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 2609.09702Decision Shifts, Lost Label Functionality, and an Inconclusive Grounding Audit in Correctness-Gated Multi-Teacher Distillation
Xiaofei Feng · AI & agents
Candidate decision correctness and rationale grounding are different objectives. We examine correctness-gated multi-teacher distillation in a fixed experiment.
- 2026-09arXiv 2609.02548Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs
Xixiang He, Xingming Li, Baiqi Wu et al. · Machine learning
Modern large language models (LLMs) rely on reinforcement learning to build strong capabilities in individual domains, but integrating those capabilities into a single deployable model remains challenging.
- 2026-07arXiv 2607.07050When Top-K Misses the Decision: Tool-Call Drift in Multi-Teacher On-Policy Distillation
Jiabin Shen, Guang Chen, Chengjun Mao · Language models & NLP
Top- teacher logits make on-policy distillation tractable, but retained teacher mass does not certify student-relative gradient fidelity. We study routed, two-teacher tool-use distillation.
- 2026-06arXiv 2606.27374World Action Models Enable Continual Imitation Learning with Recurrent Generative Replays
Manish Kumar Govind, Dominick Reilly, Smit Patel et al. · Robotics & control
Going beyond predicting robot actions, World Action Models (WAMs) can also generate future visual observations.
- 2026-03arXiv 2603.15892Temporal Fact Conflicts in LLMs: Reproducibility Insights from Unifying DYNAMICQA and MULAN
Ritajit Dey, Iadh Ounis, Graham McDonald et al. · Retrieval & data
Large Language Models (LLMs) often struggle with temporal fact conflicts due to outdated or evolving information in their training data. Two recent studies with accompanying datasets report opposite conclusions on whether external context can effectively resolve such conflicts.
- 2026-03arXiv 2603.01409MIST-RL: Mutation-based Incremental Suite Testing via Reinforcement Learning
Sicheng Zhu, Jiajun Wang, Jiawei Ai et al. · AI & agents
Large Language Models (LLMs) often fail to generate correct code on the first attempt, which requires using generated unit tests as verifiers to validate the solutions.
- 2026-01arXiv 2601.21375TeachBench: A Syllabus-Grounded Framework for Evaluating Teaching Ability in Large Language Models
Zheng Li, Siyao Song, Jingyuan Ma et al. · AI & agents
Large language models (LLMs) show promise as teaching assistants, yet their teaching capability remains insufficiently evaluated. Existing benchmarks mainly focus on problem-solving or problem-level guidance, leaving knowledge-centered teaching underexplored.
- 2026-01arXiv 2601.13097RM -RF: Reward Model for Run-Free Unit Test Evaluation
Elena Bruches, Daniil Grebenkin, Mikhail Klementev et al. · Society, software & economics
We present RM-RF, a lightweight reward model for run-free evaluation of automatically generated unit tests.
- 2026-01arXiv 2601.05280Large Language Models are Shannon Lossy Compressors Not Solomonoff Induction Estimators: Self-improvement and Singularity Are Not Near Without Symbolic Model Synthesis
Hector Zenil, Abicumaran Uthamacumaran, Luan Ozelim · Statistics & theory
We connect two questions in Algorithmic Information Theory (AIT), Machine Learning (ML) and Artificial General Intelligence (AGI): whether LLMs estimate Solomonoff induction, and whether they can self-improve towards an AI Singularity.
- 2025-10arXiv 2510.19172When Facts Change: Probing LLMs on Evolving Knowledge with evolveQA
Nishanth Sridhar Nakshatri, Shamik Roy, Manoj Ghuhan Arivazhagan et al. · Language models & NLP
LLMs often fail to handle temporal knowledge conflicts--contradictions arising when facts evolve over time within their training data.
- 2025-08arXiv 2508.05004R-Zero: Self-Evolving Reasoning LLM from Zero Data
Chengsong Huang, Wenhao Yu, Xiaoyang Wang et al. · Machine learning
Self-evolving Large Language Models (LLMs) offer a scalable path toward super-intelligence by autonomously generating, refining, and learning from their own experiences.
- 2025-08arXiv 2508.03682Self-Questioning Language Models
Lili Chen, Mihir Prabhudesai, Katerina Fragkiadaki et al. · Machine learning
Can large language models improve without external data -- by generating their own questions and answers?, algebra word problems) and asking the model to generate its own questions.
- 2025-06arXiv 2506.24119SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
Bo Liu, Leon Guertler, Simon Yu et al. · AI & agents
Recent advances in reinforcement learning have shown that language models can develop sophisticated reasoning through training on tasks with verifiable rewards, but these approaches depend on human-curated problem-answer pairs and domain-specific reward engineering.
- 2025-06arXiv 2506.13045Continual Learning for Generative AI: From LLMs to MLLMs and Beyond
Haiyang Guo, Fanhu Zeng, Fei Zhu et al. · Machine learning
The rapid advancement of generative models has empowered modern AI systems to comprehend and produce highly sophisticated content, even achieving human-level performance in specific domains.
- 2025-06arXiv 2506.08388Reinforcement Learning Teachers of Test Time Scaling
Edoardo Cetin, Tianyu Zhao, Yujin Tang · Machine learning
Training reasoning language models (LMs) with reinforcement learning (RL) for one-hot correctness inherently relies on the LM being able to explore and solve its task with some chance at initialization.
- 2025-06arXiv 2506.03136Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning
Yinjie Wang, Ling Yang, Ye Tian et al. · Language models & NLP
We propose CURE, a novel reinforcement learning framework with a dedicated reward design that co-evolves coding and unit test generation capabilities based on their interaction outcomes, without any ground-truth code as supervision.
- 2025-05arXiv 2505.03335Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Andrew Zhao, Yiran Wu, Yang Yue et al. · Machine learning
Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning capabilities of large language models by learning directly from outcome-based rewards.
- 2025-03arXiv 2503.21227LLaVA-CMoE: Towards Continual Mixture of Experts for Large Vision-Language Models
Hengyuan Zhao, Ziqin Wang, Qixin Sun et al. · Language models & NLP
Mixture of Experts (MoE) architectures have recently advanced the scalability and adaptability of large language models (LLMs) for continual multimodal learning.
- 2025-02arXiv 2502.18940MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors
Jakub Macina, Nico Daheim, Ido Hakimi et al. · Language models & NLP
Evaluating the pedagogical capabilities of AI-based tutoring models is critical for making guided progress in the field. Yet, we lack a reliable, easy-to-use, and simple-to-run evaluation that reflects the pedagogical abilities of models.
- 2025-02arXiv 2502.03461Do Large Language Model Benchmarks Test Reliability?
Joshua Vendrow, Edward Vendrow, Sara Beery et al. · Machine learning
When deploying large language models (LLMs), it is important to ensure that these models are not only capable, but also reliable. Many benchmarks have been created to track LLMs' growing capabilities, however there has been no similar focus on measuring their reliability.
- 2025-02arXiv 2502.02671On Teacher Hacking in Language Model Distillation
Daniil Tiapkin, Daniele Calandriello, Johan Ferret et al. · Machine learning
Post-training of language models (LMs) increasingly relies on the following two stages: (i) knowledge distillation, where the LM is trained to imitate a larger teacher LM, and (ii) reinforcement learning from human feedback (RLHF), where the LM is aligned by optimizing a reward model.
- 2025-02arXiv 2502.01534Preference Leakage: A Contamination Problem in LLM-as-a-judge
Dawei Li, Renliang Sun, Yue Huang et al. · Machine learning
Large Language Models (LLMs) as judges and LLM-based data synthesis have emerged as two fundamental LLM-driven data annotation methods in model development.
- 2025-01arXiv 2501.17703Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate
Yubo Wang, Xiang Yue, Wenhu Chen · Language models & NLP
Supervised Fine-Tuning (SFT) is commonly used to train language models to imitate annotated responses for given instructions. In this paper, we propose Critique Fine-Tuning (CFT), a method more effective than SFT for reasoning tasks.
- 2025-01arXiv 2501.13453Spurious Forgetting in Continual Learning of Language Models
Junhao Zheng, Xidi Cai, Shengjie Qiu et al. · Machine learning
Recent advancements in large language models (LLMs) reveal a perplexing phenomenon in continual learning: despite extensive training, models experience significant performance declines, raising questions about task alignment and underlying knowledge retention.
- 2024-10arXiv 2410.21819Self-Preference Bias in LLM-as-a-Judge
Koki Wataoka, Tsubasa Takahashi, Ryokan Ri · Language models & NLP
Automated evaluation leveraging large language models (LLMs), commonly referred to as LLM evaluators or LLM-as-a-judge, has been widely used in measuring the performance of dialogue systems.
- 2024-10arXiv 2410.05229GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
Iman Mirzadeh, Keivan Alizadeh, Hooman Shahrokhi et al. · Machine learning
Recent advancements in Large Language Models (LLMs) have sparked interest in their formal reasoning capabilities, particularly in mathematics. The GSM8K benchmark is widely used to assess the mathematical reasoning of models on grade-school-level questions.
- 2024-07arXiv 2407.09435MUSCLE: A Model Update Strategy for Compatible LLM Evolution
Jessica Echterhoff, Fartash Faghri, Raviteja Vemulapalli et al. · AI & agents
Large Language Models (LLMs) are regularly updated to enhance performance, typically through changes in data or architecture. Within the update process, developers often prioritize improving overall performance metrics, paying less attention to maintaining compatibility with earlier model versions.
- 2024-07arXiv 2407.08351AutoBencher: Towards Declarative Benchmark Construction
Xiang Lisa Li, Farzaan Kaiyom, Evan Zheran Liu et al. · Language models & NLP
We present AutoBencher, a declarative framework for automatic benchmark construction, and use it to scalably discover novel insights and vulnerabilities of existing language models.
- 2024-06arXiv 2406.07515Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification
Yunzhen Feng, Elvis Dohmatob, Pu Yang et al. · Machine learning
Large Language Models (LLM) are increasingly trained on data generated by other LLM, either because generated text and images become part of the pre-training corpus, or because synthetized data is used as a replacement for expensive human-annotation.
- 2024-06arXiv 2406.04127Are We Done with MMLU?
Aryo Pradipta Gema, Joshua Ong Jun Leang, Giwon Hong et al. · Language models & NLP
Maybe not. We identify and analyse errors in the popular Massive Multitask Language Understanding (MMLU) benchmark. Even though MMLU is widely adopted, our analysis demonstrates numerous ground truth errors that obscure the true capabilities of LLMs.
- 2024-05arXiv 2405.15568OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code
Maxence Faldor, Jenny Zhang, Antoine Cully et al. · AI & agents
Open-ended and AI-generating algorithms aim to continuously generate and solve increasingly complex tasks indefinitely, offering a promising path toward more general intelligence.
- 2024-04arXiv 2404.13076LLM Evaluators Recognize and Favor Their Own Generations
Arjun Panickssery, Samuel R. Bowman, Shi Feng · Language models & NLP
Self-evaluation using large language models (LLMs) has proven valuable not only in benchmarking but also methods like reward modeling, constitutional AI, and self-refinement.
- 2024-04arXiv 2404.01413Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data
Matthias Gerstgrasser, Rylan Schaeffer, Apratim Dey et al. · Machine learning
The proliferation of generative models, combined with pretraining on web-scale data, raises a timely question: what happens when these models are trained on their own generated outputs?
- 2024-03arXiv 2403.18886Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning
Huiyi Wang, Haodong Lu, Lina Yao et al. · Machine learning
Continual learning (CL) aims to continually accumulate knowledge from a non-stationary data stream without catastrophic forgetting of learned knowledge, requiring a balance between stability and adaptability.
- 2024-03arXiv 2403.12958Dated Data: Tracing Knowledge Cutoffs in Large Language Models
Jeffrey Cheng, Marc Marone, Orion Weller et al. · Language models & NLP
Released Large Language Models (LLMs) are often paired with a claimed knowledge cutoff date, or the dates at which training data was gathered. Such information is crucial for applications where the LLM must provide up to date information.
- 2024-03arXiv 2403.01244Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal
Jianheng Huang, Leyang Cui, Ante Wang et al. · Language models & NLP
Large language models (LLMs) suffer from catastrophic forgetting during continual learning. Conventional rehearsal-based methods rely on previous training data to retain the model's ability, which may not be feasible in real-world applications.
- 2024-02arXiv 2402.12366A Critical Evaluation of AI Feedback for Aligning Large Language Models
Archit Sharma, Sedrick Keh, Eric Mitchell et al. · Machine learning
Reinforcement learning with AI feedback (RLAIF) is a popular paradigm for improving the instruction-following abilities of powerful pre-trained language models.
- 2024-02arXiv 2402.07043A Tale of Tails: Model Collapse as a Change of Scaling Laws
Elvis Dohmatob, Yunzhen Feng, Pu Yang et al. · ICML 2024 · Machine learning
As AI model size grows, neural scaling laws have become a crucial tool to predict the improvements of large models when increasing capacity and the size of original (human or natural) training data.
- 2024-02arXiv 2402.01830PiCO: Peer Review in LLMs based on the Consistency Optimization
Kun-Peng Ning, Shuo Yang, Yu-Yang Liu et al. · Language models & NLP
Existing large language models (LLMs) evaluation methods typically focus on testing the performance on some closed-environment and domain-specific benchmarks with human annotations.
- 2024-01arXiv 2401.10020Self-Rewarding Language Models
Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho et al. · Language models & NLP
We posit that to achieve superhuman agents, future models require superhuman feedback in order to provide an adequate training signal.
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.
