9 citations · 11 across the 19 of their papers we have counts for
19 papers
Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning
Zhicheng Yang, Zhijiang Guo, Yifan Song +5
On-policy distillation (OPD) leverages dense teacher rewards to enhance reasoning models. However, scaling OPD to long-horizon tasks exposes a critical flaw: as the student's gener…
EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL
Minrui Xu, Zilin Wang, Mengyi DENG +12
Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlenecked by two challenges: the lack of scalable, robust execution environments and…
EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval
Yifan Song, Xingjian Tao, Zhicheng Yang +2
Graph-based Retrieval-Augmented Generation (GraphRAG) enhances LLMs by structuring corpus into graphs to facilitate multi-hop reasoning. While recent lightweight approaches reduce…
Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning
Zhicheng Yang, Zhijiang Guo, Yinya Huang +5
Scaling test-time compute via long Chain-of-Thought unlocks remarkable gains in reasoning capabilities, yet it faces practical limits due to the linear growth of KV cache and quadr…
CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning
Yongxin Wang, Zhicheng Yang, Meng Cao +5
Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures. When all rollouts are wrong, gradients stal…
Critique to Verify: Accurate and Honest Test-Time Scaling with RL-Trained Verifiers
Zhicheng Yang, Zhijiang Guo, Yinya Huang +4
Test-time scaling via solution sampling and aggregation has become a key paradigm for improving the reasoning performance of Large Language Models (LLMs). While reward model select…
When Inverse Data Outperforms: Exploring the Pitfalls of Mixed Data in Multi-Stage Fine-Tuning
Mengyi Deng, Xin Li, Tingyu Zhu +3
Existing work has shown that o1-level performance can be achieved with limited data distillation, but most existing methods focus on unidirectional supervised fine-tuning (SFT), ov…
Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration
Zhicheng Yang, Zhijiang Guo, Yinya Huang +6
Reinforcement Learning with Verifiable Reward (RLVR) is a powerful method for enhancing the reasoning abilities of Large Language Models, but its full potential is limited by a lac…
Understanding GUI Agent Localization Biases through Logit Sharpness
Xingjian Tao, Yiwei Wang, Yujun Cai +2
Multimodal large language models (MLLMs) have enabled GUI agents to interact with operating systems by grounding language into spatial actions. Despite their promising performance,…
TreeRPO: Tree Relative Policy Optimization
Zhicheng Yang, Zhijiang Guo, Yinya Huang +3
Large Language Models (LLMs) have shown remarkable reasoning capabilities through Reinforcement Learning with Verifiable Rewards (RLVR) methods. However, a key limitation of existi…
Are LLMs Really Not Knowledgeable? Mining the Submerged Knowledge in LLMs' Memory
Xingjian Tao, Yiwei Wang, Yujun Cai +2
Large language models (LLMs) have shown promise as parametric knowledge bases, but often underperform on question answering (QA) tasks due to hallucinations and uncertainty. While…
OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling
Zhicheng Yang, Yiwei Wang, Yinya Huang +7
Large language models (LLMs) have exhibited their problem-solving abilities in mathematical reasoning. Solving realistic optimization (OPT) problems in application scenarios requir…
Process-Driven Autoformalization in Lean 4
Jianqiao Lu, Yingjia Wan, Zhengying Liu +10
Autoformalization, the conversion of natural language mathematics into formal languages, offers significant potential for advancing mathematical reasoning. However, existing effort…
Proving Theorems Recursively
Haiming Wang, Huajian Xin, Zhengying Liu +8
Recent advances in automated theorem proving leverages language models to explore expanded search spaces by step-by-step proof generation. However, such approaches are usually base…
ATG: Benchmarking Automated Theorem Generation for Generative Language Models
Xiaohan Lin, Qingxing Cao, Yinya Huang +4
Humans can develop new theorems to explore broader and more complex mathematical results. While current generative language models (LMs) have achieved significant improvement in au…
CLOMO: Counterfactual Logical Modification with Large Language Models
Yinya Huang, Ruixin Hong, Hongming Zhang +6
In this study, we delve into the realm of counterfactual reasoning capabilities of large language models (LLMs). Our primary objective is to cultivate the counterfactual thought pr…
AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations
Zhicheng Yang, Yinya Huang, Jing Xiong +4
Large Language Models prompting, such as using in-context demonstrations, is a mainstream technique for invoking LLMs to perform high-performance and solid complex reasoning (e.g.,…
Unbiased Math Word Problems Benchmark for Mitigating Solving Bias
Zhicheng Yang, Jinghui Qin, Jiaqi Chen +1
In this paper, we revisit the solving bias when evaluating models on current Math Word Problem (MWP) benchmarks. However, current solvers exist solving bias which consists of data…
LogicSolver: Towards Interpretable Math Word Problem Solving with Logical Prompt-enhanced Learning
Zhicheng Yang, Jinghui Qin, Jiaqi Chen +2
Recently, deep learning models have made great progress in MWP solving on answer accuracy. However, they are uninterpretable since they mainly rely on shallow heuristics to achieve…