Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Paper • 2605.30621 • Published May 28 • 22
Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Paper • 2605.30621 • Published May 28 • 22
Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams Paper • 2606.01770 • Published Jun 1 • 11
Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Paper • 2605.30621 • Published May 28 • 22
MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution Paper • 2603.18718 • Published Mar 19 • 9
MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution Paper • 2603.18718 • Published Mar 19 • 9
MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution Paper • 2603.18718 • Published Mar 19 • 9
Unnoticeable Backdoor Attacks on Graph Neural Networks Paper • 2303.01263 • Published Feb 11, 2023 • 1
Protap: A Benchmark for Protein Modeling on Realistic Downstream Applications Paper • 2506.02052 • Published Jun 1, 2025
Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation Paper • 2511.02303 • Published Nov 4, 2025 • 1
How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool Use Paper • 2602.00528 • Published Jan 31