Web Agent

The Green Agent utilizes the WebJudge framework—an 'LLM-as-a-judge' system designed to replace unreliable pass/fail metrics. It identifies critical task requirements, filters for relevant screenshots of the agent's progress, and makes a final success judgment based on action history. This system evaluates agents against the Online-Mind2Web benchmark, which consists of 300 tasks across 136 real-world websites. The diversity of the benchmark suggests that our Green Agent can effectively act as a reward model or evaluator for tasks it has never seen before in the area of web browsing tasks.

green agent evaluates WebShop shopping tasks in a text‑only Gym environment. It orchestrates episodes by resetting the environment, sending observations to the purple agent, executing returned actions (search/click/buy), and collecting programmatic rewards. It reports structured JSON artifacts containing total reward, success, and per‑step traces. This provides a reproducible benchmark for instruction following in e‑commerce search and product selection without an LLM judge.

Enhanced Purple Agent for tau2-Bench with ReAct reasoning and 100% pass rate on airline domain.

AgentX Phase 2 Computer Use & Web Agent Track. Reflexive Agent Architecture for WebShop+ (budget management, preference memory, negative constraints, comparative reasoning, error recovery, cart management, checkout).