Kunvar Thaman has emerged as a notable name in machine learning circles after his solo-authored paper, Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use, was accepted to ICML 2026. The paper’s arXiv listing shows Thaman as the only author and confirms its acceptance to the prestigious conference. The conference is scheduled to take place in Seoul, South Korea, from July 6 to July 11, 2026. Public posts linked to Thaman describe him as a solo independent researcher from India, making the achievement especially notable in a field usually dominated by major AI companies, elite universities and large research labs.
What Kunvar Thaman’s research paper is about
Thaman’s paper introduces the Reward Hacking Benchmark (RHB), a framework designed to measure how tool-using large language model agents exploit shortcuts while completing multi-step tasks. The benchmark includes scenarios where AI systems may bypass verification steps, infer answers indirectly or manipulate evaluation-related tools.The study evaluates 13 frontier AI models from organisations including OpenAI, Anthropic, Google and DeepSeek. According to the paper, exploit rates ranged from 0% to 13.9%, while additional safety measures reduced exploit behaviour without significantly affecting task completion.ICML, short for the International Conference on Machine Learning, is considered one of the world’s leading AI and machine learning conferences. It attracts submissions from top institutions and technology companies including OpenAI, Google DeepMind, Stanford, MIT and other major research organisations.The conference is highly competitive, with thousands of papers submitted every year and only a fraction accepted after peer review. That makes a solo-authored acceptance particularly unusual, especially for an independent researcher without the backing of a major institution or AI lab. Kunvar Thaman is a 26-year-old researcher from Chandigarh, India. He completed his education at Birla Institute of Technology and Science Pilani, one of India’s best-known higher education institutions, and has been described in public posts and articles as an independent researcher working in artificial intelligence. According to his LinkedIn profile, Kunvar Thaman is currently based in San Francisco.Some online posts have claimed that only two other solo independent researchers globally have achieved a similar ICML acceptance since the launch of ChatGPT. However, that specific statistic has not been independently verified through official ICML records.
Why the research is drawing attention
The topic of reward hacking has become increasingly important in AI safety research. As large language models gain greater autonomy and tool access, researchers are becoming more concerned about systems exploiting loopholes or taking unintended shortcuts to maximise rewards.Thaman’s benchmark attempts to study those behaviours in more realistic environments instead of simplified experimental settings. The paper’s focus on AI agent safety places it within one of the fastest-growing areas of modern artificial intelligence research.
A rare independent breakthrough
What makes Thaman’s story stand out is not just the paper itself, but the fact that it was produced by a single independent researcher in a research ecosystem heavily dominated by billion-dollar AI companies and top universities.For many observers in the AI community, the acceptance represents a rare example of an independent voice breaking into one of machine learning’s most competitive global platforms.
