7 papers
Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing
Yutong Yin, Mingyu Jin, Jin Pan +12
Test-time scaling improves language-model reasoning, but existing approaches often face a difficult trade-off: long chain-of-thought sampling remains single-threaded, while sentenc…
AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent
Weidi Luo, Qiming Zhang, Yihao Quan +5
Coding agents based on large language models (LLMs) demonstrate remarkable autonomous capabilities, but they also introduce significant safety and misuse risks during multi-turn in…
All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs
Xi Chen, Mingyu Jin, Jingcheng Niu +7
In this paper, we present empirical and theoretical evidence against a central but largely implicit assumption in circuit and sheaf discovery (CSD), which we term the Functional An…
Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs
Mingyu Jin, Yutong Yin, Jingcheng Niu +7
In this work, we investigate how Large Language Models (LLMs) adapt their internal representations when encountering inputs of increasing difficulty, quantified as the degree of ou…
SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models
Jiaojiao Han, Wujiang Xu, Mingyu Jin +1
Large language models (LLMs) have achieved remarkable progress, yet their internal mechanisms remain largely opaque, posing a significant challenge to their safe and reliable deplo…
EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning
Wujiang Xu, Wentian Zhao, Zhenting Wang +6
Training LLM agents in multi-turn environments with sparse rewards, where completing a single task requires 30+ turns of interaction within an episode, presents a fundamental chall…