Author name cluster

Xiaofei Ma

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

NeurIPS Conference 2025 Conference Paper

Approximately Aligned Decoding

Daniel Melcer
Sujan Kumar Gonugondla
Pramuditha Perera
Haifeng Qian
Wen-Hao Chiang
Yanjun Wang
Nihal Jain
Pranav Garg

It is common to reject undesired outputs of Large Language Models (LLMs); however, current methods to do so require an excessive amount of computation to re-sample after a rejection, or distort the distribution of outputs by constraining the output to highly improbable tokens. We present a method, Approximately Aligned Decoding (AprAD), to balance the distortion of the output distribution with computational efficiency, inspired by algorithms from the speculative decoding literature. AprAD allows for the generation of long sequences of text with difficult-to-satisfy constraints, while amplifying low probability outputs much less compared to existing methods. We show through a series of experiments that the task-specific performance of AprAD is comparable to methods that do not distort the output distribution, while being much more computationally efficient.

PDF Details

NeurIPS Conference 2025 Conference Paper

Automated Composition of Agents: A Knapsack Approach for Agentic Component Selection

Michelle Yuan
Khushbu Pahwa
Shuaichen Chang
Mustafa Kaba
Jiarong Jiang
Xiaofei Ma
Yi Zhang
MONICA SUNKARA

Designing effective agentic systems requires the seamless composition and integration of agents, tools, and models within dynamic and uncertain environments. Most existing methods rely on static, semantic retrieval approaches for tool or agent discovery. However, effective reuse and composition of existing components remain challenging due to incomplete capability descriptions and the limitations of retrieval methods. Component selection suffers because the decisions are not based on capability, cost, and real-time utility. To address these challenges, we introduce a structured, automated framework for agentic system composition that is inspired by the knapsack problem. Our framework enables a composer agent to systematically identify, select, and assemble an optimal set of agentic components by jointly considering performance, budget constraints, and compatibility. By dynamically testing candidate components and modeling their utility in real-time, our approach streamlines the assembly of agentic systems and facilitates scalable reuse of resources. Empirical evaluation with Claude 3. 5 Sonnet across five benchmarking datasets shows that our online-knapsack-based composer consistently lies on the Pareto frontier, achieving higher success rates at significantly lower component costs compared to our baselines. In the single-agent setup, the online knapsack composer shows a success rate improvement of up to 31. 6\% in comparison to the retrieval baselines. In multi-agent systems, the online knapsack composer increases success rate from 37\% to 87\% when agents are selected from an agent inventory of 100+ agents. The substantial performance gap confirms the robust adaptability of our method across diverse domains and budget constraints.

PDF Details

NeurIPS Conference 2024 Conference Paper

LeDex: Training LLMs to Better Self-Debug and Explain Code

Nan Jiang
Xiaopeng Li
Shiqi Wang
Qiang Zhou
Soneya B. Hossain
Baishakhi Ray
Varun Kumar
Xiaofei Ma

In the domain of code generation, self-debugging is crucial. It allows LLMs to refine their generated code based on execution feedback. This is particularly important because generating correct solutions in one attempt proves challenging for complex tasks. Prior works on self-debugging mostly focus on prompting methods by providing LLMs with few-shot examples, which work poorly on small open-sourced LLMs. In this work, we propose LeDex, a training framework that significantly improves the self-debugging capability of LLMs. Intuitively, we observe that a chain of explanations on the wrong code followed by code refinement helps LLMs better analyze the wrong code and do refinement. We thus propose an automated pipeline to collect a high-quality dataset for code explanation and refinement by generating a number of explanations and refinement trajectories from the LLM itself or a larger teacher model and filtering via execution verification. We perform supervised fine-tuning (SFT) and further reinforcement learning (RL) on both success and failure trajectories with a novel reward design considering code explanation and refinement quality. SFT improves the pass@1 by up to 15. 92\% and pass@10 by 9. 30\% over four benchmarks. RL training brings additional up to 3. 54\% improvement on pass@1 and 2. 55\% improvement on pass@10. The trained LLMs show iterative refinement ability and can keep refining code continuously. Lastly, our human evaluation shows that the LLMs trained with our framework generate more useful code explanations and help developers better understand bugs in source code.

PDF Details DOI

TMLR Journal 2022 Journal Article

Uncertainty-Based Active Learning for Reading Comprehension

Jing Wang
Jie Shen
Xiaofei Ma
Andrew Arnold

Recent years have witnessed a surge of successful applications of machine reading comprehension. Of central importance to these tasks is the availability of massive amount of labeled data, which facilitates training of large-scale neural networks. However, in many real-world problems, annotated data are expensive to gather not only because of time cost and budget, but also of certain domain-specific restrictions such as privacy for healthcare data. In this regard, we propose an uncertainty-based active learning algorithm for reading comprehension, which interleaves data annotation and model updating to mitigate the demand of labeling. Our key techniques are two-fold: 1) an unsupervised uncertainty-based sampling scheme that queries the labels of the most informative instances with respect to the currently learned model; and 2) an adaptive loss minimization paradigm that simultaneously fits the data and controls the degree of model updating. We demonstrate on benchmark datasets that 25% less labeled samples suffice to guarantee similar, or even improved performance. Our results show strong evidence that for label-demanding scenarios, the proposed approach offers a practical guide on data collection and model training.

PDF Details