Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Bayesian Optimality of In-Context Learning with Selective State Spaces
Di Zhang, Jiaqi Xing
We propose Bayesian optimal sequential prediction as a new principle for understanding in-context learning (ICL). Unlike interpretations framing Transformers as performing implicit…
cs.LG2026
Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity
Di Zhang, Ningxu Zhang, Zimeng Liu
In-context learning (ICL) allows large language models to adapt to new tasks from a few examples without updating their parameters. Existing theories explain ICL by assuming the te…
cs.AI2026
AgentDevel: Reframing Self-Evolving LLM Agents as Release Engineering
Di Zhang
Recent progress in large language model (LLM) agents has largely focused on embedding self-improvement mechanisms inside the agent or searching over many concurrent variants. While…