Exploration and Exploitation Errors Are Measurable for Language Model Agents
Paper • 2604.13151 • Published • 13
GuoLiangTang
Tommy930
AI & ML interests
LLM，NLP，ML
Recent Activity
upvoted a paper about 11 hours ago
Exploration and Exploitation Errors Are Measurable for Language Model Agents upvoted a paper about 11 hours ago
UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding upvoted a paper about 11 hours ago
TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based ExplorationOrganizations
None yet
upvoted 8
papers about 11 hours ago
UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding
Paper • 2604.14113 • Published • 8
TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration
Paper • 2604.14116 • Published • 7
TIP: Token Importance in On-Policy Distillation
Paper • 2604.14084 • Published • 9
SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments
Paper • 2604.14144 • Published • 60
OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models
Paper • 2604.10866 • Published • 45
GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents
Paper • 2604.07429 • Published • 105
Seedance 2.0: Advancing Video Generation for World Complexity
Paper • 2604.14148 • Published • 102
upvoted 12
papers 1 day ago
Generative Refinement Networks for Visual Synthesis
Paper • 2604.13030 • Published • 8
Accelerating Speculative Decoding with Block Diffusion Draft Trees
Paper • 2604.12989 • Published • 5
Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling
Paper • 2604.05072 • Published • 4
You Only Judge Once: Multi-response Reward Modeling in a Single Forward Pass
Paper • 2604.10966 • Published • 8
Towards Long-horizon Agentic Multimodal Search
Paper • 2604.12890 • Published • 16
Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
Paper • 2604.13010 • Published • 8
Lyra 2.0: Explorable Generative 3D Worlds
Paper • 2604.13036 • Published • 25
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
Paper • 2604.12374 • Published • 26
Rethinking the Diffusion Model from a Langevin Perspective
Paper • 2604.10465 • Published • 12
Toward Autonomous Long-Horizon Engineering for ML Research
Paper • 2604.13018 • Published • 28
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Paper • 2604.13016 • Published • 71
IceCache: Memory-efficient KV-cache Management for Long-Sequence LLMs
Paper • 2604.10539 • Published • 1