12 papers
SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?
Yuqiao Tan, Shizhu He, Jun Zhao +1
While research on recursive self-improvement (RSI) has predominantly automated model training pipelines, reliable autonomous development demands a missing pillar: post-hoc monitori…
SWE-Touch: Benchmarking Coding Agents When Users Touch the Code
Yuqiao Tan, Jinxiang Meng, Fangyu Lei +4
Real-world software development requires coding agents to operate in shared workspaces where users may inspect and modify code during an ongoing task, yet existing repository-level…
Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering
Chengfeng Zhao, Yuqiao Tan, Shizhu He +3
While Large Language Models (LLMs) excel as static solvers, transforming them into autonomous agents remains challenging. This transition requires continuous environmental interact…
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents
Minzheng Wang, Run Luo, Yanbo Wang +6
While Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for closed-ended tasks, extending it to open-ended social language games via self-play reveals a cr…
From to : Investigating Reinforcement Learning in Pre-train Space
Yuqiao Tan, Minzheng Wang, Bo Liu +5
While reinforcement learning with verifiable rewards (RLVR) significantly enhances LLM reasoning by optimizing the conditional distribution P(y|x), its potential is fundamentally b…
ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning
Huanxuan Liao, Zhongtao Jiang, Yupu Hao +6
Multimodal Large Language Models (MLLMs) achieve stronger visual understanding by scaling input fidelity, yet the resulting visual token growth makes jointly sustaining high spatia…
Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies
Yuqiao Tan, Minzheng Wang, Shizhu He +6
Existing reinforcement learning (RL) approaches treat large language models (LLMs) as a unified policy, overlooking their internal mechanisms. In this paper, we decompose the LLM-b…
The Zero-Step Thinking: An Empirical Study of Mode Selection as Harder Early Exit in Reasoning Models
Yuqiao Tan, Shizhu He, Kang Liu +1
Reasoning models have demonstrated exceptional performance in tasks such as mathematics and logical reasoning, primarily due to their ability to engage in step-by-step thinking dur…
Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models
Yuqiao Tan, Shizhu He, Kang Liu +1
Large Language Models (LLMs) offer a transparent brain with accessible parameters that encode extensive knowledge, which can be analyzed, located and transferred. Consequently, a k…
Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement
Yuqiao Tan, Shizhu He, Huanxuan Liao +2
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources and incorporating them into the context. While it…
MuAP: Multi-step Adaptive Prompt Learning for Vision-Language Model with Missing Modality
Ruiting Dai, Yuqiao Tan, Lisi Mo +3
Recently, prompt learning has garnered considerable attention for its success in various Vision-Language (VL) tasks. However, existing prompt-based models are primarily focused on…
G-SAP: Graph-based Structure-Aware Prompt Learning over Heterogeneous Knowledge for Commonsense Reasoning
Ruiting Dai, Yuqiao Tan, Lisi Mo +4
Commonsense question answering has demonstrated considerable potential across various applications like assistants and social robots. Although fully fine-tuned pre-trained Language…