arXiv subjects

Xinyuan Guo

Publications and source records attributed to Xinyuan Guo.

5 recordsLinked to original sources

arXiv2026

Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization

Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. However, RL algorithms with PPO-Clip are inherently limited by exploration collapse. Subsequent works remain primarily heuristic and fail to identify the essential cause of PPO-Clip's failure. This work reveals the fundamental flaw of PPO-Clip: it implicitly measures policy discrepancy using Euclidean metric, which is theoretically inconsistent with the intrinsic geometry on the policy Riemannian manifold. This geometric mismatch results in overly conservative updates in low-probability regions while aggressive in high-probability regions, ultimately collapsing exploration. To correct this geometric flaw, we propose Riemannian Isometric Policy Optimization (RIPO), which guarantees isometric policy updates on the Riemannian manifold, effectively balancing exploration and exploitation. We further show that RIPO achieves a favorable bias-variance trade-off, which stabilizes optimization. Extensive experiments demonstrate that RIPO significantly surpasses existing LLM RL algorithms across seven competition-level benchmarks (up to 60% improvement over GRPO on AIME24).

cs.LG↗

arXiv2026

NCP: Neighborhood-Preserving Non-Uniform Circle Packing for Visualization

Circle packing is widely used in visualization due to its aesthetic appeal and simplicity, particularly in tasks where the spatial arrangement and relationships between data are of interest, such as understanding proximity relationships (e.g., images with categories) or analyzing quantitative data (e.g., housing prices). Many applications require preserving neighborhood relationships while encoding a quantitative attribute using radii for data analysis. To meet these two requirements simultaneously, we present a neighborhood-preserving non-uniform circle packing method, NCP. This method preserves neighborhood relationships between the data represented by non-uniform circles to comprehensively analyze similar data and an attribute of interest. We formulate neighborhood-preserving non-uniform circle packing as a planar graph embedding problem based on the circle packing theorem. This formulation leads to a non-convex optimization problem, which can be solved by the continuation method. We conduct a quantitative evaluation and present two use cases to demonstrate that our NCP method can effectively generate non-uniform circle packing results.

cs.HC↗

arXiv2025

FLEX: Continuous Agent Evolution via Forward Learning from Experience

Autonomous agents driven by Large Language Models (LLMs) have revolutionized reasoning and problem-solving but remain static after training, unable to grow with experience as intelligent beings do during deployment. We introduce Forward Learning with EXperience (FLEX), a gradient-free learning paradigm that enables LLM agents to continuously evolve through accumulated experience. Specifically, FLEX cultivates scalable and inheritable evolution by constructing a structured experience library through continual reflection on successes and failures during interaction with the environment. FLEX delivers substantial improvements on mathematical reasoning, chemical retrosynthesis, and protein fitness prediction (up to 23% on AIME25, 10% on USPTO50k, and 14% on ProteinGym). We further identify a clear scaling law of experiential growth and the phenomenon of experience inheritance across agents, marking a step toward scalable and inheritable continuous agent evolution. Project Page: https://flex-gensi-thuair.github.io.

cs.LG↗

arXiv2025

ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation

Infographic charts are a powerful medium for communicating abstract data by combining visual elements (e.g., charts, images) with textual information. However, their visual and structural richness poses challenges for large vision-language models (LVLMs), which are typically trained on plain charts. To bridge this gap, we introduce ChartGalaxy, a million-scale dataset designed to advance the understanding and generation of infographic charts. The dataset is constructed through an inductive process that identifies 75 chart types, 440 chart variations, and 68 layout templates from real infographic charts and uses them to create synthetic ones programmatically. We showcase the utility of this dataset through: 1) improving infographic chart understanding via fine-tuning, 2) benchmarking code generation for infographic charts, and 3) enabling example-based infographic chart generation. By capturing the visual and structural complexity of real design, ChartGalaxy provides a useful resource for enhancing multimodal reasoning and generation in LVLMs.

cs.CV↗

arXiv2025

RouteFlow: Trajectory-Aware Animated Transitions

Animating objects' movements is widely used to facilitate tracking changes and observing both the global trend and local hotspots where objects converge or diverge. Existing methods, however, often obscure critical local hotspots by only considering the start and end positions of objects' trajectories. To address this gap, we propose RouteFlow, a trajectory-aware animated transition method that effectively balances the global trend and local hotspots while minimizing occlusion. RouteFlow is inspired by a real-world bus route analogy: objects are regarded as passengers traveling together, with local hotspots representing bus stops where these passengers get on and off. Based on this analogy, animation paths are generated like bus routes, with the object layout generated similarly to seat allocation according to their destinations. Compared with state-of-the-art methods, RouteFlow better facilitates identifying the global trend and locating local hotspots while performing comparably in tracking objects' movements.

cs.HC↗