1 citations · 2 across the 20 of their papers we have counts for
21 papers
Evolving Together, Failing Apart: The Skill-Policy Co-evolution Trap in Self-Improving Agents
Yujie Feng, Xiaobin Wang, Jinluan Yang +5
Skill-policy co-evolution, in which an agent's policy model and its skill bank improve each other during training, is a promising paradigm for self-improving agents. Current evalua…
VibeMemBench: Evaluating Memory Systems for Coding Agents on Real Repository Coding Tasks
Liyang Fan, Yingcheng Shi, Yongbin Li +7
Coding agents operate on real repository coding tasks, and persistent memory systems promise to reuse experience across tasks. Yet existing evaluations do not show whether those sy…
MemoryWalker: Stop Training Agents on Contexts They Never Saw
Zinco J, Xunjie Zhu, Shen Huang +3
Production agent harnesses such as Claude Code and Qwen-Agent compress context during rollout, but training under compression creates a conditioning problem: every eviction branche…
RecurSE: Bounded Recursive Self-Evaluation for LLM Rubric Judges
Kaiyuan Liu, Ziyuan Zhuang, Rongxiang Weng +1
LLM-as-judge is essential for evaluating open-ended text and steering post-training, yet improving the judge itself typically relies on expensive annotations, reward models, or dis…
State2State: Environment-Derived Mid-Training for LLM Agents
Xuanyu Lei, Yiqi Zhu, Chenliang Li +6
Training LLM agents commonly relies on supervised fine-tuning from expert trajectories or online reinforcement learning over human-specified tasks with handcrafted verifiers. Thoug…
Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences
Mingyang Li, Yurou Liu, Jieping Ye +3
In this report, we present LOGOS (Language Of Generative Objects in Science), a scientific generative language model that unifies heterogeneous tasks across the natural sciences wi…
EIBench: A Simulator-Based Benchmark and Turn-Credit RL for Emotion Management
Rongzhi Zhu, Xiang Huang, Yuchuan Wu +8
Emotional intelligence (EI) in Large Language Models (LLMs) is often evaluated through static understanding tasks or single-response dialogue generation. However, emotion managemen…
EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
Guhong Chen, Yingcheng Shi, Yongbin Li +6
Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and s…
SkillComposer: Learning to Evolve Agent Skills for Specification and Generalization
Qi Zhang, Zhaopeng Feng, Xiaonan Shi +8
Agent skills, which consist of reusable strategies that guide agent reasoning and action, have shown strong potential for improving model capability at inference time. However, cur…
Scaling Self-Evolving Agents via Parametric Memory
Tao Ren, Weiyao Luo, Hui Yang +8
Existing memory-augmented LLM agents store past experience exclusively in prompt space, as textual summaries or retrieved passages, while keeping model parameters frozen throughout…
ESPO: Early-Stopping Proximal Policy Optimization
Zihang Li, Rui Zhou, Yingcheng Shi +8
When a large language model under reinforcement learning commits a wrong reasoning step early in a trajectory, standard algorithms force it to keep generating until the maximum hor…
STAMP: Training Explicit Memory for Mobile GUI Agents in Controllable and Scalable Virtual Environments
Junyang Wang, Haiyang Xu, Xi Zhang +4
Mobile GUI agents excel at immediate reactive control but frequently fail in realistic, long-horizon tasks that require memory. This failure stems from a fundamental conflict betwe…
Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation
Kaiyuan Liu, Ziyuan Zhuang, Yang Bai +3
On-policy distillation (OPD) trains a student model on its own rollouts using dense feedback from a stronger teacher. Prior literature suggests that, provided teacher feedback is a…
ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
Xuhao Hu, Xi Zhang, Haiyang Xu +6
Computer Use Agents (CUAs) can act through both atomic GUI actions, such as click and type, and high-level tool calls, such as API-based file operations, but this hybrid action spa…
FGGM: Fisher-Guided Gradient Masking for Continual Learning
Chao-Hong Tan, Qian Chen, Wen Wang +6
Catastrophic forgetting impairs the continuous learning of large language models. We propose Fisher-Guided Gradient Masking (FGGM), a framework that mitigates this by strategically…
Fun-Audio-Chat Technical Report
Tongyi Fun Team, Qian Chen, Luyao Cheng +10
Recent advancements in joint speech-text models show great potential for seamless voice interactions. However, existing models face critical challenges: temporal resolution mismatc…
PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio Generation
Huadai Liu, Kaicheng Luo, Wen Wang +6
Video-to-Audio (V2A) generation requires balancing four critical perceptual dimensions: semantic consistency, audio-visual temporal synchrony, aesthetic quality, and spatial accura…
Fun-ASR Technical Report
Keyu An, Yanni Chen, Zhigao Chen +35
In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling, model size scaling, and deep in…
MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models
Fan Zhang, Zebang Cheng, Chong Deng +18
Recent advances in multimodal large language models (MLLMs) have catalyzed transformative progress in affective computing, enabling models to exhibit emergent emotional intelligenc…
DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations
Chao-Hong Tan, Qian Chen, Wen Wang +14
Recent studies on end-to-end (E2E) speech generation with large language models (LLMs) have attracted significant community attention, with multiple works extending text-based LLMs…
CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training
Zhihao Du, Changfeng Gao, Yuxuan Wang +19
In our prior works, we introduced a scalable streaming speech synthesis model, CosyVoice 2, which integrates a large language model (LLM) and a chunk-aware flow matching (FM) model…