An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding the frozen backbone model. Recent methods increasingly automate this process by iteratively proposing and selecting component-wise edits of an agent harness, practically e...
Peng Xia, Ru-Jun Han, Zifeng Wang et al.· 4 citations· ⚡1
An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding the frozen backbone model. Recent methods increasingly automate this process by iteratively proposing and selecting component-wise edits of an agent harness, practically e...
Peng Xia, Ru-Jun Han, Zifeng Wang et al.· 3 citations· ⚡1
Procedural Memory Distillation is proposed, which converts crossepisode signals into reusable procedural memory and distills it into the policy's weights during training, yielding a memory-free model at inference.
Ye Liu, Srijan Bansal, Bo Pang et al.· 2 citations
Environment Harness is proposed, a programmable layer of plug-in components that wraps a static environment to reshape its behavior without modifying the underlying logic, enabling continuous, targeted co-evolution of the policy and its environment.
Chengsong Huang, Zifeng Wang, Ru-Jun Han et al.· 11 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
