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.
- 2026-08arXiv 2609.27954When Accuracy Gaps Fail to Certify: Auditing Cross-Domain Recalibration of LLM Judges
Fariya Afrin, Ibne Farabi Shihab · Machine learning
A scalar recalibration map fitted for an LLM judge on one task can fail when the task distribution changes, but the source-target accuracy gap is often treated as a proxy for that failure.
- 2026-08arXiv 2608.08239The Replay Gap: Static Evaluation of Model Switching in LLM Agents Scores the Wrong World
Ashritha Gonuguntla · Machine learning
LLM routers promise efficiency by matching each request to the cheapest adequate model, and are increasingly applied per step inside multi-step agents.
- 2026-07arXiv 2607.09015Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing
Ajay Narayanan Sridhar, Ronak Singh, Mehrdad Mahdavi et al. · Machine learning
We study contextual bandit problems with correlated arms and access to surrogate reward signals produced by a machine learning model, motivated by applications such as large language model (LLM) routing.
- 2026-06arXiv 2606.24281CALIBER: Calibrating Confidence Before and After Reasoning in Language Models
Conor Finlay, Joshua Kurien, Saurabh Dash et al. · Language models & NLP
Reasoning language models are increasingly asked not only to answer difficult questions, but also to estimate their likelihood of success. Existing methods typically elicit confidence only once: either before thinking or after answering.
- 2026-06arXiv 2606.14929Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts
Yan Dai, Negin Golrezaei, Patrick Jaillet · Machine learning
Modern recommendation systems increasingly rely on dynamically routing diverse queries to multiple embedding models. Despite its practical significance, this problem remains poorly understood under realistic conditions like adversarial queries, bandit feedback, and limited observability of models.
- 2026-05arXiv 2605.07395Unsolvability Ceiling in Multi-LLM Routing: An Empirical Study of Evaluation Artifacts
Saloni Garg, Amit Sagtani · Machine learning
Efficient routing across multiple LLMs enables cost-quality tradeoffs by directing queries to the cheapest capable model. Prior work attributes routing headroom to an "unsolvability ceiling", queries no model in the pool can solve.
- 2026-03arXiv 2603.27481On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models
Chongyang Zhao, Mingsong Li, Haodong Lu et al. · Machine learning
Multimodal Continual Instruction Tuning aims to continually enhance Large Vision Language Models (LVLMs) by learning from new data without forgetting previously acquired knowledge.
- 2026-03arXiv 2603.01697DynaMoE: Dynamic Token-Level Expert Activation with Layer-Wise Adaptive Capacity for Mixture-of-Experts Neural Networks
Gökdeniz Gülmez · Machine learning
Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling neural networks while maintaining computational efficiency.
- 2026-02arXiv 2603.04445Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey
Yasmin Moslem, John D. Kelleher · Transactions on Machine Learning Research (TMLR). 2026 · Other
The rapid growth of large language models (LLMs) with diverse capabilities, costs, and domains has created a critical need for intelligent model selection at inference time.
- 2026-02arXiv 2602.00943Dynamic Prior Thompson Sampling for Cold-Start Exploration in Recommender Systems
Zhenyu Zhao, David Zhang, Ellie Zhao et al. · Machine learning
Cold-start exploration is a core challenge in large-scale recommender systems: new or data-sparse items must receive traffic to estimate value, but over-exploration harms users and wastes impressions.
- 2025-12arXiv 2512.22029LibContinual: A Comprehensive Library towards Realistic Continual Learning
Wenbin Li, Shangge Liu, Borui Kang et al. · Machine learning
A fundamental challenge in Continual Learning (CL) is catastrophic forgetting, where adapting to new tasks degrades the performance on previous ones. While the field has evolved with diverse methods, this rapid surge in diverse methodologies has culminated in a fragmented research landscape.
- 2025-12arXiv 2512.11150Causal Judge Evaluation: Calibrated Surrogate Metrics for LLM Systems
Eddie Landesberg, Manjari Narayan · Statistics & theory
Measuring long-run LLM outcomes (user satisfaction, expert judgment, downstream KPIs) is expensive. Teams default to cheap LLM judges, but uncalibrated proxies can invert rankings entirely.
- 2025-11arXiv 2511.18397Natural Emergent Misalignment from Reward Hacking in Production RL
Monte MacDiarmid, Benjamin Wright, Jonathan Uesato et al. · AI & agents
We show that when large language models learn to reward hack on production RL environments, this can result in egregious emergent misalignment.
- 2025-11arXiv 2511.09871Expandable and Differentiable Dual Memories with Orthogonal Regularization for Exemplar-free Continual Learning
Hyung-Jun Moon, Sung-Bae Cho · Machine learning
Continual learning methods used to force neural networks to process sequential tasks in isolation, preventing them from leveraging useful inter-task relationships and causing them to repeatedly relearn similar features or overly differentiate them.
- 2025-10arXiv 2510.21614Huxley-Gödel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine
Wenyi Wang, Piotr Piękos, Li Nanbo et al. · AI & agents
Recent studies operationalize self-improvement through coding agents that edit their own codebases.
- 2025-10arXiv 2510.00841LLM Routing with Dueling Feedback
Chao-Kai Chiang, Takashi Ishida, Masashi Sugiyama · Machine learning
We study LLM routing, the problem of selecting the best model for each query while balancing user satisfaction, model expertise, and inference cost.
- 2025-09arXiv 2509.11106Fluid Language Model Benchmarking
Valentin Hofmann, David Heineman, Ian Magnusson et al. · Language models & NLP
Language model (LM) benchmarking faces several challenges: comprehensive evaluations are costly, benchmarks often fail to measure the intended capabilities, and evaluation quality can degrade due to labeling errors and benchmark saturation.
- 2025-08arXiv 2508.09974Dynamic Mixture-of-Experts for Incremental Graph Learning
Lecheng Kong, Theodore Vasiloudis, Seongjun Yun et al. · Machine learning
Graph incremental learning is a learning paradigm that aims to adapt trained models to continuously incremented graphs and data over time without the need for retraining on the full dataset.
- 2025-06arXiv 2506.17670Online Multi-LLM Selection via Contextual Bandits under Unstructured Context Evolution
Manhin Poon, XiangXiang Dai, Xutong Liu et al. · Machine learning
Large language models (LLMs) exhibit diverse response behaviors, costs, and strengths, making it challenging to select the most suitable LLM for a given user query.
- 2025-05arXiv 2505.22954Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
Jenny Zhang, Shengran Hu, Cong Lu et al. · AI & agents
Today's AI systems have human-designed, fixed architectures and cannot autonomously and continuously improve themselves. The advance of AI could itself be automated.
- 2025-05arXiv 2505.22696When Does Neuroevolution Outcompete Reinforcement Learning in Transfer Learning Tasks?
Eleni Nisioti, Joachim Winther Pedersen, Erwan Plantec et al. · Machine learning
The ability to continuously and efficiently transfer skills across tasks is a hallmark of biological intelligence and a long-standing goal in artificial systems.
- 2025-05arXiv 2505.16037Causal LLM Routing: End-to-End Regret Minimization from Observational Data
Asterios Tsiourvas, Wei Sun, Georgia Perakis · AI & agents
LLM routing aims to select the most appropriate model for each query, balancing competing performance metrics such as accuracy and cost across a pool of language models.
- 2025-04arXiv 2504.20879The Leaderboard Illusion
Shivalika Singh, Yiyang Nan, Alex Wang et al. · AI & agents
Measuring progress is fundamental to the advancement of any scientific field. As benchmarks play an increasingly central role, they also grow more susceptible to distortion.
- 2025-04arXiv 2504.15228A Self-Improving Coding Agent
Maxime Robeyns, Martin Szummer, Laurence Aitchison · AI & agents
Recent advancements in Large Language Models (LLMs) have spurred interest in deploying LLM agents to undertake tasks in the world. LLMs are often deployed in agent systems: code that orchestrates LLM calls and provides them with tools.
- 2025-03arXiv 2503.11926Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
Bowen Baker, Joost Huizinga, Leo Gao et al. · AI & agents
Mitigating reward hacking--where AI systems misbehave due to flaws or misspecifications in their learning objectives--remains a key challenge in constructing capable and aligned models.
- 2025-02arXiv 2502.14855Prompt-to-Leaderboard
Evan Frick, Connor Chen, Joseph Tennyson et al. · Machine learning
Large language model (LLM) evaluations typically rely on aggregated metrics like accuracy or human preference, averaging across users and prompts. This averaging obscures user- and prompt-specific variations in model performance.
- 2025-02arXiv 2502.08773Universal Model Routing for Efficient LLM Inference
Wittawat Jitkrittum, Harikrishna Narasimhan, Ankit Singh Rawat et al. · Language models & NLP
Model routing is a simple technique for reducing the inference cost of large language models (LLMs), wherein one maintains a pool of candidate LLMs, and learns to route each prompt to the smallest feasible LLM.
- 2025-02arXiv 2502.06210Achieving Deep Continual Learning via Evolution
Aojun Lu, Junchao Ke, Chunhui Ding et al. · Machine learning
Deep neural networks, despite their remarkable success, remain fundamentally limited in their ability to perform Continual Learning (CL).
- 2025-02arXiv 2502.18482MixLLM: Dynamic Routing in Mixed Large Language Models
Xinyuan Wang, Yanchi Liu, Wei Cheng et al. · Language models & NLP
Large Language Models (LLMs) exhibit potential artificial generic intelligence recently, however, their usage is costly with high response latency.
- 2025-01arXiv 2501.18837Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Mrinank Sharma, Meg Tong, Jesse Mu et al. · Language models & NLP
Large language models (LLMs) are vulnerable to universal jailbreaks-prompting strategies that systematically bypass model safeguards and enable users to carry out harmful processes that require many model interactions, like manufacturing illegal substances at scale.
- 2024-12arXiv 2412.17188Hierarchically Gated Experts for Efficient Online Continual Learning
Kevin Luong, Michael Thielscher · Machine learning
Continual Learning models aim to learn a set of tasks under the constraint that the tasks arrive sequentially with no way to access data from previous tasks. The Online Continual Learning framework poses a further challenge where the tasks are unknown and instead the data arrives as a single stream.
- 2024-12arXiv 2412.16339Deliberative Alignment: Reasoning Enables Safer Language Models
Melody Y. Guan, Manas Joglekar, Eric Wallace et al. · Language models & NLP
As large-scale language models increasingly impact safety-critical domains, ensuring their reliable adherence to well-defined principles remains a fundamental challenge.
- 2024-12arXiv 2412.14093Alignment faking in large language models
Ryan Greenblatt, Carson Denison, Benjamin Wright et al. · AI & agents
We present a demonstration of a large language model engaging in alignment faking: selectively complying with its training objective in training to prevent modification of its behavior out of training.
- 2024-12arXiv 2412.03671Tight Lower Bounds and Improved Convergence in Performative Prediction
Pedram Khorsandi, Rushil Gupta, Mehrnaz Mofakhami et al. · Machine learning
Performative prediction is a framework accounting for the shift in the data distribution induced by the prediction of a model deployed in the real world.
- 2024-11arXiv 2411.02454Graph-based Confidence Calibration for Large Language Models
Yukun Li, Sijia Wang, Lifu Huang et al. · Language models & NLP
Reliable confidence estimation is essential for enhancing the trustworthiness of large language models (LLMs), especially in high-stakes scenarios. Despite its importance, accurately estimating confidence in LLM responses remains a significant challenge.
- 2024-11arXiv 2411.01111Rule Based Rewards for Language Model Safety
Tong Mu, Alec Helyar, Johannes Heidecke et al. · AI & agents
Reinforcement learning based fine-tuning of large language models (LLMs) on human preferences has been shown to enhance both their capabilities and safety behavior.
- 2024-09arXiv 2409.07431Synthetic continued pretraining
Zitong Yang, Neil Band, Shuangping Li et al. · Machine learning
Pretraining on large-scale, unstructured internet text enables language models to acquire a significant amount of world knowledge. However, this knowledge acquisition is data-inefficient--to learn a given fact, models must be trained on hundreds to thousands of diverse representations of it.
Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsStudy: Continual learning order and companion dataStudy: Generational competitive continual learningStudy: Logical coherence of LLM world modelsStudy: Orchestrated specialists and bridge synthesis - 2024-07arXiv 2407.06322MagMax: Leveraging Model Merging for Seamless Continual Learning
Daniel Marczak, Bartłomiej Twardowski, Tomasz Trzciński et al. · Machine learning
This paper introduces a continual learning approach named MagMax, which utilizes model merging to enable large pre-trained models to continuously learn from new data without forgetting previously acquired knowledge.
- 2024-06arXiv 2406.16437Theory on Mixture-of-Experts in Continual Learning
Hongbo Li, Sen Lin, Lingjie Duan et al. · Machine learning
Continual learning (CL) has garnered significant attention because of its ability to adapt to new tasks that arrive over time. Catastrophic forgetting (of old tasks) has been identified as a major issue in CL, as the model adapts to new tasks.
- 2024-06arXiv 2406.10162Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
Carson Denison, Monte MacDiarmid, Fazl Barez et al. · AI & agents
In reinforcement learning, specification gaming occurs when AI systems learn undesired behaviors that are highly rewarded due to misspecified training goals.
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.
