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.
- 2026-04arXiv 2604.03904I-CALM: Incentivizing Confidence-Aware Abstention for LLM Selective Answering
Haotian Zong, Binze Li, Yufei Long et al. · Language models & NLP
Large language models (LLMs) often produce confident but incorrect answers, in part because standard evaluation incentives reward guessing over expressing uncertainty.
- 2026-04arXiv 2604.22779KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning
Cheng Gao, Cheng Huang, Kangyang Luo et al. · Machine learning
Enabling large language models (LLMs) to appropriately abstain from answering questions beyond their knowledge is crucial for mitigating hallucinations.
- 2026-04arXiv 2604.01621DWDP: Distributed Weight Data Parallelism for High-Performance LLM Inference on NVL72
Wanqian Li, Jintao Peng, Zongfei Jing et al. · Other
Large language model (LLM) inference increasingly depends on multi-GPU execution, yet existing inference parallelization strategies require layer-wise inter-rank synchronization, making end-to-end performance sensitive to workload imbalance.
Cited inThe Wrong Phase - 2026-04arXiv 2604.02460Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets
Dat Tran, Douwe Kiela · Language models & NLP
Recent work reports strong performance from multi-agent LLM systems (MAS), but these gains are often confounded by increased test-time computation.
- 2026-04arXiv 2604.01152Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning
Mohammad R. Abu Ayyash · Language models & NLP
We present Brainstacks, a modular architecture for continual multi-domain fine-tuning of large language models that packages domain expertise as frozen adapter stacks composing additively on a shared frozen base at inference.
Cited inInternal notes - 2026-03arXiv 2603.30021Urban scaling and the dynamics of individual cities
Ulysse Marquis, Marc Barthelemy · Nature Cities (2026) · Hardware, photonics & physics
Cities are often compared through scaling laws, usually expressed as power-law relations between population size and aggregate urban quantities related to infrastructure, socioeconomic activity, or environmental impacts.
- 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 2603.25100From Logic Monopoly to Social Contract: Separation of Power and the Institutional Foundations for Autonomous Agent Economies
Anbang Ruan · AI & agents
4% emergent deceptive behavior without explicit reward signals, and cascading failure modes rooted in six structural bottlenecks. The remedy is not better alignment of individual models but a social contract for agents: institutional infrastructure that enforces a constitutional Separation of Power.
- 2026-03arXiv 2603.25187Probing the Lack of Stable Internal Beliefs in LLMs
Yifan Luo, Kangping Xu, Yanzhen Lu et al. · Language models & NLP
Persona-driven large language models (LLMs) require consistent behavioral tendencies across interactions to simulate human-like personality traits, such as persistence or reliability.
- 2026-03arXiv 2603.24621ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence
ARC Prize Foundation · AI & agents
We introduce ARC-AGI-3, an interactive benchmark for studying agentic intelligence through novel, abstract, turn-based environments in which agents must explore, infer goals, build internal models of environment dynamics, and plan effective action sequences without explicit instructions.
Cited inStudy: Superintelligence - 2026-03arXiv 2603.22213SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injection
Kexian Tang, Jiani Wang, Shaowen Wang et al. · Machine learning
While large language models (LLMs) are pretrained on massive amounts of data, their knowledge coverage remains incomplete in specialized, data-scarce domains, motivating extensive efforts to study synthetic data generation for knowledge injection.
- 2026-03arXiv 2603.21396Mechanisms of Introspective Awareness
Uzay Macar, Li Yang, Atticus Wang et al. · Machine learning
" We investigate the mechanisms underlying this capability in open-weights models. First, we find that it is behaviorally robust: models detect injected steering vectors at moderate rates with 0% false positives across diverse prompts and dialogue formats.
- 2026-03arXiv 2603.20101Pitfalls in Evaluating Interpretability Agents
Tal Haklay, Nikhil Prakash, Sana Pandey et al. · AI & agents
Automated interpretability systems aim to reduce the need for human labor and scale analysis to increasingly large models and diverse tasks.
- 2026-03arXiv 2603.18894I Can't Believe It's Corrupt: Evaluating Corruption in Multi-Agent Governance Systems
Vedanta S P, Ponnurangam Kumaraguru · AI & agents
Large language models are increasingly proposed as autonomous agents for high-stakes public workflows, yet we lack systematic evidence about whether they would follow institutional rules when granted authority.
- 2026-03arXiv 2603.19149Optimal Splitting of Language Models from Mixtures to Specialized Domains
Skyler Seto, Pierre Ablin, Anastasiia Filippova et al. · Language models & NLP
Language models achieve impressive performance on a variety of knowledge, language, and reasoning tasks due to the scale and diversity of pretraining data available.
- 2026-03arXiv 2603.17973TDAD: Test-Driven Agentic Development - Reducing Code Regressions in AI Coding Agents via Graph-Based Impact Analysis
Pepe Alonso, Sergio Yovine, Victor A. Braberman · Society, software & economics
AI coding agents can resolve real-world software issues, yet they frequently introduce regressions -- breaking tests that previously passed. Current benchmarks focus almost exclusively on resolution rate, leaving regression behavior under-studied.
- 2026-03arXiv 2603.18073Continually self-improving AI
Zitong Yang · AI & agents
Modern language model-based AI systems are remarkably powerful, yet their capabilities remain fundamentally capped by their human creators in three key ways.
- 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 2603.14517Learning to Forget: Sleep-Inspired Memory Consolidation for Resolving Proactive Interference in Large Language Models
Ying Xie · AI & agents
Large language models (LLMs) suffer from proactive interference (PI): outdated information in the context window disrupts retrieval of current values.
- 2026-03arXiv 2603.14623Proactive Routing to Interpretable Surrogates with Distribution-Free Safety Guarantees
Iqtedar Uddin, Mazin Khider, André Bauer · Machine learning
Model routing determines whether to use an accurate black-box model or a simpler surrogate that approximates it at lower cost or greater interpretability.
- 2026-03arXiv 2603.13972FLUX: Data Worth Training On
Gowtham, Sai Rupesh, Sanjay Kumar et al. · Language models & NLP
Modern large language model training is no longer limited by data availability, but by the inability of existing preprocessing pipelines to simultaneously achieve massive scale and high data quality.
- 2026-03arXiv 2603.12658Beyond Static Models: An Evolving Framework for Continual Learning in Large Language Models across Training Stages
Hongyang Chen, Zhongwu Sun, Hongfei Ye et al. · Language models & NLP
Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting, a critical limitation of the static pre-training paradigm inherent to modern LLMs.
- 2026-03arXiv 2603.11395ARROW: Augmented Replay for RObust World models
Abdulaziz Alyahya, Abdallah Al Siyabi, Markus R. Ernst et al. · Transactions on Machine Learning Research, 2026 · Machine learning
Continual reinforcement learning challenges agents to acquire new skills while retaining previously learned ones with the goal of improving performance in both past and future tasks.
- 2026-03arXiv 2603.09892MSSR: Memory-Aware Adaptive Replay for Continual LLM Fine-Tuning
Yiyang Lu, Yu He, Jianlong Chen et al. · Machine learning
Continual fine-tuning of large language models (LLMs) is becoming increasingly crucial as these models are deployed in dynamic environments where tasks and data distributions evolve over time.
- 2026-03arXiv 2603.09938Model Merging in the Era of Large Language Models: Methods, Applications, and Future Directions
Mingyang Song, Mao Zheng · Language models & NLP
Model merging combines the parameters of multiple neural networks into a single model without additional training.
- 2026-03arXiv 2603.10090A Survey of Weight Space Learning: Understanding, Representation, and Generation
Xiaolong Han, Zehong Wang, Bo Zhao et al. · Machine learning
Neural network weights are typically viewed as the end product of training, while most deep learning research focuses on data, features, and architectures.
- 2026-03arXiv 2603.08640PostTrainBench: Can LLM Agents Automate LLM Post-Training?
Ben Rank, Hardik Bhatnagar, Ameya Prabhu et al. · Society, software & economics
AI agents have become surprisingly proficient at software engineering over the past year, largely due to improvements in reasoning capabilities. This raises a deeper question: can these systems extend their capabilities to automate AI research itself?
- 2026-03arXiv 2603.13364FineRMoE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach
Ning Liao, Xiaoxing Wang, Xiaohan Qin et al. · Vision
As revealed by the scaling law of fine-grained MoE, model performance ceases to be improved once the granularity of the intermediate dimension exceeds the optimal threshold, limiting further gains from single-dimension fine-grained design.
- 2026-03arXiv 2603.07670Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
Pengfei Du · AI & agents
Large language model (LLM) agents increasingly operate in settings where a single context window is far too small to capture what has happened, what was learned, and what should not be repeated.
- 2026-03arXiv 2603.06003EvoESAP: Non-Uniform Expert Pruning for Sparse MoE
Zongfang Liu, Shengkun Tang, Boyang Sun et al. · Machine learning
Sparse Mixture-of-Experts (SMoE) language models achieve strong capability at low per-token compute, yet deployment remains constrained by memory footprint and throughput because the full expert pool must still be stored and served.
- 2026-03arXiv 2603.16910TerraLingua: Emergence and Analysis of Open-endedness in LLM Ecologies
Giuseppe Paolo, Jamieson Warner, Hormoz Shahrzad et al. · AI & agents
As autonomous agents increasingly operate in real-world digital ecosystems, understanding how they coordinate, form institutions, and accumulate shared culture becomes both a scientific and practical priority.
- 2026-03arXiv 2603.03818Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
Huihan Liu, Changyeon Kim, Bo Liu et al. · Machine learning
Continual learning is a long-standing challenge in robot policy learning, where a policy must acquire new skills over time without catastrophically forgetting previously learned ones.
Cited inStudy: Genesys program prior art - 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.
- 2026-03arXiv 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.
- 2026-03arXiv 2603.01935Dream2Learn: Structured Generative Dreaming for Continual Learning
Salvatore Calcagno, Matteo Pennisi, Federica Proietto Salanitri et al. · Machine learning
Continual learning requires balancing plasticity and stability while mitigating catastrophic forgetting.
- 2026-02arXiv 2602.21012International AI Safety Report 2026
Yoshua Bengio, Stephen Clare, Carina Prunkl et al. · Society, software & economics
The International AI Safety Report 2026 synthesises the current scientific evidence on the capabilities, emerging risks, and safety of general-purpose AI systems.
- 2026-02arXiv 2602.20031Latent Introspection: Models Can Detect Prior Concept Injections
Theia Pearson-Vogel, Martin Vanek, Raymond Douglas et al. · AI & agents
We uncover a latent capacity for introspection in a Qwen 32B model, demonstrating that the model can detect when concepts have been injected into its earlier context and identify which concept was injected.
- 2026-02arXiv 2602.20044Let There Be Claws: An Early Social Network Analysis of AI Agents on Moltbook
H. C. W. Price, H. AlMuhanna, P. M. Bassani et al. · Hardware, photonics & physics
Within twelve days of launch, an AI-native social platform exhibits extreme attention concentration, hierarchical role separation, and one-way attention flow, consistent with the hypothesis that stratification in agent ecosystems can emerge rapidly rather than gradually.
- 2026-02arXiv 2602.20273The Truthfulness Spectrum Hypothesis
Zhuofan Josh Ying, Shauli Ravfogel, Nikolaus Kriegeskorte et al. · Machine learning
Large language models (LLMs) have been reported to linearly encode truthfulness, yet recent work questions this finding's generality.
- 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.
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.
