Papers by Biqing Qi
MARS2: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation (2026.acl-long)
Copied to clipboard
Pengfei Li, Shijie Wang, Fangyuan Li, Yikun Fu, Kaifeng Liu, Kaiyan Zhang, Dazhi Zhang, Yuqiang Li, Biqing Qi, Bowen Zhou
| Challenge: | Existing approaches to reinforcement learning are decoupled from structured search due to limited trajectory diversity. |
| Approach: | They propose a unified RL framework that integrates multiple agents within a shared tree-structured search environment. |
| Outcome: | Experiments show that MARS2 improves performance across diverse model combinations and training settings. |
ReviewRL: Towards Automated Scientific Review with RL (2025.emnlp-main)
Copied to clipboard
Sihang Zeng, Kai Tian, Kaiyan Zhang, Yuru Wang, Junqi Gao, Runze Liu, Sa Yang, Jingxuan Li, Xinwei Long, Jiaheng Ma, Biqing Qi, Bowen Zhou
| Challenge: | Existing automated review systems struggle with factual accuracy, rating consistency, and analytical depth. |
| Approach: | They propose a framework for generating comprehensive and factually grounded scientific paper reviews using supervised fine-tuning and reinforcement learning. |
| Outcome: | The proposed framework outperforms existing methods on ICLR 2025 papers. |
CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following (2024.acl-long)
Copied to clipboard
| Challenge: | Large-scale language models (LLMs) are increasingly exposed to private data and are becoming more and more prevalent. |
| Approach: | They propose a collaborative generation framework that integrates large and small language models to address privacy concerns logically. |
| Outcome: | The proposed framework combines large and small models to address privacy concerns logically. |
PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuning (2024.naacl-long)
Copied to clipboard
| Challenge: | Large language models excel in various tasks, but their huge size and inaccessibility of parameters present challenges for practical deployment. |
| Approach: | They propose to use CoT data to distill task-specific ability from large language models to smaller models . they use reasoning programs to suppress errors in distilled data and improve distillation quality . |
| Outcome: | The proposed model outperforms LLMs on arithmetic reasoning, symbolic reasoning, and general ability. |
Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System (2025.acl-long)
Copied to clipboard
Haoyang Su, Renqi Chen, Shixiang Tang, Zhenfei Yin, Xinzhe Zheng, Jinzhe Li, Biqing Qi, Qi Wu, Hui Li, Wanli Ouyang, Philip Torr, Bowen Zhou, Nanqing Dong
| Challenge: | Recent AI methods have shown promise in tasks such as hypothesis generation and experimental design, but they fail to replicate the collaborative nature of real-world scientific practices. |
| Approach: | They propose a virtual scientific system that mimics the collaborative nature of scientific research by organizing a team of agents to generate, evaluate, and refine research ideas. |
| Outcome: | The proposed system outperforms the state-of-the-art method in producing new scientific ideas and offers valuable insights to guide future research. |
On Large Language Models’ Hallucination with Regard to Known Facts (2024.naacl-long)
Copied to clipboard
Che Jiang, Biqing Qi, Xiangyu Hong, Dayuan Fu, Yang Cheng, Fandong Meng, Mo Yu, Bowen Zhou, Jie Zhou
| Challenge: | Large language models are successful in answering factoid questions but are also prone to hallucination. |
| Approach: | They propose self-reporting to the model when faced with such limitations. |
| Outcome: | The proposed classifier can detect hallucinations with an 88% success rate and can be used to answer factoid questions with correct answer knowledge. |
Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process (2025.acl-long)
Copied to clipboard
| Challenge: | Supervised Fine-Tuning (SFT) and Preference Optimization (PO) are key processes for aligning Language Models with human preferences post pre-training. |
| Approach: | They propose to combine Supervised Fine-Tuning and Preference Optimization (PO) with two sub-processes defined at token level within the Markov Decision Process (MDP) |
| Outcome: | The proposed process performs comparably or even superiorly to SFT and some typical PO methods across several tasks, particularly those requires generation, reasoning, and fact-following abilities. |
SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation (2026.findings-acl)
Copied to clipboard
Shuang Cheng, Yihan Bian, Dawei Liu, Yuhua Jiang, Yihao Liu, Linfeng Zhang, Qian Yao, Zhongbo Tian, Wenhai Wang, Qipeng Guo, Kai Chen, Biqing Qi, Bowen Zhou
| Challenge: | Autoregressive (AR) language models are a dominant paradigm in the field of parallelism and non-causal modeling. |
| Approach: | They propose a blockwise discrete diffusion model that preserves AR-compatible serving while enabling parallel intra-block generation. |
| Outcome: | The proposed model achieves theoretical speedups over 5 and wall-clock speedup of 2.3 on H200 GPUs in latency-critical regimes. |
LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing (2026.findings-acl)
Copied to clipboard
Hao Li, Yiqun Zhang, Zhaoyan Guo, Chenxu Wang, Shengji Tang, Qiaosheng Zhang, Yang Chen, Biqing Qi, Peng Ye, Lei Bai, Zhen Wang, Shuyue Hu
| Challenge: | Large language model (LLM) routing assigns each query to the best suitable model from an ensemble. |
| Approach: | They introduce a large-scale benchmark and unified framework for LLM routing . they find that many routing methods exhibit similar performance under unified evaluation . |
| Outcome: | The proposed benchmark provides comprehensive metrics for both performance-oriented and performance-cost trade-off routing. |
WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for self-improvement of large language models with verifiable rewards (RLVR) can drift over iterations, while corpus-grounded approaches rely on curated data environments. |
| Approach: | They propose a Web-grounded Iterative Self-play Tree framework for domain-targeted reasoning improvement that learns directly from the open-web without requiring any pre-arranged domain corpus. |
| Outcome: | The proposed framework outperforms both purely endogenous self-evolution and corpus-grounded self-play baselines and is domain-steerable. |
SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding (2026.acl-long)
Copied to clipboard
| Challenge: | Existing block-wise discrete diffusion models lack robust autoregressive (AR) decoders. |
| Approach: | They propose a block-wise discrete diffusion framework for large-scale vision-language understanding with a progressive beta noise curriculum. |
| Outcome: | The proposed framework improves training efficiency, convergence stability, and task performance over conventional block diffusion. |
On the token distance modeling ability of higher RoPE attention dimension (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on extending the context length of language models based on Rotary position embedding (RoPE) has shown promising results in capturing longer-range contextual information. |
| Approach: | They propose to use a hidden dimension of an attention head to investigate its contribution to capturing long-distance dependencies. |
| Outcome: | The proposed model can capture long-distance dependencies by extending the attention of a particular dimension of an attention head. |
MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making (2024.emnlp-main)
Copied to clipboard
| Challenge: | Insight is a form of long-term memory for an agent but lack of general insight can undermine its effectiveness. |
| Approach: | They propose an embodied agent that summarises and utilizes insight effectively across different scales and generates task-specific and high-level insight, stores it in a database, and then uses relevant insight from it. |
| Outcome: | The proposed agent outperforms a similar agent when planning by GPT3.5 and is more robust when faced with domain-shifting scenarios. |
Graph Counselor: Adaptive Graph Exploration via Multi-Agent Synergy to Enhance LLM Reasoning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for enhancing LLM reliability suffer from inefficient information aggregation and rigid reasoning schemes. |
| Approach: | They propose a method that explicitly models external knowledge integration capabilities by explicitly modeling knowledge relationships. |
| Outcome: | The proposed method outperforms existing methods in multiple graph reasoning tasks. |
A Survey of Inductive Reasoning for Large Language Models (2026.acl-long)
Copied to clipboard
Kedi Chen, Dezhao Ruan, Yuhao Dan, Yaoting Wang, Siyu Yan, Xuecheng Wu, Yinqi Zhang, Qin Chen, Jie Zhou, Liang He, Biqing Qi, Linyang Li, Qipeng Guo, Xiaoming Shi, Wei Zhang
| Challenge: | Inductive reasoning is an important task for large language models (LLMs). |
| Approach: | They propose a survey of inductive reasoning for large language models . they categorize methods into three main areas: post-training enhancement, test-time exploration, and data augmentation. |
| Outcome: | The proposed method improves inductive reasoning in large language models. |
SMR: State Memory Replay for Long Sequence Modeling (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing state space models (SSMs) address non-uniform sampling, but their recursive structures impede efficient SSM computation via convolution. |
| Approach: | They propose a plug-and-play mechanism to solve the Non-Stable State problem by adjusting input sequences with early memories. |
| Outcome: | The proposed method overcomes the non-uniform sample processing problem . it can achieve Sampling Step Adaptation (SSA) by adjusting input sequences with early memories. |
CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model (2023.emnlp-main)
Copied to clipboard
| Challenge: | Instruction tuning is an effective way of aligning large language models with private instruction data. |
| Approach: | They propose a training-free strategy to derive improved emulators from LLMs by using Offsite-Tuning (OFT) they propose CRaSh, which transfers transformer blocks between centralized LLM and downstream emulators . |
| Outcome: | The proposed technique boosts performance of large language models with billions of parameters. |
Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism (2026.acl-long)
Copied to clipboard
Yuhua Jiang, Shuang Cheng, Yihao Liu, Ermo Hua, Che Jiang, Weigao Sun, Yu Cheng, Feifei Gao, Biqing Qi, Bowen Zhou
| Challenge: | Existing models lack task-guided specialized memory mechanisms . specialized generalist models excel at general language tasks but struggle in specialized domains. |
| Approach: | They propose a specialized generalist model with specialized memory and updater that can optimize for specialized domains. |
| Outcome: | The proposed model matches or surpasses baselines on general benchmarks and achieves lowest perplexity across specialized domains. |