Newest papers

Propose, Don't Judge: An Anytime-Valid Referee for LLM Agents That Mine Investment Factors

Bo Qu, Mingguang Chen, Licheng Wang · 2026 · arXiv

DOI: 10.48550/arXiv.2609.27051 · open-access PDF

Hindi

भाषा मॉडल एजेंट अब पूरी मात्रात्मक कारक अनुसंधान चलाते हैं: वे निवेश कारकों की पेशकश करते हैं, उन्हें बैकटेस्ट करते हैं, जीवित रहने वालों को चुनते हैं और उन्हें सेवानिवृत्त करते हैं। हम पूछते हैं कि उन नौकरियों में से एक एजेंट को क्या रखना चाहिए। हमारा जवाब आत्म-विकास को नियंत्रित करता है: एजेंट प्रस्ताव कर सकता है, और एक ठंडा सांख्यिकीय न्यायाधीश जो एजेंट स्पर्श नहीं कर सकता है, निर्णय कर सकता है।

Machine translation (Meta M2M100); the English original follows.

Abstract

Language-model agents now run the whole of quantitative factor research: they propose investment factors, backtest them, select the survivors and retire them. We ask which of those jobs an agent should keep. Our answer is governed self-evolution: the agent may propose, and a frozen statistical referee that the agent cannot touch must judge. The referee scores each candidate only on market outcomes revealed after submission, by betting, so its false-discovery guarantee holds at every stopping time for any proposal policy. We cross three proposers (a script, a bandit and a language model) with t

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2609.27051, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange