SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
Paper • 2606.13673 • Published • 80
GuoLiangTang
Tommy930
AI & ML interests
LLM，NLP，ML
Recent Activity
upvoted a paper 1 day ago
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning upvoted a paper 1 day ago
InterleaveThinker: Reinforcing Agentic Interleaved Generation upvoted a paper 1 day ago
TreeSeeker: Tree-Structured Trial, Error, and Return in Deep SearchOrganizations
None yet
upvoted 20
papers 1 day ago
InterleaveThinker: Reinforcing Agentic Interleaved Generation
Paper • 2606.13679 • Published • 74
TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search
Paper • 2606.11662 • Published • 10
EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
Paper • 2606.13662 • Published • 21
LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories
Paper • 2606.13578 • Published • 52
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces
Paper • 2606.09426 • Published • 94
MiniMax Sparse Attention
Paper • 2606.13392 • Published • 99
MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling
Paper • 2606.13473 • Published • 73
FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents
Paper • 2606.12087 • Published • 71
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
Paper • 2606.13681 • Published • 117
RepWAM: World Action Modeling with Representation Visual-Action Tokenizers
Paper • 2606.13674 • Published • 5
DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch
Paper • 2606.10728 • Published • 31
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Paper • 2606.11926 • Published • 106
SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference
Paper • 2606.04511 • Published • 3
i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models
Paper • 2606.11289 • Published • 8
Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization
Paper • 2606.12373 • Published • 7
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models
Paper • 2606.11324 • Published • 10
EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
Paper • 2606.03108 • Published • 11
TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning
Paper • 2606.11119 • Published • 17
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
Paper • 2606.12370 • Published • 20