2 papers
cs.CL2026
AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents
Zhaopeng Feng, Liangcai Su, Zhen Zhang +16
As large language models (LLMs) evolve into autonomous agents for long-horizon information-seeking, managing finite context capacity has become a critical bottleneck. Existing cont…
q-fin.GN2026
A Financial Brain Scan of the LLM
Hui Chen, Antoine Didisheim, Mohammad +3
Emerging techniques in computer science make it possible to "brain scan" large language models (LLMs), identify the plain-English concepts that guide their reasoning, and steer the…