An apron can be given. Character has to be built. In Freemasonry, the apron reminds us that the work begins with ourselves: keeping our word, governing our actions and treating others fairly. #SelfImprovement# #personalgrowth# #freemasonry#

The apron is given. The work is yours. Freemasonry asks us to build character through integrity, discipline and the choices we make when no one is watching. Where do you stand in your self-improvement journey? Please answer below 👇👇👇 #Freemasonry# #Selfimprovement#

A self-improving multimodal model can decide when to switch to fresh problems using only its training logs 🔄 A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement 📌 Overview A-RSI is a method for refreshing the training task pool at the right time when a VLM improves itself without human labels. ⚠️ The problem ・Most work focuses on what to generate next, not when to replace the data ・Labels from majority voting can turn the model's own errors into training targets 🧩 Method ・The base model writes parameterized task generators that programmatically produce an image, a question, and a reference answer ・Training uses GRPO, with correctness ranked above all auxiliary rewards ・When prompts with reward variance drop or accuracy rises, the whole pool is replaced with unused tasks 📊 Results ・Qwen3-VL-8B's 11-benchmark average rose from 57.77 to 61.05 using 800 fresh tasks ・Refreshing every window reached 60.64 but used 3,200 tasks, four times as many ・MiMo-VL-7B also went from 59.08 to 60.71 🔭 Why it matters Timing the refresh without validation scores is practical. Note that each comparison is a single training run. #SelfImprovement# #MultimodalAI#

When AI output gets too good for human experts to grade, how does self-improvement keep going? A new method breaks right through that wall. Title: Recursive Self-Improvement through Multi-Agent Self-Supervision URL: A single model grading its own output hits a ceiling fast. MASS (Multi-Agent Self-Supervision) coordinates multiple copies of the same model to evolve better workflows, then retrains itself on the resulting traces, breaking the homogeneous self-critique loop. 🧬 Evolving workflows For each task, an evolutionary search improves the orchestrator-subagent setup, meaning roles, instructions, output contracts, and execution order, guided only by self-evaluation, gradually discovering better coordination patterns. 📈 Efficiency and performance together Across two improvement cycles on Qwen3.6-27B, MASS delivers 1.2-1.6x higher performance per output token on four open-ended benchmarks. Students trained on multi-agent traces even outperformed single-agent students trained on 1.4x more tokens. 🔁 Internalization drives the bootstrap Without any workflow prompt at inference time, coordination behaviors like code handoffs start appearing on their own, jumping from 1 in 110 trajectories to 83 in 110. The improved model then becomes a better optimizer and evaluator for the next cycle, keeping the recursive loop spinning. As AI output increasingly outpaces human grading, having models supervise each other through coordination looks like a path worth watching closely. #AIAgents# #SelfImprovement#

TL;DR A method that rewrites successes found under several harnesses into training data a single general harness can reproduce. Training on the raw traces hurts; rewriting them lifts pass@3 from 57.0% to 74.2%. Title: Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite URL: Points 🧩 Different harnesses solve different tasks; the union of three solves 34.3% more than the best single one 📝 A planner turns each success into a runbook, and an executor re-solves the task from scratch under the general harness 🔍 A critic screens every runbook for leaked answers and sends rejects back with a reason 🧹 The model then flags values that can't be derived from the task or environment and discards those traces 📈 Training data grows from 2,001 to 11,094 trajectories, and Terminal-Bench Hard rises from 39.0% to 63.0% ⚠️ Direct SFT actually degrades TB2, with dead-end loops where the model repeats the same action pattern forever 🎛 Even with no training, swapping the harness doubles TBH from 33.0% to 66.0% If you're thinking about feeding your own agent logs back into training, this makes a solid case for a rewrite-and-audit step first. #AIAgents# #SelfImprovement#

TL;DR: Re-evaluating an agent against a benchmark every time it self-improves gets expensive fast. SelfSearch instead learns purely from records of its own prior self-modification attempts, cutting search cost by more than half while still improving performance. Title: SelfSearch: Reward-Free Search for Self-Improving Agents URL: Points 🧠 Agents read "episode records" of prior self-modification attempts — reasoning traces, tool use, success/failure — and improve themselves with no downstream evaluation needed during search 🔀 Two parallel lineages evolve under "capability" and "adaptive" search directions, sharing discoveries while developing separately 📊 On Terminal-Bench 2.1, GPT rose from 43.8% to 55.1% and DeepSeek from 65.2% to 73.0% 💰 Search cost drops 49.0–53.2% versus evaluation-guided baselines; with DeepSeek V4 Flash it reaches 82.0% on Terminal-Bench 2.1 for just $4.03 in search cost, matching the strongest baseline ⚡ On SWE-bench Multilingual, it gains +5.0 points in success while cutting execution cost 38.5% 🔁 Agents evolved on GPT-5.6 Sol transfer effectively to DeepSeek V4 Flash with no code changes, still beating the baseline Removing the evaluation-cost bottleneck from the self-improvement loop feels like a genuinely practical design for running this in production. #AIAgents# #SelfImprovement#

What if letting an agent evolve its own workflow just meant it got better at gaming the test? This paper tackles exactly that overfitting problem. Title: RRSI: Regularized Recursive Self-Improvement of Agent Harnesses URL: ❓ What's a harness? It's everything wrapped around the frozen LLM: prompts, control flow, tooling, memory, context management. The same model can perform very differently depending on this design. ❓ Why does self-improving it overfit? Three failure modes show up: fitting too tightly to the evolve-set benchmark, chasing noise, and letting complexity pile up unchecked. 💡 How does RRSI fix it? It applies classic ML regularization (L0, L1, L2) to harness evolution: an annealed edit budget limits changes per round, benchmark-specific proposals get screened out at selection, and unproductive components get pruned. 💡 What's the payoff? Across 8 benchmarks, RRSI beats baselines by up to 22.9% on unseen tasks, while using 30% fewer tokens. It feels like a genuinely grounded step toward agents that can safely improve their own workflow in production. #AIAgents# #SelfImprovement#

Every interaction your deployed AI agent handles could double as training data to make it smarter. That is the pitch of this paper. NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness 🧩 Overview The authors turn logs from a "routing harness" (the layer that decides which capability tier handles each request) directly into training data, with no extra synthetic data pipeline, to recursively improve the model. ❓ The problem it solves Recursive self-improvement needs a way for a system to observe its own capabilities and feed that back into training. Most approaches build a separate data pipeline for this, but the material is already sitting inside everyday routing logs. ⚙️ Method Execution trajectories are structured by user turn, quality-checked with six semantic dimensions plus structural validation, and routing scores are used to order a three-stage curriculum for both SFT and on-policy distillation. Evaluation results then steer the next batch of training data toward weak spots. 📊 Results Across 10 agentic, coding, and instruction-following benchmarks, the 4B model's macro-average rose from 58.94 to 64.87, and the 9B model from 65.60 to 69.04, beating public synthetic data by +6.26 macro-average points. #AIAgents# #SelfImprovement#

Self-improving agents are a top research topic right now. This new survey is a good map of the area. (bookmark it) It splits recursive self-improvement into stages of autonomy. An agent first executes improvements someone else designed. Then it chooses its own improvement strategy, collects its own experience, adapts to new environments, and finally improves the process of improvement itself. That staging makes claims easier to check. When a paper says its agent is self-improving, you can ask which of these stages it actually automates. The survey also uses a Headroom-Closed Index to show where current LLMs fall short, and compares requirements across scientific discovery, embodied agents and software engineering. Paper: