arXiv subjects

Xianliang Yang

Publications and source records attributed to Xianliang Yang.

6 recordsLinked to original sources

arXiv2026

The Quality-Utility Paradox: Why High-Reward Data Impairs Small Model Mathematical Reasoning

Knowledge distillation from powerful reasoning models is widely used to improve Small Language Models (SLMs) on mathematical reasoning, often assuming that traces with higher reward model scores provide more useful supervision. We identify a counterintuitive \textbf{Quality-Utility Paradox} in mathematical reasoning distillation. Data refined or synthesized by a stronger Oracle obtains higher perceived quality according to reward models, yet consistently underperforms traces generated by the SLM itself and selected through rejection sampling across Qwen2.5, LLaMA-3, and DeepSeek families. Our analysis shows that Oracle refinement couples logical repair with distributional drift away from the SLM's native reasoning distribution. This drift increases the learner's adaptation cost and can outweigh the benefit of improved reasoning logic. To test this mechanism, we introduce \textbf{Style-Aligned Refinement}, which preserves the native trajectory of the SLM while retaining logical repair from the Oracle. This intervention lowers adaptation cost and restores downstream utility. These findings suggest that effective mathematical reasoning distillation should jointly optimize perceived solution quality and learner-data compatibility, rather than relying solely on reward-model scores. The datasets and code are available at https://github.com/Dracoqhl/Quality-Utility-Paradox.

cs.AI↗

arXiv2026

Holdout-Loss-Based Data Selection for LLM Finetuning via In-Context Learning

Fine-tuning large pretrained language models is a common approach for aligning them with human preferences, but noisy or off-target examples can dilute supervision. While small, well-chosen datasets often match the performance of much larger ones, systematic and efficient ways to identify high-value training data remain underexplored. Many current methods rely on heuristics or expensive retraining. We present a principled, resource-efficient framework for data selection and reweighting. At its core is an In-Context Approximation (ICA) that estimates the holdout loss a model would incur after training on a candidate example by conditioning on a small, curated holdout set in context. ICA requires no reference model and no additional finetuning. We define the resulting estimate as the ICA score, and derive per-example weights that dynamically reweight gradient updates as model parameters evolve. Across SFT, DPO, and SimPO, and over diverse backbones and datasets, ICA-based reweighting consistently improves model alignment with minimal overhead. We analyze sensitivity to score update frequency and the number of in-context holdout examples. We also discuss limitations in rapidly drifting on-policy settings, highlighting directions for future work. Code and prompts will be released.

cs.LG↗

arXiv2025

HeurAgenix: Leveraging LLMs for Solving Complex Combinatorial Optimization Challenges

Heuristic algorithms play a vital role in solving combinatorial optimization (CO) problems, yet traditional designs depend heavily on manual expertise and struggle to generalize across diverse instances. We introduce \textbf{HeurAgenix}, a two-stage hyper-heuristic framework powered by large language models (LLMs) that first evolves heuristics and then selects among them automatically. In the heuristic evolution phase, HeurAgenix leverages an LLM to compare seed heuristic solutions with higher-quality solutions and extract reusable evolution strategies. During problem solving, it dynamically picks the most promising heuristic for each problem state, guided by the LLM's perception ability. For flexibility, this selector can be either a state-of-the-art LLM or a fine-tuned lightweight model with lower inference cost. To mitigate the scarcity of reliable supervision caused by CO complexity, we fine-tune the lightweight heuristic selector with a dual-reward mechanism that jointly exploits singals from selection preferences and state perception, enabling robust selection under noisy annotations. Extensive experiments on canonical benchmarks show that HeurAgenix not only outperforms existing LLM-based hyper-heuristics but also matches or exceeds specialized solvers. Code is available at https://github.com/microsoft/HeurAgenix.

cs.AI↗

arXiv2024

Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems

Recent advancements in solving large-scale traveling salesman problems (TSP) utilize the heatmap-guided Monte Carlo tree search (MCTS) paradigm, where machine learning (ML) models generate heatmaps, indicating the probability distribution of each edge being part of the optimal solution, to guide MCTS in solution finding. However, our theoretical and experimental analysis raises doubts about the effectiveness of ML-based heatmap generation. In support of this, we demonstrate that a simple baseline method can outperform complex ML approaches in heatmap generation. Furthermore, we question the practical value of the heatmap-guided MCTS paradigm. To substantiate this, our findings show its inferiority to the LKH-3 heuristic despite the paradigm's reliance on problem-specific, hand-crafted strategies. For the future, we suggest research directions focused on developing more theoretically sound heatmap generation methods and exploring autonomous, generalizable ML approaches for combinatorial problems. The code is available for review: https://github.com/xyfffff/rethink_mcts_for_tsp.

cs.AI↗

arXiv2024

Knowing What Not to Do: Leverage Language Model Insights for Action Space Pruning in Multi-agent Reinforcement Learning

Multi-agent reinforcement learning (MARL) is employed to develop autonomous agents that can learn to adopt cooperative or competitive strategies within complex environments. However, the linear increase in the number of agents leads to a combinatorial explosion of the action space, which may result in algorithmic instability, difficulty in convergence, or entrapment in local optima. While researchers have designed a variety of effective algorithms to compress the action space, these methods also introduce new challenges, such as the need for manually designed prior knowledge or reliance on the structure of the problem, which diminishes the applicability of these techniques. In this paper, we introduce Evolutionary action SPAce Reduction with Knowledge (eSpark), an exploration function generation framework driven by large language models (LLMs) to boost exploration and prune unnecessary actions in MARL. Using just a basic prompt that outlines the overall task and setting, eSpark is capable of generating exploration functions in a zero-shot manner, identifying and pruning redundant or irrelevant state-action pairs, and then achieving autonomous improvement from policy feedback. In reinforcement learning tasks involving inventory management and traffic light control encompassing a total of 15 scenarios, eSpark consistently outperforms the combined MARL algorithm in all scenarios, achieving an average performance gain of 34.4% and 9.9% in the two types of tasks respectively. Additionally, eSpark has proven to be capable of managing situations with a large number of agents, securing a 29.7% improvement in scalability challenges that featured over 500 agents. The code can be found in https://github.com/LiuZhihao2022/eSpark.git.

cs.MA↗

arXiv2023

A Versatile Multi-Agent Reinforcement Learning Benchmark for Inventory Management

Multi-agent reinforcement learning (MARL) models multiple agents that interact and learn within a shared environment. This paradigm is applicable to various industrial scenarios such as autonomous driving, quantitative trading, and inventory management. However, applying MARL to these real-world scenarios is impeded by many challenges such as scaling up, complex agent interactions, and non-stationary dynamics. To incentivize the research of MARL on these challenges, we develop MABIM (Multi-Agent Benchmark for Inventory Management) which is a multi-echelon, multi-commodity inventory management simulator that can generate versatile tasks with these different challenging properties. Based on MABIM, we evaluate the performance of classic operations research (OR) methods and popular MARL algorithms on these challenging tasks to highlight their weaknesses and potential.

cs.AI↗