256 citations · 295 across the 24 of their papers we have counts for
28 papers
QREF: Improving DeepSearch Agents by Aligning Search with Reasoning via Query Refinement and Evidence Filtering
Yujia Chen, Yuhui Wang, Junzhe Wang +15
DeepSearch agents achieve strong performance on complex information-seeking tasks through iterative search and reasoning. However, they often issue intent-misaligned, under-constra…
LifeSearch: Benchmarking Deep Research Agents for Real-World Life and Productivity
Yibo Wang, Senjie Jin, Yansong Ning +6
Deep research (DR) agents address open-ended information needs through multi-step reasoning, long-horizon web search, and evidence synthesis. However, existing benchmarks primarily…
Scaling Verifiable Environments for Long-horizon Work Agents
Jiazheng Zhang, Long Ma, Yunxian Yang +24
Work agents operate over digital artifacts to execute professional knowledge-intensive work, requiring training environments that support long-horizon interaction and trustworthy v…
Sci-MMR: Benchmarking Multi-Step Evidence-Grounded Scientific Reasoning in Multimodal Agents
Jiaqiang Li, Yajie Yang, Zhiheng Xi +15
Autonomous research agents are increasingly expected to search the literature, analyze experimental evidence, and generate scientific hypotheses. These capabilities require multi-s…
A Token-Level Analysis of Sampled-Token Reverse-KL On-Policy Distillation
Bing Shao, Jiazheng Zhang, Long Ma +12
On-policy distillation (OPD) supervises a student on its own trajectories with token-level signals from a frozen teacher, yet how a sampled loss allocates updates across tokens rem…
CAFE: Self-Improving Search Agents Need Co-Evolving Feedback
Boyang Liu, Senjie Jin, Peixin Wang +17
Reliable search requires more than acquiring external evidence. An agent must also recognize and recover from errors as its trajectory unfolds. In-trajectory feedback provides a me…
Entropy Is Not Enough: Unlocking Effective Reinforcement Learning for Visual Reasoning via Vision-Anchored Token Selection
Senjie Jin, Peixin Wang, Boyang Liu +8
While token-level entropy is commonly recognized as effective for credit assignment in text-only reinforcement learning with verifiable rewards (RLVR), it remains unclear whether t…
JFTA-Bench: Evaluate LLM's Ability of Tracking and Analyzing Malfunctions Using Fault Trees
Yuhui Wang, Zhixiong Yang, Ming Zhang +10
In the maintenance of complex systems, fault trees are used to locate problems and provide targeted solutions. To enable fault trees stored as images to be directly processed by la…
Memory in the Age of AI Agents
Yuyang Hu, Shichun Liu, Yanwei Yue +44
Memory has emerged, and will continue to remain, a core capability of foundation model-based agents. As research on agent memory rapidly expands and attracts unprecedented attentio…
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
Hengyuan Zhang, Zhihao Zhang, Mingyang Wang +26
Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat…
The Role of Entropy in Visual Grounding: Analysis and Optimization
Shuo Li, Jiajun Sun, Zhihao Zhang +10
Recent advances in fine-tuning multimodal large language models (MLLMs) using reinforcement learning have achieved remarkable progress, particularly with the introduction of variou…
DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training
Dingwei Zhu, Zhiheng Xi, Shihan Dou +15
Reinforcement learning (RL) has shown strong performance in LLM post-training, but real-world deployment often involves noisy or incomplete supervision. In such settings, complex a…
AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress
Zhiheng Xi, Chenyang Liao, Guanyu Li +12
Despite rapid development, large language models (LLMs) still encounter challenges in multi-turn decision-making tasks (i.e., agent tasks) like web shopping and browser navigation,…
Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning
Senjie Jin, Lu Chen, Zhiheng Xi +9
Natural language chain-of-thought (N-CoT) and Program chain-of-thought (P-CoT) have emerged as two primary paradigms for large language models (LLMs) to solve mathematical reasonin…
Unlocking the Essence of Beauty: Advanced Aesthetic Reasoning with Relative-Absolute Policy Optimization
Boyang Liu, Yifan Hu, Senjie Jin +5
Multimodal large language models (MLLMs) are well suited to image aesthetic assessment, as they can capture high-level aesthetic features leveraging their cross-modal understanding…
VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training
Dingwei Zhu, Shihan Dou, Zhiheng Xi +16
Reinforcement Learning (RL) in real-world environments often suffers from ambiguous or incomplete reward supervision, which undermines policy stability and generalization. Such noi…
Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination
Mingqi Wu, Zhihao Zhang, Qiaole Dong +11
Reasoning in large language models has long been a central research focus, and recent studies employing reinforcement learning (RL) have introduced diverse methods that yield subst…
Why Reinforcement Fine-Tuning Enables MLLMs Preserve Prior Knowledge Better: A Data Perspective
Zhihao Zhang, Qiaole Dong, Qi Zhang +12
Post-training algorithms such as Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT) are widely used to adapt (multimodal) large language models to downstream tasks. W…
What Makes a Good Speech Tokenizer for LLM-Centric Speech Generation? A Systematic Study
Xiaoran Fan, Zhichao Sun, Yangfan Gao +19
Speech-language models (SLMs) offer a promising path toward unifying speech and text understanding and generation. However, challenges remain in achieving effective cross-modal ali…
EliteKV: Scalable KV Cache Compression via RoPE Frequency Selection and Joint Low-Rank Projection
Yuhao Zhou, Sirui Song, Boyang Liu +6
Rotary Position Embedding (RoPE) enables each attention head to capture multi-frequency information along the sequence dimension and is widely applied in foundation models. However…
SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model
Yongting Zhang, Lu Chen, Guodong Zheng +10
The emergence of Vision Language Models (VLMs) has brought unprecedented advances in understanding multimodal information. The combination of textual and visual semantics in VLMs i…
Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
Zhiheng Xi, Wenxiang Chen, Boyang Hong +18
In this paper, we propose R: Learning Reasoning through Reverse Curriculum Reinforcement Learning (RL), a novel method that employs only outcome supervision to achieve the bene…
MouSi: Poly-Visual-Expert Vision-Language Models
Xiaoran Fan, Tao Ji, Changhao Jiang +21
Current large vision-language models (VLMs) often encounter challenges such as insufficient capabilities of a single visual component and excessively long visual tokens. These issu…
Secrets of RLHF in Large Language Models Part II: Reward Modeling
Binghai Wang, Rui Zheng, Lu Chen +24
Reinforcement Learning from Human Feedback (RLHF) has become a crucial technology for aligning language models with human values and intentions, enabling models to produce more hel…