1 citations · 2 across the 5 of their papers we have counts for
3 papers · 1 filter
Reward-Free Evolving Agents via Pairwise Validator
Minghao Liu, Yu Wang, Jiayun Wang +1
A self-evolving agentic loop repeatedly proposes a tweaked version of an agent (its prompt template or program) and accepts or rejects the change based on a per-iteration quality s…
CacheRL:Multi-Turn Tool-Calling Agents via Cached Rollouts and Hybrid Reward
Md Amirul Islam, Sumiran Thakur, Huancheng Chen +3
We present CacheRL, a system for training small agent foundation models that achieves 92 percent process accuracy on multi-step tool-calling tasks, approaching GPT-5's 94 percent w…
Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory
Zhenting Wang, Huancheng Chen, Jiayun Wang +1
Large language model (LLM) agents are fundamentally bottlenecked by finite context windows on long-horizon tasks. As trajectories grow, retaining tool outputs and intermediate reas…