AI Papers of the Week
Every paper worth reading in AI, hand-picked one week at a time.
Autogenesis
Static agents age quickly. As deployment environments change and new tools arrive, the agents that survive will be the ones that can safely rewrite themselves. This paper introduces Autogenesis, a self-evolving agent protocol where agents identify their own capability gaps, generate candidate improvements, validate them through testing, and integrate what works back into their own operational framework. No retraining and no human patching, just an ongoing loop of assessment, proposal, validation, and integration.
Automated Weak-to-Strong Researcher
Anthropic shows that Claude can run fully autonomous progress on scalable oversight research. A team of parallel Automated Alignment Researchers (AARs) built on Claude Opus 4.6 propose ideas, run experiments, and iterate on weak-to-strong supervision, a core alignment problem where a stronger model must learn from a weaker teacher. The system closes almost the entire remaining performance gap that human researchers could not, at a total cost of roughly $18K in tokens and model training.
Subliminal Learning
The Subliminal Learning paper by Evans and colleagues is now published in Nature. The work showed that LLMs can transmit traits (such as a preference for owls) through data that appears unrelated to that trait, like sequences of numbers that look meaningless on inspection. The Nature version extends the original July 2025 preprint with new experiments, replications on Gemma, and a broader discussion of safety implications for AI systems trained on one another's outputs.
Muses-Bench
Every agent framework assumes one user giving instructions, but in real team workflows agents have multiple bosses with conflicting goals, private information, and different authority levels. Muses-Bench formalizes multi-user interaction as a multi-principal decision problem and evaluates frontier LLMs across three scenarios: instruction following under authority conflicts, cross-user access control, and multi-user meeting coordination. Gemini-3-Pro tops the leaderboard at just 85.6% average, and no model exceeds 64.8% on meeting coordination. Privacy-utility tradeoffs are brutal: Grok-3-Mini scores 99.6% on privacy but collapses to 60.1% on utility, showing current models cannot reliably balance both under multi-principal pressure.
Neural Computers
Researchers from Meta AI and KAUST propose Neural Computers (NCs), an emerging machine form that unifies computation, memory, and I/O in a single learned runtime state. Unlike conventional computers that execute explicit programs, agents that act over external environments, or world models that learn dynamics, NCs aim to make the model itself the running computer, establishing a new computing paradigm.
Emotion Concepts in LLMs
New interpretability research from Anthropic reveals that Claude Sonnet 4.5 develops internal representations of emotion concepts that functionally influence its behavior. The researchers identified 171 emotion concept vectors that activate in contextually appropriate situations and causally drive decision-making, suggesting that language models may benefit from approaches grounded in psychological principles for alignment and safety.
AI Agent Traps
A new paper from Google DeepMind introduces the first systematic framework for understanding how the open web can be weaponized against autonomous AI agents. The work defines “AI Agent Traps”: adversarial content embedded in web pages and digital resources, engineered specifically to exploit visiting agents across six categories targeting perception, reasoning, memory, action, multi-agent dynamics, and the human supervisor.
Hyperagents
Self-improving AI systems promise to reduce reliance on human engineering, but existing approaches rely on fixed, handcrafted meta-level mechanisms that fundamentally limit how fast they can improve. Hyperagents introduce self-referential agents that integrate a task agent and a meta agent into a single editable program, enabling the system to improve not just its task-solving behavior but also the mechanism that generates future improvements.
Agentic AI and the Next Intelligence Explosion
A new report from Google researchers argues that the AI “singularity” framed as a single superintelligent mind bootstrapping to godlike intelligence is fundamentally wrong. Drawing on evolution, sociology, and recent advances in agentic AI, the authors make the case that every prior intelligence explosion in human history was social, not individual, and that the next one will follow the same pattern.
Claudini
Researchers demonstrate that an autoresearch-style pipeline powered by Claude Code can autonomously discover novel adversarial attack algorithms for LLMs that significantly outperform all 30+ existing methods. The work, called Claudini, shows that incremental safety and security research can be effectively automated using LLM agents, with white-box red-teaming being a particularly well-suited domain.
SkillNet
AI agents repeatedly rediscover solutions across separate scenarios instead of systematically reusing what they have already learned. SkillNet introduces an open infrastructure designed to create, evaluate, and organize AI skills at scale, enabling agents to transition from transient experience to durable mastery.
The Spike, the Sparse and the Sink
Yann LeCun and collaborators at NYU dissect two recurring phenomena in Transformer language models: massive activations, where a small number of tokens exhibit extreme outliers in specific channels, and attention sinks, where certain tokens attract disproportionate attention mass regardless of semantic relevance. The paper reveals that their co-occurrence is largely an architectural artifact.
Why LLMs Form Geometric Representations
LLMs spontaneously form striking geometric structures in their internal representations: calendar months organize into circles, historical years form spirals, and spatial coordinates align to recoverable manifolds. This paper proves these patterns are not the product of deep learning dynamics but emerge directly from symmetries in natural language statistics.
Auton Agentic AI Framework
Snap Research introduces the Auton framework, a declarative architecture for specification, governance, and runtime execution of autonomous agent systems. It addresses a fundamental mismatch: LLMs produce stochastic, unstructured outputs, while backend infrastructure requires deterministic, schema-conformant inputs.
CoT Faithfulness via REMUL
Researchers propose REMUL, a training approach for making chain-of-thought reasoning more faithful and monitorable. A speaker model generates reasoning traces that multiple listener models attempt to follow and complete, using RL to reward reasoning that is understandable to other models. Tested across BIG-Bench Extra Hard, MuSR, ZebraLogicBench, and FOLIO, REMUL improves three faithfulness metrics while also boosting overall accuracy, producing shorter and more direct reasoning chains.
Intelligent AI Delegation
Google DeepMind introduces a comprehensive framework for intelligent AI delegation that goes beyond simple task assignment. The framework models delegation as a sequence of decisions: whether to delegate, how to instruct, and how to verify and integrate AI outputs, addressing the gap between what AI agents can do and how humans should interact with them.
Shaping Capabilities with Token-Level Data Filtering
Researchers from Anthropic and Stanford show that filtering pretraining data at the token level is a highly effective, scalable, and robust approach for selectively removing undesired capabilities from language models. Using medical knowledge removal as a proxy task, token-level filtering Pareto dominates document-level filtering and achieves a 7,000x compute slowdown on the target domain for 1.8B parameter models - while preserving capabilities in related fields.
How AI Impacts Skill Formation
Researchers from Anthropic conducted randomized experiments to study how AI assistance affects the development of software engineering skills. They find that using AI to complete coding tasks with a new Python library significantly impaired conceptual understanding, code reading, and debugging abilities - without delivering significant efficiency gains on average.
Self-Improving Pretraining
Self-Improving Pretraining is a new pretraining paradigm from Meta FAIR that replaces standard next-token prediction with sequence-level generation guided by an existing post-trained model acting as both a suffix rewriter and a suffix judge. The approach addresses quality, safety, and factuality issues at pretraining time rather than deferring them to post-training, yielding large gains across all three dimensions.
Team of Rivals: Orchestrating Reliable AI Agents
This paper proposes organizing AI agents into corporate-style teams with strict role boundaries and opposing incentives (planners, executors, critics, experts) to achieve reliability through careful orchestration of imperfect components. A remote code executor separates reasoning from data transformations, preventing raw tool outputs from contaminating agent context windows. The system achieves over 90% internal error interception before user exposure while maintaining acceptable latency tradeoffs.
Reasoning Models Generate Societies of Thought
This paper reveals that enhanced reasoning in models like DeepSeek-R1 and QwQ-32B emerges not from extended computation alone, but from simulating multi-agent-like interactions - a “society of thought” - enabling diversification and debate among internal cognitive perspectives with distinct personality traits and domain expertise.
Adversarial Program Evolution with LLMs
Digital Red Queen (DRQ) introduces an algorithm where LLMs evolve assembly-like programs called “warriors” that compete for control of a virtual machine in the game of Core War. Rather than optimizing toward static objectives, DRQ embraces “Red Queen” dynamics where goals continually shift based on competition, demonstrating how adversarial self-play can drive the evolution of increasingly sophisticated programs.
Nemotron-Cascade
Nemotron-Cascade introduces cascaded domain-wise reinforcement learning (Cascade RL) to build general-purpose reasoning models capable of operating in both instruct and deep thinking modes. Rather than blending heterogeneous prompts from different domains, Cascade RL orchestrates sequential, domain-wise RL stages that reduce engineering complexity while delivering state-of-the-art performance.
Monitoring Monitorability
OpenAI introduces a framework for measuring how well we can detect misbehavior in AI systems by monitoring their chain-of-thought reasoning. The paper proposes three evaluation archetypes and a new metric (g-mean2) to track monitorability across different models and training regimes.