arXiv subjects

Yangyang Feng

Publications and source records attributed to Yangyang Feng.

8 recordsLinked to original sources

arXiv2026

CompEvo: Competition-Induced Evolution for Multi-Agent in News-Driven Time Series Forecasting

News-driven time series forecasting uses evolving textual events together with historical observations to predict future values, supporting applications such as market risk monitoring and resource scheduling. In multi-agent settings, two challenges still remain. The first is degeneration of thought, where agents converge to similar evidence-seeking behaviors. The second is insufficient theoretical grounding, where strategy updates are often heuristic and lack a principled formulation. To address the above challenges, we propose CompEvo, a competition-induced evolution framework for multi-agent news-driven time series forecasting. For theoretical grounding, we introduce an evolutionary game formulation to guarantee equilibrium existence and optimization convergence. Building on this formulation, we construct a trainable multi-agent evolution framework that integrates strategy execution, fitness-based differentiable selection, and competition-induced strategy evolution. CompEvo enables heterogeneous agents to explore diverse news evidence, converts forecasting feedback into differentiable influence weights, and evolves agent strategies under competitive pressure to preserve effective logic while maintaining diversity. Experiments on four real-world datasets show that CompEvo reduces RMSE by 27.3% and MAPE by 26.2% on average over strong baselines. Further analysis indicates that CompEvo successfully maintains diverse and specialized agent behaviors.

cs.NE↗

arXiv2026

PAST: Privileged Adaptation from Complete Student Trajectories for On-Policy Self-Distillation

On-policy self-distillation (OPSD) uses a privileged teacher to supervise a reasoning model on prefixes sampled from its own rollouts. Yet each rollout also reveals how the student's response unfolds and whether it succeeds, student-specific hindsight that standard OPSD does not use to form the teacher. We introduce Privileged Adaptation from Student Trajectories (PAST), which treats each completed student trajectory as additional privileged information for the OPSD teacher while leaving the student's distillation prefixes unchanged. PAST preserves the student's next-token distribution on correct trajectories and uses failed trajectories to adapt the teacher toward verified success under student-proximity regularization. We characterize what such a trajectory-conditioned teacher can transfer to a prefix-only student. Forward-KL distillation projects the teacher distributions to their conditional arithmetic mean given the prefix. This projection separates trajectory-specific variation that remains privileged from the mean policy shift available to the student. For correct trajectories, the unclipped population objective also has the frozen student as an ideal distributional fixed point. Across three mathematical reasoning benchmarks, PAST improves the Avg@12 macro average over Vanilla OPSD by 5.6 percentage points. A $2\times2$ factorial study shows gains from both complete-trajectory access and teacher adaptation, while trajectory removal and shuffling confirm that the adapted teacher uses the matching hindsight context.

cs.LG↗

arXiv2025

Two-way Evidence self-Alignment based Dual-Gated Reasoning Enhancement

Large language models (LLMs) encounter difficulties in knowledge-intensive multi-step reasoning (KIMSR) tasks. One challenge is how to effectively extract and represent rationale evidence. The current methods often extract semantically relevant but logically irrelevant evidence, resulting in flawed reasoning and inaccurate responses. We propose a two-way evidence self-alignment (TW-ESA) module, which utilizes the mutual alignment between strict reasoning and LLM reasoning to enhance its understanding of the causal logic of evidence, thereby addressing the first challenge. Another challenge is how to utilize the rationale evidence and LLM's intrinsic knowledge for accurate reasoning when the evidence contains uncertainty. We propose a dual-gated reasoning enhancement (DGR) module to gradually fuse useful knowledge of LLM within strict reasoning, which can enable the model to perform accurate reasoning by focusing on causal elements in the evidence and exhibit greater robustness. The two modules are collaboratively trained in a unified framework ESA-DGR. Extensive experiments on three diverse and challenging KIMSR datasets reveal that ESA-DGR significantly surpasses state-of-the-art LLM-based fine-tuning methods, with remarkable average improvements of 4% in exact match (EM) and 5% in F1 score. The implementation code is available at https://anonymous.4open.science/r/ESA-DGR-2BF8.

cs.CL↗

arXiv2025

Can Competition Enhance the Proficiency of Agents Powered by Large Language Models in the Realm of News-driven Time Series Forecasting?

Multi-agents-based news-driven time series forecasting is considered as a potential paradigm shift in the era of large language models (LLMs). The challenge of this task lies in measuring the influences of different news events towards the fluctuations of time series. This requires agents to possess stronger abilities of innovative thinking and the identifying misleading logic. However, the existing multi-agent discussion framework has limited enhancement on time series prediction in terms of optimizing these two capabilities. Inspired by the role of competition in fostering innovation, this study embeds a competition mechanism within the multi-agent discussion to enhance agents' capability of generating innovative thoughts. Furthermore, to bolster the model's proficiency in identifying misleading information, we incorporate a fine-tuned small-scale LLM model within the reflective stage, offering auxiliary decision-making support. Experimental results confirm that the competition can boost agents' capacity for innovative thinking, which can significantly improve the performances of time series prediction. Similar to the findings of social science, the intensity of competition within this framework can influence the performances of agents, providing a new perspective for studying LLMs-based multi-agent systems.

cs.AI↗

arXiv2025

Light-Induced Spin Slanting in 2D Multiferroic Magnet

Controlling spin orientation of two-dimensional (2D) materials has emerged as a frontier of condensed-matter physics, resulting in the discovery of various phases of matter. However, in most cases, spin orientation can be stablished only at specific directions of out-of-plane and in-plane, which is a drawback compared with three-dimensional systems, limiting exploration of novel physics. Here, we introduce a methodology for manipulating spin slanting in 2D multiferroic materials through ultrafast pulses of light. Based on model analysis, we find that simultaneous triggering spin-orbit coupling induced interactions from in-plane and out-of-plane orbitals can generate spin slanting. By choosing 2D multiferroic materials with specific low-energy composition endowed by symmetry, such triggering can be readily achieved through ultrafast light illumination, leading to light-induced spin slanting. Using real-time time-dependent density-functional theory, we demonstrate this approach in multiferroic single-layer CuCr2Se4. This study provides an efficient way to manipulate spin orientation in 2D materials and establishes a general platform to explore physics and applications associated with spin slanting.

cond-mat.mes-hall↗

arXiv2025

Structuring Scientific Innovation: A Framework for Modeling and Discovering Impactful Knowledge Combinations

The emergence of large language models offers new possibilities for structured exploration of scientific knowledge. Rather than viewing scientific discovery as isolated ideas or content, we propose a structured approach that emphasizes the role of method combinations in shaping disruptive insights. Specifically, we investigate how knowledge unit--especially those tied to methodological design--can be modeled and recombined to yield research breakthroughs. Our proposed framework addresses two key challenges. First, we introduce a contrastive learning-based mechanism to identify distinguishing features of historically disruptive method combinations within problem-driven contexts. Second, we propose a reasoning-guided Monte Carlo search algorithm that leverages the chain-of-thought capability of LLMs to identify promising knowledge recombinations for new problem statements.Empirical studies across multiple domains show that the framework is capable of modeling the structural dynamics of innovation and successfully highlights combinations with high disruptive potential. This research provides a new path for computationally guided scientific ideation grounded in structured reasoning and historical data modeling.

cs.AI↗

arXiv2024

Ferro-Valleytricity with In-Plane Magnetization

Ferro-valleytricity, a fundamental phenomenon that manifests spontaneous valley polarization, is generally considered to occur in two-dimensional (2D) materials with out-of-plane magnetization. Here, we propose a mechanism to realize ferro-valleytricity in 2D materials with in-plane magnetization, wherein the physics correlates to non-collinear magnetism in triangular lattice. Our model analysis provides comprehensive ingredients that allows for in-plane ferro-valleytricity, revealing that mirror symmetry is required for remarkable valley polarization and time-reversal-mirror joint-symmetry should be excluded. Through modulating in-plane magnetization offset, the valley polarization could be reversed. Followed by first-principles, such mechanism is demonstrated in a multiferroic triangular lattice of single-layer W3Cl8. We further show that the reversal of valley polarization could also be driven by applying electric field that modulates ferroelectricity. Our findings greatly enrich the valley physics research and significantly extend the scope for material classes of ferro-valleytricity.

cond-mat.mtrl-sci↗

arXiv2024

Ferroelectrovalley in Two-Dimensional Multiferroic Lattices

Engineering valley index is essential and highly sought for valley physics, but currently it is exclusively based on the paradigm of the challenging ferrovalley with spin-orientation reversal under magnetic field. Here, an alternative strategy, i.e., the so-called ferroelectrovalley, is proposed to tackle the insurmountable spin-orientation reversal, which reveres valley index with the feasible ferroelectricity. Using symmetry arguments and tight-binding model, the C_2 rotation is unveiled to be able to take the place of time reversal for operating valley index in two-dimensional multiferroic kagome lattices, which enables the ferroelectricity-engineered valley index, thereby generating the concept of ferroelectrovalley. Based on first-principles calculations, this concept is further demonstrated in the breathing kagome lattice of single-layer Ti3Br8, wherein ferroelectricity couples the breathing process. These findings open a new direction for valleytronics and two-dimensional materials research.

cond-mat.mtrl-sci↗