2 citations · 3 across the 15 of their papers we have counts for
20 papers
Group-Marginalized Self-Rewarding RL Drives Zero-Label Self-Evolving
Yiming Wang, Yikang Liu, Qingyuan Tian +4
Self-rewarding reinforcement learning (RL) enables large language models (LLMs) to self-evolve without human labels. Existing ensemble-based methods construct reward references fro…
LivingArena: Do LLMs Know What Other LLMs Don't? Peer-Probing as Scalable Evaluation
Xingyu Chen, Rui Wang, Zhaopeng Tu +1
Fixed benchmarks are costly to renew and cannot adapt their questions to model-specific failures. We ask whether LLMs can instead discover one another's weaknesses and turn those o…
AdaMem: Learning What to Remember with Adaptive Memory Policies for Personalized Agents
Xingyu Chen, Rui Wang, Zhaopeng Tu +1
Long-term memory systems allow LLM agents to preserve information beyond a single context window, but most systems focus on storing and retrieving facts after extraction, leaving t…
Stabilizing Efficient Reasoning with Step-Level Advantage Selection
Han Wang, Xiaodong Yu, Jialian Wu +4
Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and verbose reasoning traces. While…
CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models
Runpeng Dai, Linfeng Song, Haolin Liu +8
Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm for enhancing the reasoning ability of Large Language Models (LLMs). Yet current RLVR methods often exp…
DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning
Ziyin Zhang, Jiahao Xu, Zhiwei He +10
Theorem proving serves as a major testbed for evaluating complex reasoning abilities in large language models (LLMs). However, traditional automated theorem proving (ATP) approache…
Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
Mengru Wang, Xingyu Chen, Yue Wang +12
Mixture-of-Experts (MoE) architectures within Large Reasoning Models (LRMs) have achieved impressive reasoning capabilities by selectively activating experts to facilitate structur…
DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
Zhiwei He, Tian Liang, Jiahao Xu +12
Reinforcement learning (RL) with large language models shows promise in complex reasoning. However, its progress is hindered by the lack of large-scale training data that is suffic…
Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
Xiaoyuan Liu, Tian Liang, Zhiwei He +6
Large Language Models (LLMs) show great promise in complex reasoning, with Reinforcement Learning with Verifiable Rewards (RLVR) being a key enhancement strategy. However, a preval…
Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains
Yi Su, Dian Yu, Linfeng Song +5
Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs…
Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls
Ante Wang, Linfeng Song, Ye Tian +6
Recent advancements in tree search algorithms guided by verifiers have significantly enhanced the reasoning capabilities of large language models (LLMs), but at the cost of increas…
Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique
Yansi Li, Jiahao Xu, Tian Liang +8
Enhancing the reasoning capabilities of large language models (LLMs), particularly for complex tasks requiring multi-step logical deductions, remains a significant challenge. Tradi…
RaSA: Rank-Sharing Low-Rank Adaptation
Zhiwei He, Zhaopeng Tu, Xing Wang +7
Low-rank adaptation (LoRA) has been prominently employed for parameter-efficient fine-tuning of large language models (LLMs). However, the limited expressive capacity of LoRA, stem…
The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
Ke Ji, Jiahao Xu, Tian Liang +10
Improving the reasoning capabilities of large language models (LLMs) typically requires supervised fine-tuning with labeled data or computationally expensive sampling. We introduce…
The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement
Ruihan Yang, Fanghua Ye, Jian Li +5
Large language models (LLMs) have recently transformed from text-based assistants to autonomous agents capable of planning, reasoning, and iteratively improving their actions. Whil…
Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
Yue Wang, Qiuzhi Liu, Jiahao Xu +11
Large language models (LLMs) such as OpenAI's o1 have demonstrated remarkable abilities in complex reasoning tasks by scaling test-time compute and exhibiting human-like deep think…
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
Xingyu Chen, Jiahao Xu, Tian Liang +11
The remarkable performance of models like the OpenAI o1 can be attributed to their ability to emulate human-like long-time thinking during inference. These models employ extended c…
Teaching LLMs to Refine with Tools
Dian Yu, Yuheng Zhang, Jiahao Xu +5
Large language models (LLMs) can refine their responses based on feedback, enabling self-improvement through iterative training or test-time refinement. However, existing methods p…
Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
Zicheng Lin, Tian Liang, Jiahao Xu +7
Mathematical reasoning tasks pose significant challenges for large language models (LLMs) because they require precise logical deduction and sequence analysis. In this work, we int…
Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation
Ziyin Zhang, Jiahao Xu, Tian Liang +4
Conventional speculative decoding (SD) methods utilize a predefined length policy for proposing drafts, which implies the premise that the target model smoothly accepts the propose…