arXiv subjects

Derek Chen

Publications and source records attributed to Derek Chen.

16 recordsLinked to original sources

arXiv2026

SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?

AI agents are increasingly expected to complete long-horizon workflows that require sustained progress over hours, millions of tokens, and complex environments. Yet current agent benchmarks largely evaluate short-form tasks, such as single pull requests, small tickets, or 5-10 minute exercises, limiting our ability to measure agents' capabilities in planning, long-context understanding, and memory use. We introduce SWE-Marathon, a benchmark of 20 long-horizon tasks spanning software engineering and adjacent technical domains. Each task consists of a unique executable environment, a human-written reference solution, and a multi-layer verification suite. Logged agent attempts average 27.2M total tokens, making SWE-Marathon substantially longer-horizon than existing SWE and command-line agent benchmarks. Current frontier coding agents solve fewer than 30% of tasks. Failures often arise from poor self-verification, self-reported infeasibility, and premature termination. We also observe reward-hacking behavior in 13.8% of rollouts, where agents attempt to exploit the environment or verifier to bypass the intended workflow. SWE-Marathon includes adversarial review of test suites and execution environments, as well as multi-layer checks designed to prevent shortcut solutions. We release SWE-Marathon, evaluation code, and agent trajectories at https://swe-marathon.org/.

cs.SE↗

arXiv2025

Characterization and Evaluation of Screw-Based Locomotion Across Aquatic, Granular, and Transitional Media

Screw-based propulsion systems offer promising capabilities for amphibious mobility, yet face significant challenges in optimizing locomotion across water, granular materials, and transitional environments. This study presents a systematic investigation into the locomotion performance of various screw configurations in media such as dry sand, wet sand, saturated sand, and water. Through a principles-first approach to analyze screw performance, it was found that certain parameters are dominant in their impact on performance. Depending on the media, derived parameters inspired from optimizing heat sink design help categorize performance within the dominant design parameters. Our results provide specific insights into screw shell design and adaptive locomotion strategies to enhance the performance of screw-based propulsion systems for versatile amphibious applications.

cs.RO↗

arXiv2024

CRANE: A Redundant, Multi-Degree-of-Freedom Computed Tomography Robot for Heightened Needle Dexterity within a Medical Imaging Bore

Computed Tomography (CT) image guidance enables accurate and safe minimally invasive treatment of diseases, including cancer and chronic pain, with needle-like tools via a percutaneous approach. The physician incrementally inserts and adjusts the needle with intermediate images due to the accuracy limitation of free-hand adjustment and patient physiological motion. Scanning frequency is limited to minimize ionizing radiation exposure for the patient and physician. Robots can provide high positional accuracy and compensate for physiological motion with fewer scans. To accomplish this, the robots must operate within the confined imaging bore while retaining sufficient dexterity to insert and manipulate the needle. This paper presents CRANE: CT Robotic Arm and Needle Emplacer, a CT-compatible robot with a design focused on system dexterity that enables physicians to manipulate and insert needles within the scanner bore as naturally as they would be able to by hand. We define abstract and measurable clinically motivated metrics for in-bore dexterity applicable to general-purpose intra-bore image-guided needle placement robots, develop an automatic robot planning and control method for intra-bore needle manipulation and device setup, and demonstrate the redundant linkage design provides dexterity across various human morphology and meets the clinical requirements for target accuracy during an in-situ evaluation.

cs.RO↗

arXiv2023

Symbolic Planning and Code Generation for Grounded Dialogue

Large language models (LLMs) excel at processing and generating both text and code. However, LLMs have had limited applicability in grounded task-oriented dialogue as they are difficult to steer toward task objectives and fail to handle novel grounding. We present a modular and interpretable grounded dialogue system that addresses these shortcomings by composing LLMs with a symbolic planner and grounded code execution. Our system consists of a reader and planner: the reader leverages an LLM to convert partner utterances into executable code, calling functions that perform grounding. The translated code's output is stored to track dialogue state, while a symbolic planner determines the next appropriate response. We evaluate our system's performance on the demanding OneCommon dialogue task, involving collaborative reference resolution on abstract images of scattered dots. Our system substantially outperforms the previous state-of-the-art, including improving task success in human evaluations from 56% to 69% in the most challenging setting.

cs.CL↗

arXiv2023

Using Textual Interface to Align External Knowledge for End-to-End Task-Oriented Dialogue Systems

Traditional end-to-end task-oriented dialogue systems have been built with a modularized design. However, such design often causes misalignment between the agent response and external knowledge, due to inadequate representation of information. Furthermore, its evaluation metrics emphasize assessing the agent's pre-lexicalization response, neglecting the quality of the completed response. In this work, we propose a novel paradigm that uses a textual interface to align external knowledge and eliminate redundant processes. We demonstrate our paradigm in practice through MultiWOZ-Remake, including an interactive textual interface built for the MultiWOZ database and a correspondingly re-processed dataset. We train an end-to-end dialogue system to evaluate this new dataset. The experimental results show that our approach generates more natural final responses and achieves a greater task success rate compared to the previous models.

cs.CL↗

arXiv2023

GPT-4 Technical Report

We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs. While less capable than humans in many real-world scenarios, GPT-4 exhibits human-level performance on various professional and academic benchmarks, including passing a simulated bar exam with a score around the top 10% of test takers. GPT-4 is a Transformer-based model pre-trained to predict the next token in a document. The post-training alignment process results in improved performance on measures of factuality and adherence to desired behavior. A core component of this project was developing infrastructure and optimization methods that behave predictably across a wide range of scales. This allowed us to accurately predict some aspects of GPT-4's performance based on models trained with no more than 1/1,000th the compute of GPT-4.

cs.CL↗

arXiv2023

Mixture of Soft Prompts for Controllable Data Generation

Large language models (LLMs) effectively generate fluent text when the target output follows natural language patterns. However, structured prediction tasks confine the output format to a limited ontology, causing even very large models to struggle since they were never trained with such restrictions in mind. The difficulty of using LLMs for direct prediction is exacerbated in few-shot learning scenarios, which commonly arise due to domain shift and resource limitations. We flip the problem on its head by leveraging the LLM as a tool for data augmentation rather than direct prediction. Our proposed Mixture of Soft Prompts (MSP) serves as a parameter-efficient procedure for generating data in a controlled manner. Denoising mechanisms are further applied to improve the quality of synthesized data. Automatic metrics show our method is capable of producing diverse and natural text, while preserving label semantics. Moreover, MSP achieves state-of-the-art results on three benchmarks when compared against strong baselines. Our method offers an alternate data-centric approach for applying LLMs to complex prediction tasks.

cs.CL↗

arXiv2023

Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking

Prompt-based methods with large pre-trained language models (PLMs) have shown impressive unaided performance across many NLP tasks. These models improve even further with the addition of a few labeled in-context exemplars to guide output generation. However, for more complex tasks such as dialogue state tracking (DST), designing prompts that reliably convey the desired intent is nontrivial, leading to unstable results. Furthermore, building in-context exemplars for dialogue tasks is difficult because conversational contexts are long while model input lengths are relatively short. To overcome these issues we first adapt a meta-learning scheme to the dialogue domain which stabilizes the ability of the model to perform well under various prompts. We additionally design a novel training method to improve upon vanilla retrieval mechanisms to find ideal in-context examples. Finally, we introduce a saliency model to limit dialogue text length, allowing us to include more exemplars per query. In effect, we are able to achieve highly competitive results for few-shot DST on MultiWOZ.

cs.CL↗

arXiv2022

Sources of Noise in Dialogue and How to Deal with Them

Training dialogue systems often entails dealing with noisy training examples and unexpected user inputs. Despite their prevalence, there currently lacks an accurate survey of dialogue noise, nor is there a clear sense of the impact of each noise type on task performance. This paper addresses this gap by first constructing a taxonomy of noise encountered by dialogue systems. In addition, we run a series of experiments to show how different models behave when subjected to varying levels of noise and types of noise. Our results reveal that models are quite robust to label errors commonly tackled by existing denoising algorithms, but that performance suffers from dialogue-specific noise. Driven by these observations, we design a data cleaning algorithm specialized for conversational settings and apply it as a proof-of-concept for targeted dialogue denoising.

cs.CL↗

arXiv2022

Data Augmentation for Intent Classification

Training accurate intent classifiers requires labeled data, which can be costly to obtain. Data augmentation methods may ameliorate this issue, but the quality of the generated data varies significantly across techniques. We study the process of systematically producing pseudo-labeled data given a small seed set using a wide variety of data augmentation techniques, including mixing methods together. We find that while certain methods dramatically improve qualitative and quantitative performance, other methods have minimal or even negative impact. We also analyze key considerations when implementing data augmentation methods in production.

cs.CL↗

arXiv2021

DG2: Data Augmentation Through Document Grounded Dialogue Generation

Collecting data for training dialog systems can be extremely expensive due to the involvement of human participants and need for extensive annotation. Especially in document-grounded dialog systems, human experts need to carefully read the unstructured documents to answer the users' questions. As a result, existing document-grounded dialog datasets are relatively small-scale and obstruct the effective training of dialogue systems. In this paper, we propose an automatic data augmentation technique grounded on documents through a generative dialogue model. The dialogue model consists of a user bot and agent bot that can synthesize diverse dialogues given an input document, which are then used to train a downstream model. When supplementing the original dataset, our method achieves significant improvement over traditional data augmentation methods. We also achieve great performance in the low-resource setting.

cs.CL↗

arXiv2021

Clean or Annotate: How to Spend a Limited Data Collection Budget

Crowdsourcing platforms are often used to collect datasets for training machine learning models, despite higher levels of inaccurate labeling compared to expert labeling. There are two common strategies to manage the impact of such noise. The first involves aggregating redundant annotations, but comes at the expense of labeling substantially fewer examples. Secondly, prior works have also considered using the entire annotation budget to label as many examples as possible and subsequently apply denoising algorithms to implicitly clean the dataset. We find a middle ground and propose an approach which reserves a fraction of annotations to explicitly clean up highly probable error samples to optimize the annotation process. In particular, we allocate a large portion of the labeling budget to form an initial dataset used to train a model. This model is then used to identify specific examples that appear most likely to be incorrect, which we spend the remaining budget to relabel. Experiments across three model variations and four natural language processing tasks show our approach outperforms or matches both label aggregation and advanced denoising methods designed to handle noisy labels when allocated the same finite annotation budget.

cs.CL↗

arXiv2021

GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentation

Practical dialogue systems require robust methods of detecting out-of-scope (OOS) utterances to avoid conversational breakdowns and related failure modes. Directly training a model with labeled OOS examples yields reasonable performance, but obtaining such data is a resource-intensive process. To tackle this limited-data problem, previous methods focus on better modeling the distribution of in-scope (INS) examples. We introduce GOLD as an orthogonal technique that augments existing data to train better OOS detectors operating in low-data regimes. GOLD generates pseudo-labeled candidates using samples from an auxiliary dataset and keeps only the most beneficial candidates for training through a novel filtering mechanism. In experiments across three target benchmarks, the top GOLD model outperforms all existing methods on all key metrics, achieving relative gains of 52.4%, 48.9% and 50.3% against median baseline performance. We also analyze the unique properties of OOS data to identify key factors for optimally applying our proposed method.

cs.CL↗

arXiv2021

Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems

Existing goal-oriented dialogue datasets focus mainly on identifying slots and values. However, customer support interactions in reality often involve agents following multi-step procedures derived from explicitly-defined company policies as well. To study customer service dialogue systems in more realistic settings, we introduce the Action-Based Conversations Dataset (ABCD), a fully-labeled dataset with over 10K human-to-human dialogues containing 55 distinct user intents requiring unique sequences of actions constrained by policies to achieve task success. We propose two additional dialog tasks, Action State Tracking and Cascading Dialogue Success, and establish a series of baselines involving large-scale, pre-trained language models on this dataset. Empirical results demonstrate that while more sophisticated networks outperform simpler models, a considerable gap (50.8% absolute accuracy) still exists to reach human-level performance on ABCD.

cs.CL↗

arXiv2019

SocialIQA: Commonsense Reasoning about Social Interactions

We introduce Social IQa, the first largescale benchmark for commonsense reasoning about social situations. Social IQa contains 38,000 multiple choice questions for probing emotional and social intelligence in a variety of everyday situations (e.g., Q: "Jordan wanted to tell Tracy a secret, so Jordan leaned towards Tracy. Why did Jordan do this?" A: "Make sure no one else could hear"). Through crowdsourcing, we collect commonsense questions along with correct and incorrect answers about social interactions, using a new framework that mitigates stylistic artifacts in incorrect answers by asking workers to provide the right answer to a different but related question. Empirical results show that our benchmark is challenging for existing question-answering models based on pretrained language models, compared to human performance (>20% gap). Notably, we further establish Social IQa as a resource for transfer learning of commonsense knowledge, achieving state-of-the-art performance on multiple commonsense reasoning tasks (Winograd Schemas, COPA).

cs.CL↗

arXiv2018

Decoupling Strategy and Generation in Negotiation Dialogues

We consider negotiation settings in which two agents use natural language to bargain on goods. Agents need to decide on both high-level strategy (e.g., proposing \$50) and the execution of that strategy (e.g., generating "The bike is brand new. Selling for just \$50."). Recent work on negotiation trains neural models, but their end-to-end nature makes it hard to control their strategy, and reinforcement learning tends to lead to degenerate solutions. In this paper, we propose a modular approach based on coarse di- alogue acts (e.g., propose(price=50)) that decouples strategy and generation. We show that we can flexibly set the strategy using supervised learning, reinforcement learning, or domain-specific knowledge without degeneracy, while our retrieval-based generation can maintain context-awareness and produce diverse utterances. We test our approach on the recently proposed DEALORNODEAL game, and we also collect a richer dataset based on real items on Craigslist. Human evaluation shows that our systems achieve higher task success rate and more human-like negotiation behavior than previous approaches.

cs.CL↗