ABF-Bench: a verifiable benchmark for agentic blockchain forensics from Imperial College
ImperialCollegeLondon · hf · 2026-10-31
Researchers at Imperial College London and Oxford introduce ABF-Bench, an interactive, verifiable benchmark for agentic blockchain fund tracing. Agents must cite retrieved ledger records for every claimed fund movement; a case-to-task pipeline builds well-posed tasks across ledgers. Evaluations reveal gaps in recall and overconfidence of adaptive agents versus fixed tracers, and the setup enables verifiable LLM agent training.
More from Research
- Professor runs Pangram on 50 pre-ChatGPT self-published novels: zero false positives — TuhinChakr · 2026-10-31
- Researchers push back on Samuelson brief with Pangram audit: 0.04% false positives — TuhinChakr · 2026-10-31
- Stanford's TaskNet builds occupational task inventories from worker interviews at scale — stanfordnlp · 2026-10-31
- AI cracks a 27-year-old pillar of computer science, OpenAI and Anthropic claim — Fcking_Chuck · 2026-10-31
- Aligning image and text embeddings without paired data: Wasserstein Procrustes and rotation papers — phillip_isola · 2026-10-31
- Phillip Isola demos aligning image and text embeddings with just a single rotation — phillip_isola · 2026-10-31