Mingyang Xu

Yiyou Sun, Xinyang Han, Weichen Zhang et al.

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long-horizon, economically valuable, real-world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 subfields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is 2.6%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP-relevant impact.

Manqing Mao, Paishun Ting, Yijian Xiang et al.

Recent advancements in large language models (LLMs) have provided a new avenue for chatbot development. Most existing research, however, has primarily centered on single-user chatbots that determine "What" to answer. This paper highlights the complexity of multi-user chatbots, introducing the 3W design dimensions: "What" to say, "When" to respond, and "Who" to answer. Additionally, we proposed Multi-User Chat Assistant (MUCA), an LLM-based framework tailored for group discussions. MUCA consists of three main modules: Sub-topic Generator, Dialog Analyzer, and Conversational Strategies Arbitrator. These modules jointly determine suitable response contents, timings, and appropriate addressees. This paper further proposes an LLM-based Multi-User Simulator (MUS) to ease MUCA's optimization, enabling faster simulation of conversations between the chatbot and simulated users, and speeding up MUCA's early development. In goal-oriented conversations with a small to medium number of participants, MUCA demonstrates effectiveness in tasks like chiming in at appropriate timings, generating relevant content, and improving user engagement, as shown by case studies and user studies.

Maurice Diesendruck, Jianzhe Lin, Shima Imani et al.

When LLMs perform zero-shot inference, they typically use a prompt with a task specification, and generate a completion. However, there is no work to explore the possibility of the reverse - going from completion to task specification. In this paper, we employ both directions to perform cycle-supervised learning entirely in-context. Our goal is to create a forward map f : X -> Y (e.g. image -> generated caption), coupled with a backward map g : Y -> X (e.g. caption -> generated image) to construct a cycle-consistency "loss" (formulated as an update to the prompt) to enforce g(f(X)) ~= X. The technique, called CyclePrompt, uses cycle-consistency as a free supervisory signal to iteratively craft the prompt. Importantly, CyclePrompt reinforces model performance without expensive fine-tuning, without training data, and without the complexity of external environments (e.g. compilers, APIs). We demonstrate CyclePrompt in two domains: code generation and image captioning. Our results on the HumanEval coding benchmark put us in first place on the leaderboard among models that do not rely on extra training data or usage of external environments, and third overall. Compared to the GPT4 baseline, we improve accuracy from 80.5% to 87.2%. In the vision-language space, we generate detailed image captions which outperform baseline zero-shot GPT4V captions, when tested against natural (VQAv2) and diagrammatic (FigureQA) visual question-answering benchmarks. To the best of our knowledge, this is the first use of self-supervised learning for prompting.

Qing Zhang, Jing Huang, Mingyang Xu et al.

While mainstream robotics pursues metric precision and flawless performance, this paper explores the creative potential of a deliberately "lo-fi" approach. We present the "Semantic Glitch," a soft flying robotic art installation whose physical form, a 3D pixel style cloud, is a "physical glitch" derived from digital archaeology. We detail a novel autonomous pipeline that rejects conventional sensors like LiDAR and SLAM, relying solely on the qualitative, semantic understanding of a Multimodal Large Language Model to navigate. By authoring a bio-inspired personality for the robot through a natural language prompt, we create a "narrative mind" that complements the "weak," historically, loaded body. Our analysis begins with a 13-minute autonomous flight log, and a follow-up study statistically validates the framework's robustness for authoring quantifiably distinct personas. The combined analysis reveals emergent behaviors, from landmark-based navigation to a compelling "plan to execution" gap, and a character whose unpredictable, plausible behavior stems from a lack of precise proprioception. This demonstrates a lo-fi framework for creating imperfect companions whose success is measured in character over efficiency.

Yaogen Yang, Haozhe Zhang, Xiaoyi Qin et al.

Building cross-lingual voice conversion (VC) systems for multiple speakers and multiple languages has been a challenging task for a long time. This paper describes a parallel non-autoregressive network to achieve bilingual and code-switched voice conversion for multiple speakers when there are only mono-lingual corpora for each language. We achieve cross-lingual VC between Mandarin speech with multiple speakers and English speech with multiple speakers by applying bilingual bottleneck features. To boost voice cloning performance, we use an adversarial speaker classifier with a gradient reversal layer to reduce the source speaker's information from the output of encoder. Furthermore, in order to improve speaker similarity between reference speech and converted speech, we adopt an embedding consistency loss between the synthesized speech and its natural reference speech in our network. Experimental results show that our proposed method can achieve high quality converted speech with mean opinion score (MOS) around 4. The conversion system performs well in terms of speaker similarity for both in-set speaker conversion and out-set-of one-shot conversion.