15 citations · 74 across the 40 of their papers we have counts for
23 papers · 1 filter
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
Yan Yu, Zhengxi Lu, Yizhou Liu +8
Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivates self on-policy distillation (OPD) to supply dense token-le…
PaperGym: Rubric-Centered Evolution for Research-Plan Generation
Yuhan Wang, Zhengxi Lu, Yuchen Yan +6
Research planning is the decisive capability of AI scientists. Yet a research plan admits no verifiable answer, so reinforcement learning lacks the environment it requires: tasks p…
Pause or Fabricate? Training Language Models for Grounded Reasoning
Yiwen Qiu, Linjuan Wu, Yizhou Liu +9
Large language models have achieved remarkable progress on complex reasoning tasks. However, they often implicitly fabricate information when inputs are incomplete, producing confi…
Active Confusion Expression in Large Language Models: Leveraging World Models toward Better Social Reasoning
Jialu Du, Guiyang Hou, Yihui Fu +4
While large language models (LLMs) excel in mathematical and code reasoning, we observe they struggle with social reasoning tasks, exhibiting cognitive confusion, logical inconsist…
EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering
Haolei Xu, Xinyu Mei, Yuchen Yan +5
Large language model (LLM) steering has emerged as a promising paradigm for controlling model behavior at inference time through targeted manipulation of hidden states, offering a…
Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models
Haitao Hong, Yuchen Yan, Xingyu Wu +5
Large language models (LLMs) have demonstrated remarkable performance in reasoning tasks, where reinforcement learning (RL) serves as a key algorithm for enhancing their reasoning…
GroundAct: Can LLM Agents Ground Actions in Environmental States?
Zixuan Wang, Dingming Li, Hongxing Li +8
LLM agents achieve 85-96% success on tasks where instructions fully specify the action, but drop to 29-53% when action feasibility depends on environmental state that the instructi…
TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence
Guiyang Hou, Xing Gao, Yuchuan Wu +8
Recently, Large Language Models (LLMs) have made significant progress in IQ-related domains that require careful thinking, such as mathematics and coding. However, enhancing LLMs'…
Let LRMs Break Free from Overthinking via Self-Braking Tuning
Haoran Zhao, Yuchen Yan, Yongliang Shen +7
Large reasoning models (LRMs), such as OpenAI o1 and DeepSeek-R1, have significantly enhanced their reasoning capabilities by generating longer chains of thought, demonstrating out…
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks
Wenqi Zhang, Mengna Wang, Gangao Liu +10
Recent advances in deep thinking models have demonstrated remarkable reasoning capabilities on mathematical and coding tasks. However, their effectiveness in embodied domains which…
DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL
Haoyuan Ma, Yongliang Shen, Hengwei Liu +5
Recent text-to-SQL systems powered by large language models (LLMs) have demonstrated remarkable performance in translating natural language queries into SQL. However, these systems…
AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification
Xuan Zhang, Yongliang Shen, Zhe Zheng +6
Large language models (LLMs) have demonstrated remarkable capabilities in tool learning. In real-world scenarios, user queries are often ambiguous and incomplete, requiring effecti…
STaR-SQL: Self-Taught Reasoner for Text-to-SQL
Mingqian He, Yongliang Shen, Wenqi Zhang +3
Generating step-by-step "chain-of-thought" rationales has proven effective for improving the performance of large language models on complex reasoning tasks. However, applying such…
EgoSocialArena: Benchmarking the Social Intelligence of Large Language Models from a First-person Perspective
Guiyang Hou, Wenqi Zhang, Yongliang Shen +3
Social intelligence is built upon three foundational pillars: cognitive intelligence, situational intelligence, and behavioral intelligence. As large language models (LLMs) become…
TimeToM: Temporal Space is the Key to Unlocking the Door of Large Language Models' Theory-of-Mind
Guiyang Hou, Wenqi Zhang, Yongliang Shen +2
Theory of Mind (ToM)-the cognitive ability to reason about mental states of ourselves and others, is the foundation of social interaction. Although ToM comes naturally to humans, i…
Advancing Process Verification for Large Language Models via Tree-Based Preference Learning
Mingqian He, Yongliang Shen, Wenqi Zhang +2
Large Language Models (LLMs) have demonstrated remarkable potential in handling complex reasoning tasks by generating step-by-step rationales.Some methods have proven effective in…
Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives
Wenqi Zhang, Yongliang Shen, Linjuan Wu +4
The reflection capacity of Large Language Model (LLM) has garnered extensive attention. A post-hoc prompting strategy, e.g., reflexion and self-refine, refines LLM's response based…
TaskBench: Benchmarking Large Language Models for Task Automation
Yongliang Shen, Kaitao Song, Xu Tan +6
In recent years, the remarkable progress of large language models (LLMs) has sparked interest in task automation, which involves decomposing complex tasks described by user instruc…
An Expression Tree Decoding Strategy for Mathematical Equation Generation
Wenqi Zhang, Yongliang Shen, Qingpeng Nong +3
Generating mathematical equations from natural language requires an accurate understanding of the relations among math expressions. Existing approaches can be broadly categorized i…
Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow
Wenqi Zhang, Yongliang Shen, Zeqi Tan +3
Industries such as finance, meteorology, and energy generate vast amounts of data daily. Efficiently managing, processing, and displaying this data requires specialized expertise a…
PromptNER: Prompt Locating and Typing for Named Entity Recognition
Yongliang Shen, Zeqi Tan, Shuhui Wu +5
Prompt learning is a new paradigm for utilizing pre-trained language models and has achieved great success in many tasks. To adopt prompt learning in the NER task, two kinds of met…
Query-based Instance Discrimination Network for Relational Triple Extraction
Zeqi Tan, Yongliang Shen, Xuming Hu +4
Joint entity and relation extraction has been a core task in the field of information extraction. Recent approaches usually consider the extraction of relational triples from a ste…
Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem
Wenqi Zhang, Yongliang Shen, Yanna Ma +4
Math word problem solver requires both precise relation reasoning about quantities in the text and reliable generation for the diverse equation. Current sequence-to-tree or relatio…