Large language models have evolved from single-turn chatbots into interactive agents capable of long-horizon reasoning. In real deployments, MCP tool services can return noisy feedback and users may intervene to correct the agent, but existing methods provide limited supervision for reflection learning and failure recovery.
ORIGINAL PAPER
Agent-Reflex: Teaching Language Agents to Act Reflectively
WHAT WE KNOW
To bridge this gap, we propose Agent-Reflex, a general training framework for incentivizing proactive reflection in agents. Specifically, Agent-Reflex comprises three stages. First, Environment Reflection Skill Discovery (RSD) injects grounded tool-feedback perturbations into environment scaling, samples a capability-diverse LLM pool, mines matched success-failure pairs, and summarizes reusable reflection meta-skills.
WATCH NEXT
Review the primary source, validate the main result, and establish whether any listed-company transmission is direct.
EVIDENCE
What the evidence supports so far
Research signals
agent
reasoning
training-method
What remains unverified
The full methodology, effect size, and limitations still require analyst review.
Company impact remains unverified until a direct economic transmission is established.