Web$hell unifies agentic web access in one interface, matching benchmarks at lower cost
yonsei-dli · hf · 2026-10-14
Yonsei University researchers present Web$hell, a unified interface for agentic web access that merges the strengths of search-augmented, browser-based, and filesystem-based agents.
- Existing access models support either broad information gathering or browser interaction — combining them incurs substantial cost or performance trade-offs
- WebContract defines a common schema; WebCompiler compiles live webpages into addressable information and action objects, maintained in WebCache and handled through a shared operation set
- Agents can gather information, perform browser actions, and revisit evidence within a single trajectory
Across web search, navigation, and deep research benchmarks, Web$hell achieves strong task performance at lower cost, showing that interface design is a key lever for capable and efficient LLM agents on the web.
More from coding & agent
- Index Network open-sources Social Discovery Protocol: agents negotiate fit on your behalf — carsonfarmer · 2026-10-23
- Installed a formal-verification skill: it silently installed Java, MacBook runs 10 degrees hotter — zealcaiden · 2026-10-23
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- Ruff author warns: upgrade Node/Bun now — --use-system-ca still accepts the eMudhra cert — charliermarsh · 2026-10-23
- Proof of Agent: paste one prompt and your AI mines, grades, and self-governs — adamamcbride · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23