ClawEnvKit: Automatic Environment Generation for Claw-Like Agents
Paper • 2604.18543 • Published • 31
AstroAI
-
-
Near-Future Policy Optimization
Paper • 2604.20733 • Published • 77 -
Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
Paper • 2604.20987 • Published • 22 -
PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering
Paper • 2602.23161 • Published -
Hybrid Policy Distillation for LLMs
Paper • 2604.20244 • Published • 13 -
ClawGym: A Scalable Framework for Building Effective Claw Agents
Paper • 2604.26904 • Published • 55 -
Heterogeneous Scientific Foundation Model Collaboration
Paper • 2604.27351 • Published • 223 -
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
Paper • 2605.03042 • Published • 150 -
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
Paper • 2605.06130 • Published • 117 -
SkillOS: Learning Skill Curation for Self-Evolving Agents
Paper • 2605.06614 • Published • 48 -
MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning
Paper • 2605.13037 • Published • 8 -
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation
Paper • 2605.10813 • Published • 17 -
Self-Distilled Agentic Reinforcement Learning
Paper • 2605.15155 • Published • 118 -
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
Paper • 2605.10912 • Published • 47 -
Orchard: An Open-Source Agentic Modeling Framework
Paper • 2605.15040 • Published • 21 -
Nexus : An Agentic Framework for Time Series Forecasting
Paper • 2605.14389 • Published • 6 -
Code as Agent Harness
Paper • 2605.18747 • Published • 227 -
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
Paper • 2605.20025 • Published • 192 -
Toto 2.0: Time Series Forecasting Enters the Scaling Era
Paper • 2605.20119 • Published • 40 -
π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
Paper • 2605.14678 • Published • 109 -
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Paper • 2605.23904 • Published • 265 -
SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research
Paper • 2605.22878 • Published • 61 -
Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement
Paper • 2605.26952 • Published • 16 -
AI Research Agents Narrow Scientific Exploration
Paper • 2605.27905 • Published • 26 -
Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents
Paper • 2605.28775 • Published • 38 -
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
Paper • 2605.31264 • Published • 132 -
SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
Paper • 2606.01311 • Published • 38 -
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
Paper • 2605.30611 • Published • 254 -
EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
Paper • 2606.13662 • Published • 32 -
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
Paper • 2606.12191 • Published • 72 -
Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories
Paper • 2606.11176 • Published • 133 -
AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation
Paper • 2607.00052 • Published • 7 -
SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
Paper • 2607.03451 • Published • 35 -
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
Paper • 2607.08964 • Published • 77 -
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement
Paper • 2607.23802 • Published • 106 -
OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents
Paper • 2608.05013 • Published • 37 -
DarwinX: Evolving Agent Harnesses Through Natural Selection
Paper • 2608.07545 • Published • 113 -
Agent Lightning v1.0: Towards Harnessed Agentic RL
Paper • 2608.17528 • Published • 32 -
Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements
Paper • 2608.17310 • Published • 107 -
SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?
Paper • 2608.19799 • Published • 65 -
Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence
Paper • 2608.21156 • Published • 63 -
Apodex 1.1: Scaling Agentic Intelligence for Complex Work
Paper • 2608.23283 • Published • 205 -
Prime Agent: A Self-Improving RLM Harness
Paper • 2608.23552 • Published • 48 -
PaperGym: Rubric-Centered Evolution for Research-Plan Generation
Paper • 2608.31119 • Published • 37