NeuroGenesysThe research we build on.
1,514 papers by other researchers that our work cites, from continual learning and verification to language models, agents and hardware. Each entry links to the paper on arXiv and to where we use it. 301 are cited on published pages of this site; the rest in the research notes behind our studies. Our own papers are in the archive.
- 2026-09arXiv 2609.09776Proof-Carrying Cognition: Closing the Verification Gap with Reality-Settled Reward
Eshwar Reddy M, Sourav Karmakar · AI & agents
Frontier gains in language-model reasoning come from reinforcement learning on reasoning traces and are concentrated in domains with a cheap, sound verifier. We argue the field's binding constraint is the verification gap: no scalable, incorruptible reward for reasoning outside formal domains.
- 2026-08arXiv 2608.08002Evaluator Ensembles Under Reward Hacking: Covariance Geometry and Finite-Search Guarantees
Fariya Afrin, Ibne Farabi Shihab · Machine learning
Language-model judges and reward models enable scalable supervision, but finite optimization can exploit evaluator errors rather than improve response quality. We characterize this failure through the covariance geometry of evaluator ensembles.
- 2025-07arXiv 2507.08794One Token to Fool LLM-as-a-Judge
Yulai Zhao, Haolin Liu, Dian Yu et al. · Machine learning
Large language models (LLMs) are increasingly trusted as automated judges, assisting evaluation and providing reward signals for training other models, particularly in reference-based settings like Reinforcement Learning with Verifiable Rewards (RLVR).
- 2025-03arXiv 2503.21878Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
Audrey Huang, Adam Block, Qinghua Liu et al. · AI & agents
Inference-time computation offers a powerful axis for scaling the performance of language models. However, naively increasing computation in techniques like Best-of-N sampling can lead to performance degradation due to reward hacking.
- 2025-02arXiv 2502.18581Scalable Best-of-N Selection for Large Language Models via Self-Certainty
Zhewei Kang, Xuandong Zhao, Dawn Song · Language models & NLP
Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models (LLMs) through increased test-time computation. Current state-of-the-art methods often employ computationally intensive reward models for response evaluation and selection.
- 2024-11arXiv 2411.17501The Limits of Inference Scaling Through Resampling
Benedikt Stroebl, Sayash Kapoor, Arvind Narayanan · Machine learning
Recent research has generated hope that inference scaling, such as resampling solutions until they pass verifiers like unit tests, could allow weaker models to match stronger ones.
- 2022-10arXiv 2210.10760Scaling Laws for Reward Model Overoptimization
Leo Gao, John Schulman, Jacob Hilton · Machine learning
In reinforcement learning from human feedback, it is common to optimize against a reward model trained to predict human preferences. Because the reward model is an imperfect proxy, optimizing its value too much can hinder ground truth performance, in accordance with Goodhart's law.
Cited inReal judges did not break Best-of-N at N ≤ 32, and measured ε did not predict the budgetThurstone Bounds Best-of-N: A 1927 Identity, Calibrated for Modern VerifiersStudy: Generational competitive continual learningStudy: Genesys program prior artInternal notesStudy: Judge exploitability on real Best-of-NStudy: Logical coherence of LLM world modelsStudy: Stopping confident wrong expert votes - 2021-10arXiv 2110.14168Training Verifiers to Solve Math Word Problems
Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian et al. · Machine learning
State-of-the-art language models can match human performance on many tasks, but they still struggle to robustly perform multi-step mathematical reasoning.5K high quality linguistically diverse grade school math word problems.
Built from every arXiv paper cited in our papers, posts, topic hubs, reports and research notes, with titles, authors, dates and abstracts from the arXiv API (updated 2026-11-12). Summaries are the opening sentences of each paper's own abstract, not our assessment; a citation means we used or checked the work, not that we endorse it. Fields follow each paper's primary arXiv category. Papers cited only outside arXiv (journals, proceedings) are not listed yet. Entries are generated from our citations, so a mistyped ID in a note would list the wrong paper; we remove those as we find them. Report a wrong entry.
