1 citations · 3 across the 15 of their papers we have counts for
13 papers · 1 filter
PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking
Pan Wang, Yihao Hu, Guangyuan Dong +8
Looped language models can run more iterations at test time, but additional iterations need not help them solve longer problems. For sequential state tracking, final-answer supervi…
Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise Reasoning
Yongqi Tong, Zhenyu Zhang, Zimi Liu +8
Answer-only reinforcement learning (RL) trains reasoning models to solve fully specified problems, but many realistic queries omit a premise needed for a unique answer. In this set…
STAGE: Controlled Objective Admission for Multi-Preference LLM Alignment
Yongqi Tong, Zhenyu Zhang, Ruirui Wang +6
Multi-preference alignment is often framed as scalarization: combine reward dimensions, then optimize. This leaves a temporal decision underspecified: when should each preference d…
Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction
Pan Wang, Yihao Hu, Hang Wang +6
Self-correction is particularly useful when a failure constrains the next repair. Coding agents benefit from this property because compilers, tests, and execution traces turn many…
How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel
Chang Liu, Chaoyang Ning, Dayi Jiang +32
Traditional industrial agents rely on modular pipelines, including Router, Retriever, Planner, Executor, Responder, Reviewer, and other components. These systems often fracture int…
Dingtalk DeepResearch: A Unified Multi Agent Framework for Adaptive Intelligence in Enterprise Environments
Mengyuan Chen, Chengjun Dai, Xinyang Dong +7
We present Dingtalk DeepResearch, a unified multi agent intelligence framework for real world enterprise environments, delivering deep research, heterogeneous table reasoning, and…
REWARD CONSISTENCY: Improving Multi-Objective Alignment from a Data-Centric Perspective
Zhihao Xu, Yongqi Tong, Xin Zhang +2
Multi-objective preference alignment in language models often encounters a challenging trade-off: optimizing for one human preference (e.g., helpfulness) frequently compromises oth…
BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment
Sizhe Wang, Yongqi Tong, Hengyuan Zhang +3
Reinforcement Learning with Human Feedback (RLHF) is the key to the success of large language models (LLMs) in recent years. In this work, we first introduce the concepts of knowle…
Optimizing Language Model's Reasoning Abilities with Weak Supervision
Yongqi Tong, Sizhe Wang, Dawei Li +6
While Large Language Models (LLMs) have demonstrated proficiency in handling complex queries, much of the past work has depended on extensively annotated datasets by human experts.…
Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning
Yongqi Tong, Dawei Li, Sizhe Wang +3
Recent works have shown the benefits to LLMs from fine-tuning golden-standard Chain-of-Thought (CoT) rationales or using them as correct examples in few-shot prompting. While human…
Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinking
Yongqi Tong, Yifan Wang, Dawei Li +4
Chain-of-Thought(CoT) prompting and its variants explore equipping large language models (LLMs) with high-level reasoning abilities by emulating human-like linear cognition and log…
ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation
Zi Lin, Zihan Wang, Yongqi Tong +4
Despite remarkable advances that large language models have achieved in chatbots, maintaining a non-toxic user-AI interactive environment has become increasingly critical nowadays.…
Pretrained Language Encoders are Natural Tagging Frameworks for Aspect Sentiment Triplet Extraction
Yanjie Gou, Yinjie Lei, Lingqiao Liu +3
Aspect Sentiment Triplet Extraction (ASTE) aims to extract the spans of aspect, opinion, and their sentiment relations as sentiment triplets. Existing works usually formulate the s…