Story

arxiv_agent_systems_research ยท Nov 11, 2026 ยท paper

Source brief

Knowledge in the Harness, Reliability in the Weights: Teacher-Free Co-Evolution of an LLM Agent

arxiv.orgNov 11, 2026
original source linked

In brief

Small open models suit private customer-service deployments but trail frontier models in two ways: they miss what the written policy requires in a given situation, and they act inconsistently on what they know. We stu...

Feed lens
agentharness

Continue reading

Read the original at arxiv.org โ†’Open in live feedRead that dayโ€™s brief

Earlier in this thread 4 items