7 papers
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
NeoHorse Team, Guoliang Cao, Guohao Dai +34
Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and converts that evidence into the next round of learning. We p…
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
Mengyu Zheng, Kai Han, Boxun Li +13
The software engineering capabilities of general-purpose agent harnesses remain underexplored, and existing benchmarks offer limited support for comparing these harnesses under con…
Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory
Suozhao Ji, Baodong Wu, Zehao Wang +8
Long-term LLM agents need persistent memory that can track changing facts and provide relevant evidence across sessions. Existing memory systems often store observations as isolate…
Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation
Haozhan Tang, Xiuqi Zhu, Xinyin Zhang +3
Recent literature on fine-tuning Large Language Models highlights a fundamental debate. While Full Fine-Tuning (FFT) provides greater representational plasticity, Low-Rank Adaptati…
DynaTrain: Fast Online Parallelism Switching for Elastic LLM Training
Yuanqing Wang, Yuchen Zhang, Hao Lin +9
Modern large language model (LLM) training is inherently dynamic: resource fluctuations, RLHF phase shifts, and cluster elasticity continually reshape the optimal parallelism layou…
EARL: Efficient Agentic Reinforcement Learning Systems for Large Language Models
Zheyue Tan, Mustapha Abdullahi, Tuo Shi +5
Reinforcement learning (RL) has become a pivotal component of large language model (LLM) post-training, and agentic RL extends this paradigm to operate as agents through multi-turn…
MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs
Huining Yuan, Zelai Xu, Zheyue Tan +10
Developing Large Language Models (LLMs) to cooperate and compete effectively within multi-agent systems (MASs) is a critical step towards more advanced intelligence. While reinforc…