32 citations · 112 across the 94 of their papers we have counts for
101 papers
MMedAgent-Plus: Scaling Multimodal Medical Agents across Modalities, Tasks and Workflows
Ruoxin Wang, Yuanting Pan, Binxu Li +13
Medical workflows often require multiple interdependent analyses, but existing specialist and generalist AI models are not designed to coordinate them. We introduce MMedAgent-Plus,…
CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution
Jixuan Chen, Jiaxin Zhang, Qinyuan Ye +11
Terminal-agent capability depends jointly on model weights and the runtime harness that formats prompts, binds tools, and handles error recovery. Existing harness-model co-evolutio…
Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight
Haoxiang Zhang, Qinglin Chen, Hiroaki Hayashi +9
Reinforcement learning with verifiable rewards (RLVR) turns agent experience into learning signals primarily through scalar outcome rewards after interaction. For group-relative ob…
Opera: A Verbal Critic Framework for Long-horizon Coding Agents
Kai Mei, Zhiyuan Hu, Yutong Dai +7
Long-horizon coding agents need timely corrections, yet feedback can be ineffective or even harmful when it misjudges ongoing work or fails to address the underlying problem. Exist…
Critical-State RL: Diagnosing Trainable States for Multi-Turn Tool Use
Zixiang Chen, Wenting Zhao, Zhepeng Cen +9
Multi-turn tool-use failures can hinge on a single model call, yet reward variation alone does not reveal which call would benefit from training. When rewards depend on later inter…
Salesforce Koa: An Enterprise Language Model for Agentic Tool Use
Zixiang Chen, Sufeng Niu, Yingchi Liu +23
We present Salesforce Koa, an enterprise language model built by post-training the open-weight Nemotron-3-Super-120B foundation model with reinforcement learning using Group Relati…
Fork Where the Model Changes Its Mind: Belief-Shift Branching for Tree-Structured Reinforcement Learning
Bin Lei, Yu Li, Prafulla Kumar Choubey +7
Tree-structured rollouts give critic-free reinforcement learning with verifiable rewards (RLVR) step-level credit: fork a chain at an intermediate point, and sibling outcome differ…
RAPTOR: Role-Aware Private Training for Mixture-of-Experts
Duc Dm, Khai Le-Duc, Nguyen Do +18
Differentially private (DP) fine-tuning methods treat sparse Mixture-of-Experts (MoE) models as a single dense block, ignoring that shared layers see all data while experts only se…
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
Heng Wang, Jielin Qiu, Wenting Zhao +8
Large language models achieve superior performance on tasks that require extended reasoning, but long chains of thought make the KV cache a severe memory bottleneck. Existing KV ca…
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
Cheng Qian, Wenting Zhao, Liangwei Yang +6
Recent work on distillation transfers the capabilities of large models to smaller ones often by updating the latter's parameters, through teacher forcing, on-policy distillation, a…
DarwinX: Evolving Agent Harnesses Through Natural Selection
Yifan Zhang, Yutong Dai, Juntao Tan +9
An LLM agent's capability depends not only on model weights but on its harness: prompts, tools, skills, and control flow. Self-improvement loops already edit harnesses, yet single-…
Evidence-Backed Video Question Answering
Shijie Wang, Honglu Zhou, Ziyang Wang +5
Current Video Large Language Models (Video LLMs) excel in question answering (QA) but largely operate as black boxes, providing textual answers without verifiable visual grounding.…
Mixture-of-Parallelisms: Towards Memory-Efficient Training Stack for Mixture-of-Experts Models
Xuan-Phi Nguyen, Shrey Pandit, Yiran Zhao +3
This paper showcases a memory-efficient training stack for Mixture-of-Experts (MoE) models. It is a training paradigm that combines and specializes various existing and novel paral…
BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces
Liangwei Yang, Jielin Qiu, Zixiang Chen +9
Many decision-support settings require systems that adapt to individual users, but evaluation data for this problem remain limited. Existing benchmarks for user understanding often…
Counterparty Modeling is Not Strategy: The Limits of LLM Negotiators
Romain Cosentino, Sarath Shekkizhar, Adam Earle +1
Negotiation requires more than inferring what the other side wants: it requires using that information to make advantageous offers and counteroffers over multiple turns. We study w…
Whisper-AuT: Domain-Adapted Audio Encoder for Efficient Audio-LLM Training
Jielin Qiu, Ming Zhu, Wenting Zhao +11
Audio-native large language models (audio-LLMs) commonly use Whisper as their audio encoder. However, Whisper was trained exclusively on speech data, producing weak representations…
RealUserSim: Bridging the Reality Gap in Agent Benchmarking via Grounded User Simulation
Ming Zhu, Juntao Tan, Rithesh Murthy +6
LLM-based user simulation is the primary mechanism for end-to-end agent evaluation, yet simulated users are poor proxies for real humans: unconstrained LLM defaults produce a Forma…
Enterprise Sales Copilot: Enabling Real-Time AI Support with Automatic Information Retrieval in Live Sales Calls
Jielin Qiu, Liangwei Yang, Ming Zhu +11
During live sales calls, customers frequently ask detailed product questions that require representatives to manually search internal databases and CRM systems. This process typica…
Building Enterprise Realtime Voice Agents from Scratch: A Technical Tutorial
Jielin Qiu, Zixiang Chen, Liangwei Yang +11
We present a technical tutorial for building enterprise-grade realtime voice agents from first principles. While end-to-end speech-to-speech models may ultimately provide the best…
Position: Vector Prompt Interfaces Should Be Exposed to Enable Customization of Large Language Models
Liangwei Yang, Shiyu Wang, Haolin Chen +12
As large language models (LLMs) transition from research prototypes to real-world systems, customization has emerged as a central bottleneck. While text prompts can already customi…
VoiceAgentRAG: Solving the RAG Latency Bottleneck in Real-Time Voice Agents Using Dual-Agent Architectures
Jielin Qiu, Jianguo Zhang, Zixiang Chen +12
We present VoiceAgentRAG, an open-source dual-agent memory router that decouples retrieval from response generation. A background Slow Thinker agent continuously monitors the conve…
AudioCapBench: Quick Evaluation on Audio Captioning across Sound, Music, and Speech
Jielin Qiu, Jianguo Zhang, Zixiang Chen +13
We introduce AudioCapBench, a benchmark for evaluating audio captioning capabilities of large multimodal models. \method covers three distinct audio domains, including environmenta…
Prompt Optimization Via Diffusion Language Models
Shiyu Wang, Haolin Chen, Liangwei Yang +8
We propose a diffusion-based framework for prompt optimization that leverages Diffusion Language Models (DLMs) to iteratively refine system prompts through masked denoising. By con…
Future Optical Flow Prediction Improves Robot Control & Video Generation
Kanchana Ranasinghe, Honglu Zhou, Yu Fang +7
Future motion representations, such as optical flow, offer immense value for control and generative tasks. However, forecasting generalizable spatially dense motion representations…