Salesforce's CLIFT turns sparse judge feedback into rewards for open-source web agents
Salesforce · hf · 2026-10-16
Salesforce AI Research released CLIFT (arXiv:2610.06829), using conformal self-verification to address sparse judge feedback in web agent training.
- Training: learns what to verify, maintaining a certified question bank (e.g. target reached? correct page? task completed? — with URL scope, polarity and trust weight) that converts sparse judge feedback into denser, reusable training rewards.
- Test time: enables judge-free trajectory selection (test-time scaling) based on reusable verification evidence.
- Targets open-source web agents: denser feedback for training, better trajectories for selection, reusable evidence for transfer.
More from coding & agent
- OpenAI Astra tutorial shows PolyHaven-powered 3D scenes as GPT-6 docs page surfaces — jason_mayes · 2026-10-16
- 10 GitHub repos to see what your AI agent really did, from Langfuse to claude-code-log — victor_explore · 2026-10-16
- Mosaic: multi-session agentic RL with hierarchical advantage estimation — LARK-Lab · 2026-10-16
- Recursive Environment Scaling tanks six models' success rates by 57–77 points — Lingxiao Jing · 2026-10-16
- Harvard's MPT: decentralized agent swarms learn self-orchestration via bidding — Harvard · 2026-10-16
- How LiteLLM routes one OpenAI-shaped API across every model provider — Mahmoud_Zalt · 2026-10-16