13 citations · 32 across the 68 of their papers we have counts for
40 papers · 1 filter
DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment
Xinyu Geng, Xuanhua He, Sixiang Chen +7
Training tool-use agents to improve from their own experience remains challenging, as supervised fine-tuning relies on fixed teacher-distilled trajectories, while sparse-reward rei…
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
Xiang Hu, Xinyu Wei, Hao Gu +10
Scaling modern large language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of dense attention. Chunk-wise sparse atten…
DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification
Rui Liu, Dian Yu, Zhenwen Liang +6
Aligning Multimodal Large Language Models (MLLMs) requires reliable reward models, yet existing single-step evaluators can suffer from lazy judging, exploiting language priors over…
Locas: Your Models are Principled Initializers of Locally-Supported Parametric Memories
Sidi Lu, Zhenwen Liang, Dongyang Ma +3
In this paper, we aim to bridge test-time-training with a new type of parametric memory that can be flexibly offloaded from or merged into model parameters. We present Locas, a Loc…
Verified Critical Step Optimization for LLM Agents
Mukai Li, Qingcheng Zeng, Tianqing Fang +5
As large language model agents tackle increasingly complex long-horizon tasks, effective post-training becomes critical. Prior work faces fundamental challenges: outcome-only rewar…
The End of Manual Decoding: Towards Truly End-to-End Language Models
Zhichao Wang, Dongyang Ma, Xinting Huang +6
The "end-to-end" label for LLMs is a misnomer. In practice, they depend on a non-differentiable decoding process that requires laborious, hand-tuning of hyperparameters like temper…
CLUE: Non-parametric Verification from Experience via Hidden-State Clustering
Zhenwen Liang, Ruosen Li, Yujun Zhou +5
Assessing the quality of Large Language Model (LLM) outputs presents a critical challenge. Previous methods either rely on text-level information (e.g., reward models, majority vot…
WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models
Rui Wang, Ce Zhang, Jun-Yu Ma +10
The hallmark of Deep Research agents lies in compositional reasoning, the capacity to aggregate distributed, heterogeneous information into coherent logical insights. However, curr…
UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
Chenlong Deng, Zhisong Zhang, Kelong Mao +6
Large language models are increasingly capable of handling long-context inputs, but the memory overhead of key-value (KV) cache remains a major bottleneck for general-purpose deplo…
EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving
Mukai Li, Linfeng Song, Zhenwen Liang +5
Large Language Models (LLMs) have recently advanced the field of Automated Theorem Proving (ATP), attaining substantial performance gains through widely adopted test-time scaling s…
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…
Recall with Reasoning: Chain-of-Thought Distillation for Mamba's Long-Context Memory and Extrapolation
Junyu Ma, Tianqing Fang, Zhisong Zhang +3
Mamba's theoretical infinite-context potential is limited in practice when sequences far exceed training lengths. This work explores unlocking Mamba's long-context memory ability b…
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…
InComeS: Integrating Compression and Selection Mechanisms into LLMs for Efficient Model Editing
Shuaiyi Li, Zhisong Zhang, Yang Deng +6
Although existing model editing methods perform well in recalling exact edit facts, they often struggle in complex scenarios that require deeper semantic understanding rather than…
WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback
Minda Hu, Tianqing Fang, Jianshu Zhang +7
Web agents powered by Large Language Models (LLMs) show promise for next-generation AI, but their limited reasoning in uncertain, dynamic web environments hinders robust deployment…
WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model
Tianqing Fang, Hongming Zhang, Zhisong Zhang +4
Agent self-improvement, where the backbone Large Language Model (LLM) of the agent are trained on trajectories sampled autonomously based on their own policies, has emerged as a pr…
WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms
Zhisong Zhang, Tianqing Fang, Kaixin Ma +4
With recent advancements in large language models, web agents have been greatly improved. However, dealing with complex and dynamic web environments requires more advanced planning…
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…
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…
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…