arXiv subjects

Qi Peng

Publications and source records attributed to Qi Peng.

11 recordsLinked to original sources

arXiv2026

Evidence, Logic, and Compliance: Multi-Agent Structured Graph Reasoning with Expert Arbitration for Medical Referral

Medical referral (directing patients to the appropriate hospital department) is a complex decision-making process requiring the synthesis of multimodal data, including patient narratives, laboratory indicators, and radiology imaging. While Large Language Models (LLMs) have advanced medical dialogue systems, they struggle with real-world referral tasks due to two primary limitations: (1) Information Overload, where models fixate on high-frequency disease terms while overlooking subtle but critical urgency indicators; and (2) Unstructured Collaboration, where existing multi-agent frameworks rely on loose dialogue that leads to semantic drift and confirmation bias. To address these challenges, we introduce MASGR (Multi-Agent Structured Graph Reasoning), a framework that treats referral not as a classification task but as a structured graph construction problem. MASGR deploys specialized agents to extract evidence from distinct modalities and coordinates them through a clinical reasoning graph. This graph forces agents to establish explicit logical connections between conflicting evidence. Furthermore, we integrate a knowledge-guided arbitration mechanism that prioritizes patient safety rules over standard diagnostic classification. Extensive experiments on real-world medical records demonstrate that MASGR significantly outperforms state-of-the-art LLMs and existing multi-agent systems, particularly in complex cases requiring the balancing of chronic disease management and emergency intervention. The AI contribution lies in the Multi-Agent Structured Graph Reasoning framework that transforms unstructured multi-agent dialogue into a verifiable logical graph construction. The engineering application is demonstrated through its deployment in a complex healthcare decision-making system to optimize the precision of complex medical referrals.

cs.MA↗

arXiv2026

Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning

Large language models (LLMs) have emerged as important tools in healthcare, showing growing potential for clinical reasoning and patient care. This survey examines recent progress in medical LLMs, focusing on reasoning applications and requirements. We present a dual-view approach that connects clinical practice with computational methods. On the clinical side, we establish a five-level competency scheme following Miller's Pyramid, progressing from knowledge recall to dynamic case management. On the computational side, we link deductive, inductive, and abductive reasoning patterns to common medical goals and tasks. We also introduce a benchmark dataset spanning five levels of medical reasoning capability and report results on 18 state-of-the-art models, revealing that medical specialist models excel in diagnosis-centric tasks while general models lead in decision support and dialogue. We conclude by discussing current progress and open challenges, including data limitations, hallucination, and grounding issues, and outline directions toward safer, more reliable, and workflow-ready systems.

cs.AI↗

arXiv2026

CDPR: Counterfactual Advantage-based Credit Assignment for Cost-Aware Sequential Medical Diagnosis

Clinical diagnosis is a step-by-step, cost-aware process: a physician orders examinations one at a time, observes the results, and updates the diagnosis before reaching a final conclusion. Most medical language models instead treat diagnosis as a one-pass classification task and ignore the trade-off between a test's value and its cost. We model diagnosis as a cost-aware sequential decision process and train the policy with reinforcement learning. The main difficulty is credit assignment: the only reliable signal comes once at the end of a long trajectory, so it scores a wasteful workup the same as an efficient one. We propose CDPR (Counterfactual Diagnostic Process Reward), which needs no expert labels and no learned critic. CDPR first finds the states where the policy hesitates, using the uncertainty of its action distribution, and then scores the chosen action by its advantage over the alternatives the policy itself would consider, estimated with short rollouts under a utility that balances correctness against test count, cost, and infeasible requests. A rollout cache reuses within-batch trajectories to keep the cost low. We integrate CDPR into GRPO and test it on one in-domain (MIMIC-IV) and two out-of-domain (ClinicalBench and a private hospital dataset) benchmarks. CDPR improves diagnostic accuracy while clearly reducing the number and cost of examinations.

cs.AI↗

arXiv2025

Tree-of-Reasoning: Towards Complex Medical Diagnosis via Multi-Agent Reasoning with Evidence Tree

Large language models (LLMs) have shown great potential in the medical domain. However, existing models still fall short when faced with complex medical diagnosis task in the real world. This is mainly because they lack sufficient reasoning depth, which leads to information loss or logical jumps when processing a large amount of specialized medical data, leading to diagnostic errors. To address these challenges, we propose Tree-of-Reasoning (ToR), a novel multi-agent framework designed to handle complex scenarios. Specifically, ToR introduces a tree structure that can clearly record the reasoning path of LLMs and the corresponding clinical evidence. At the same time, we propose a cross-validation mechanism to ensure the consistency of multi-agent decision-making, thereby improving the clinical reasoning ability of multi-agents in complex medical scenarios. Experimental results on real-world medical data show that our framework can achieve better performance than existing baseline methods.

cs.AI↗

arXiv2024

General Relativistic Approach to the Vis-viva Equation on Schwarzschild Metric

A modification to the vis-viva equation that accounts for general relativistic effects is introduced to enhance the accuracy of predictions of orbital motion and precession. The updated equation reduces to the traditional vis-viva equation under Newtonian conditions and is a more accurate tool for astrodynamics than the traditional equation. Preliminary simulation results demonstrate the application potential of the modified vis-viva equation for more complex n-body systems. Spherical symmetry is assumed in this approach; however, this limitation could be removed in future research. This study is a pivotal step toward bridging classical and relativistic mechanics and thus makes an important contribution to the field of celestial dynamics.

gr-qc↗

arXiv2023

GeoGauss: Strongly Consistent and Light-Coordinated OLTP for Geo-Replicated SQL Database

Multinational enterprises conduct global business that has a demand for geo-distributed transactional databases. Existing state-of-the-art databases adopt a sharded master-follower replication architecture. However, the single-master serving mode incurs massive cross-region writes from clients, and the sharded architecture requires multiple round-trip acknowledgments (e.g., 2PC) to ensure atomicity for cross-shard transactions. These limitations drive us to seek yet another design choice. In this paper, we propose a strongly consistent OLTP database GeoGauss with full replica multi-master architecture. To efficiently merge the updates from different master nodes, we propose a multi-master OCC that unifies data replication and concurrent transaction processing. By leveraging an epoch-based delta state merge rule and the optimistic asynchronous execution, GeoGauss ensures strong consistency with light-coordinated protocol and allows more concurrency with weak isolation, which are sufficient to meet our needs. Our geo-distributed experimental results show that GeoGauss achieves 7.06X higher throughput and 17.41X lower latency than the state-of-the-art geo-distributed database CockroachDB on the TPC-C benchmark.

cs.DB↗

arXiv2022

Dynamic Stochastic Ensemble with Adversarial Robust Lottery Ticket Subnetworks

Adversarial attacks are considered the intrinsic vulnerability of CNNs. Defense strategies designed for attacks have been stuck in the adversarial attack-defense arms race, reflecting the imbalance between attack and defense. Dynamic Defense Framework (DDF) recently changed the passive safety status quo based on the stochastic ensemble model. The diversity of subnetworks, an essential concern in the DDF, can be effectively evaluated by the adversarial transferability between different networks. Inspired by the poor adversarial transferability between subnetworks of scratch tickets with various remaining ratios, we propose a method to realize the dynamic stochastic ensemble defense strategy. We discover the adversarial transferable diversity between robust lottery ticket subnetworks drawn from different basic structures and sparsity. The experimental results suggest that our method achieves better robust and clean recognition accuracy by adversarial transferable diversity, which would decrease the reliability of attacks.

cs.CV↗

arXiv2022

An Improved Automatic Modulation Classification Scheme Based on Adaptive Fusion Network

Due to the over-fitting problem caused by imbalance samples, there is still room to improve the performance of data-driven automatic modulation classification (AMC) in noisy scenarios. By fully considering the signal characteristics, an AMC scheme based on adaptive fusion network (AFNet) is proposed in this work. The AFNet can extract and aggregate multi-scale spatial features of in-phase and quadrature (I/Q) signals intelligently, thus improving the feature representation capability. Moreover, a novel confidence weighted loss function is proposed to address the imbalance issue and it is implemented by a two-stage learning scheme.Through the two-stage learning, AFNet can focus on high-confidence samples with more valid information and extract effective representations, so as to improve the overall classification performance. In the simulations, the proposed scheme reaches an average accuracy of 62.66% on a wide range of SNRs, which outperforms other AMC models. The effects of the loss function on classification accuracy are further studied.

eess.SP↗

arXiv2021

Directed flow of charged particles within idealized viscous hydrodynamics at energies available at the BNL Relativistic Heavy Ion Collider and at the CERN Large Hadron Collider

Following the Boz$\dot{\textrm{e}}$k-Wyskiel parametrization tilted initial condition, an alternative way to construct a longitudinal tilted fireball based on the Glauber collision geometry is presented. This longitudinal tilted initial condition combined with the Ideal-CLVisc (3 + 1)D hydrodynamic model, a nonvanishing directed flow coefficient $v_{1}$ in a wide rapidity range is observed. After comparing the model's results with experimentally observed data of directed flow coefficient $v_{1}(η)$ from $\sqrt{s_{NN}}$ = 200 GeV Cu + Cu, Au + Au collisions at RHIC energy to $\sqrt{s_{NN}}$ = 2.76 TeV and $\sqrt{s_{NN}}$ = 5.02 TeV Pb + Pb collisions at the LHC energy. We find that the directed flow measurements in heavy-ion collisions can set strong constraints on the imbalance of forward and backward incoming nuclei and on the magnitude asymmetry of pressure gradients along the $x$ direction.

hep-ph↗

arXiv2021

What Have We Learned from OpenReview?

Anonymous peer review is used by the great majority of computer science conferences. OpenReview is such a platform that aims to promote openness in peer review process. The paper, (meta) reviews, rebuttals, and final decisions are all released to public. We collect 5,527 submissions and their 16,853 reviews from the OpenReview platform. We also collect these submissions' citation data from Google Scholar and their non-peer-reviewed versions from arXiv.org. By acquiring deep insights into these data, we have several interesting findings that could help understand the effectiveness of the public-accessible double-blind peer review process. Our results can potentially help writing a paper, reviewing it, and deciding on its acceptance.

cs.DL↗

arXiv2015

A density compensation-based path computing model for measuring semantic similarity

The shortest path between two concepts in a taxonomic ontology is commonly used to represent the semantic distance between concepts in the edge-based semantic similarity measures. In the past, the edge counting is considered to be the default method for the path computation, which is simple, intuitive and has low computational complexity. However, a large lexical taxonomy of such as WordNet has the irregular densities of links between concepts due to its broad domain but. The edge counting-based path computation is powerless for this non-uniformity problem. In this paper, we advocate that the path computation is able to be separated from the edge-based similarity measures and form various general computing models. Therefore, in order to solve the problem of non-uniformity of concept density in a large taxonomic ontology, we propose a new path computing model based on the compensation of local area density of concepts, which is equal to the number of direct hyponyms of the subsumers of concepts in their shortest path. This path model considers the local area density of concepts as an extension of the edge-based path and converts the local area density divided by their depth into the compensation for edge-based path with an adjustable parameter, which idea has been proven to be consistent with the information theory. This model is a general path computing model and can be applied in various edge-based similarity algorithms. The experiment results show that the proposed path model improves the average correlation between edge-based measures with human judgments on Miller and Charles benchmark from less than 0.8 to more than 0.85, and has a big advantage in efficiency than information content (IC) computation in a dynamic ontology, thereby successfully solving the non-uniformity problem of taxonomic ontology.

cs.AI↗