The paper introduces the Infinity Machine, a self‑improving AI agent designed to solve research problems whose solutions can be programmatically verified. The system operates autonomously: it generates candidate solutions, verifies them, and audits the results without human intervention, all within a sandboxed environment governed by a kernel‑enforced gate. In a six‑day experiment, the Infinity Machine achieved four new state‑of‑the‑art results in quantum information and improved qubit‑routing and hardware efficiency, while also documenting several failure modes.
arXiv:2607. 13070v2 Announce Type: replace-cross Abstract: Safety claims for self-improving agent runtimes are almost always self-graded: a policy file, a guardrail, a promise in a README.
arXiv:2607. 00871v1 Announce Type: new Abstract: Self-evolving agents violate the assumption behind most learning-theoretic guarantees: the data, evaluator, components, and hypothesis space are produced by the policy being updated.
arXiv:2605. 05138v2 Announce Type: replace Abstract: We evaluate an initial coding-agent system for ARC-AGI-3 in which the agent maintains an executable Python world model, verifies it against previous observations, refactors it toward simpler abstractions as a practical proxy for an MDL-like simplicity bias, and plans through the model before acting.
The paper reports on training and calibration experiments for three open models on the ARC‑AGI‑2 benchmark, using offline runs on four L4 GPUs for up to 12 hours. For the NVARC Qwen3‑4B grid model, a curated corpus of 12,000 executable rules and 95,993 tasks was built, and fine‑tuning on 1,920 real task records raised the semi‑private score from 28.96 to 33.06, with no synthetic‑task checkpoint outperforming the real‑task model. For the Qwen3.8‑27B reasoning model, fine‑tuning on 1,036 of its own reasoning traces and a specialized inference procedure increased the score from 26.81 to 44.03, while the Qwen3.8‑Flash‑Next mixture‑of‑experts model achieved a best score of 56.67 after expert pruning, routing statistics adaptation, and an FP8 indexer cache.
arXiv:2608.21356v1 Announce Type: cross Abstract: For sixty years, machine verification has been a major cost overhead, affordable only for exceptional artifacts. Here we report that generative AI in...
arXiv:2608. 07743v1 Announce Type: new Abstract: Identifying a meaningful quantum speedup requires more than matching a classical problem to a familiar quantum primitive: the claim must preserve the task, respect access and output models, expose required promises, and remain within a defensible complexity scope.
Eureka is a task‑conditioned Meta‑Agent architecture that transforms long‑horizon scientific tasks into dynamic obligation graphs with explicit acceptance semantics. During execution it constructs Macro‑Agents equipped with specialized state, memory, operators, tools, verifiers, and local topology, using receding‑horizon planning, architecture promotion, and minimal‑sufficient compilation. The system demonstrates strong empirical performance, completing all 170 recursive tasks, generating 3,948 certificates without false acceptances, and achieving significant reductions in input size, recomputation, and consistent serialization across 16,000 concurrent executions.
arXiv:2609.26086v1 Announce Type: new Abstract: An agentic retrieval system issues a sequence of search queries and must decide, at each step, whether the evidence collected so far is enough to stop....
arXiv:2607. 13070v1 Announce Type: cross Abstract: Safety claims on self-improving agent runtimes are almost always self-graded: a policy file, a guardrail, or a README commitment.
InfraDev is a new benchmark comprising 36 tasks derived from real-world pull requests to Megatron‑LM, vLLM, and verl, designed to test coding agents on infrastructure development for training, inference, and reinforcement learning across many GPUs. Each task requires agents to reimplement multi‑file changes and run correctly, with grading that includes hidden probes and a prompt exposing only the interfaces used. The benchmark reveals that current frontier models resolve only about 39% of tasks, with probes rejecting a third of submissions that pass official tests, and that structural and state errors dominate failures.
arXiv:2607. 04542v1 Announce Type: cross Abstract: Every LLM agent run re-derives its behavior token by token on a frontier model: brilliant, expensive, slow, and unbounded.
arXiv:2604. 16870v2 Announce Type: replace-cross Abstract: AI agents increasingly call external tools (file system, network, APIs) through the Model Context Protocol (MCP).