structure, ultimately obtaining all unduplicated guidelines from a global perspective. In addition, we induce the model to generate intermediate processes to ensure the reasoning consistent with the guidelines. Experimental results demonstrate that our approach achieves superior performance across multiple tasks, thereby highlighting the effectiveness of using the guidelines in prompt.

cs.HC↗

arXiv2024

An Effective Dynamic Gradient Calibration Method for Continual Learning

Continual learning (CL) is a fundamental topic in machine learning, where the goal is to train a model with continuously incoming data and tasks. Due to the memory limit, we cannot store all the historical data, and therefore confront the ``catastrophic forgetting'' problem, i.e., the performance on the previous tasks can substantially decrease because of the missing information in the latter period. Though a number of elegant methods have been proposed, the catastrophic forgetting phenomenon still cannot be well avoided in practice. In this paper, we study the problem from the gradient perspective, where our aim is to develop an effective algorithm to calibrate the gradient in each updating step of the model; namely, our goal is to guide the model to be updated in the right direction under the situation that a large amount of historical data are unavailable. Our idea is partly inspired by the seminal stochastic variance reduction methods (e.g., SVRG and SAGA) for reducing the variance of gradient estimation in stochastic gradient descent algorithms. Another benefit is that our approach can be used as a general tool, which is able to be incorporated with several existing popular CL methods to achieve better performance. We also conduct a set of experiments on several benchmark datasets to evaluate the performance in practice.

cs.LG↗

arXiv2024

AI2Apps: A Visual IDE for Building LLM-based AI Agent Applications

We introduce AI2Apps, a Visual Integrated Development Environment (Visual IDE) with full-cycle capabilities that accelerates developers to build deployable LLM-based AI agent Applications. This Visual IDE prioritizes both the Integrity of its development tools and the Visuality of its components, ensuring a smooth and efficient building experience.On one hand, AI2Apps integrates a comprehensive development toolkit ranging from a prototyping canvas and AI-assisted code editor to agent debugger, management system, and deployment tools all within a web-based graphical user interface. On the other hand, AI2Apps visualizes reusable front-end and back-end code as intuitive drag-and-drop components. Furthermore, a plugin system named AI2Apps Extension (AAE) is designed for Extensibility, showcasing how a new plugin with 20 components enables web agent to mimic human-like browsing behavior. Our case study demonstrates substantial efficiency improvements, with AI2Apps reducing token consumption and API calls when debugging a specific sophisticated multimodal agent by approximately 90% and 80%, respectively. The AI2Apps, including an online demo, open-source code, and a screencast video, is now publicly accessible.

cs.AI↗

arXiv2022

Coresets for Relational Data and The Applications

A coreset is a small set that can approximately preserve the structure of the original input data set. Therefore we can run our algorithm on a coreset so as to reduce the total computational complexity. Conventional coreset techniques assume that the input data set is available to process explicitly. However, this assumption may not hold in real-world scenarios. In this paper, we consider the problem of coresets construction over relational data. Namely, the data is decoupled into several relational tables, and it could be very expensive to directly materialize the data matrix by joining the tables. We propose a novel approach called ``aggregation tree with pseudo-cube'' that can build a coreset from bottom to up. Moreover, our approach can neatly circumvent several troublesome issues of relational learning problems [Khamis et al., PODS 2019]. Under some mild assumptions, we show that our coreset approach can be applied for the machine learning tasks, such as clustering, logistic regression and SVM.

cs.LG↗

arXiv2021

Spectral caustics of high-order harmonics in one-dimensional periodic crystals

We theoretically investigate the spectral caustics of high-order harmonics in solids. We analyze the 1-dimension model of solids HHG and find that, apart from the caustics originated from the van Hove singularities in the energy-band structure, another kind of catastrophe singularities also emerge when the different branches of electron-hole trajectories generating high-order harmonics coalesce into a single branch. We solve time-dependent Schrödinger equation in periodic potential and demonstrate the control of this kind of singularities in HHG with the aids of two-color laser fields. The diffraction patterns of the harmonic spectrum near the caustics agree well with the inter-band electron-hole recombination trajectories predicted by the semiconductor semi-classical equation. This work is expected to help to understand the HHG dynamics in solids and manipulate the harmonic spectrum by adjusting driving field parameters.

physics.optics↗