Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating
Paper • 2606.09068 • Published • 4
GuoLiangTang
Tommy930
AI & ML interests
LLM，NLP，ML
Recent Activity
Organizations
None yet
upvoted 18
papers 1 day ago
ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations
Paper • 2606.11188 • Published • 23
Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information Seeking
Paper • 2606.07689 • Published • 5
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts
Paper • 2606.05922 • Published • 52
Rethinking the Divergence Regularization in LLM RL
Paper • 2606.09821 • Published • 28
SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning
Paper • 2606.10804 • Published • 35
MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism
Paper • 2606.07512 • Published • 36
ABot-Earth 0.5: Generative 3D Earth Model
Paper • 2606.09967 • Published • 204
Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution
Paper • 2606.10917 • Published • 73
SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research
Paper • 2606.09730 • Published • 49
Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval
Paper • 2606.04391 • Published • 10
Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory
Paper • 2606.09365 • Published • 2
AsyncWebRL: Efficient Multi-Step RL for Visual Web Agents
Paper • 2606.05597 • Published • 4
DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning
Paper • 2606.07299 • Published • 6
Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill
Paper • 2606.03980 • Published • 13
LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents
Paper • 2606.06087 • Published • 59
SWE-Explore: Benchmarking How Coding Agents Explore Repositories
Paper • 2606.07297 • Published • 108
Agents' Last Exam
Paper • 2606.05405 • Published • 254
upvoted 2
papers 3 days ago