Radar archive
Every daily edition.
| Date | Top item | Items |
|---|---|---|
| 16 Nov 2026 | ModHarness-RL: Recasting Harnesses as Learnable and Evolving Programs for Agentic RL | 6 |
| 15 Nov 2026 | MLIRBench: A Benchmark and Dataset for Compiler and Hardware-Aware Reasoning | 5 |
| 14 Nov 2026 | Experience-Handoff Reinforcement Learning for Recursive Self-Improvement | 6 |
| 13 Nov 2026 | Singularity-Bench: Can Agents Build Agents? | 7 |
| 12 Nov 2026 | New best on PostTrainBench: Fable 5.1 (Max) · Claude Code (44.6%) | 7 |
| 11 Nov 2026 | No Second Run: Does RSI Stop at Frontier Pre-training? | 7 |
| 10 Nov 2026 | Where is all the AI safety research uplift? | 7 |
| 9 Nov 2026 | Ajeya: AI is dramatically accelerating AI research right now | 12 |
| 8 Nov 2026 | ServerBench: How can your coding agents design specialized LLM serving systems? | 12 |
| 7 Nov 2026 | Independent Assessment of AI R&D Acceleration at Anthropic in October 2026 | 12 |
| 6 Nov 2026 | When Can Self-Play Fix a False Belief? Answer Keys, Pass Bands and Replacement Rules in an Execution-Grounded Loop | 7 |
| 5 Nov 2026 | EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling | 9 |
| 4 Nov 2026 | Think Less, Locally: Local Preference Learning for Reasoning Compression | 8 |
| 3 Nov 2026 | Exo: An Architecture for Self-Improving Systems at Runtime | 11 |
| 2 Nov 2026 | RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory | 5 |
| 1 Nov 2026 | Search-Guided Reasoning Trace Curation for Verilog Generation | 8 |
| 31 Oct 2026 | InfraDev: Can Coding Agents Develop AI Infrastructure, and How Can We Tell? | 8 |
| 30 Oct 2026 | A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement | 6 |
| 29 Oct 2026 | Build, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top Players | 12 |
| 28 Oct 2026 | How Much Does the Hint Matter? Scope Conditions for Hindsight Self-Distillation in Financial Reasoning | 12 |
| 27 Oct 2026 | Infinity Machine: a self-improving AI agent for research | 8 |
| 26 Oct 2026 | RSI-Opt: Recursive Self-Improvement Optimizer Agents For Model Training | 7 |
| 25 Oct 2026 | Agentic Knowledge-Model Co-Evolution via Consistency Regularization | 7 |
| 24 Oct 2026 | VeriEvolve: Evaluator-First Evolution for Tool-Using Agents | 8 |
| 23 Oct 2026 | SplatLab: Autonomous Scientific Discovery for 3DGS Research | 8 |
| 22 Oct 2026 | Recursive Self-Improvement on a Budget: Scoring Code Edits Before They Run | 7 |
| 21 Oct 2026 | Training the Whole Agent, Not Just the Model | 7 |
| 20 Oct 2026 | VibeTraining-Bench: Data-Trainer-Harness Co-Design for Iterative System Improvement | 8 |
| 19 Oct 2026 | Self-Evolving Coding Agents via Harness-Policy Optimization | 4 |
| 18 Oct 2026 | AdaRSI: On-Demand Recursive Self-Improvement for Embodied Agents | 6 |
| 17 Oct 2026 | AutoEnvScaling: Automating the Data Flywheel with Terminal Agents | 6 |
| 16 Oct 2026 | A Self-Improving Agent that Grows its Own DSL: Oracle-Free Operator Induction for Exact Question Answering | 9 |
| 15 Oct 2026 | CARD: Closing the Teacher-Student Loop for Adversarial Robustness Distillation | 6 |
| 14 Oct 2026 | Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules | 8 |
| 13 Oct 2026 | Sage | 6 |
| 12 Oct 2026 | Recursive Self-Improvement through Collective Intelligence | 6 |
| 11 Oct 2026 | Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models | 6 |
| 10 Oct 2026 | AdvSim2Real: Training Web Agents Against Adaptive Prompt Injection in a Web World Model | 5 |
| 9 Oct 2026 | The Red Queen Gödel Machine: Co-Evolving Agents and Their Evaluators | 9 |
| 8 Oct 2026 | FreeEvolve: Learning to Evolve Beyond Fixed Loops | 6 |
| 7 Oct 2026 | RRSI: Regularized Recursive Self-Improvement of Agent Harnesses | 5 |
| 6 Oct 2026 | SEIS: Self-Evolving Inference Systems | 6 |
| 5 Oct 2026 | Recursive Self-Improvement in Unified Multimodal Models | 7 |
| 4 Oct 2026 | Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents | 7 |
| 3 Oct 2026 | MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution | 8 |
| 2 Oct 2026 | AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks | 8 |