self-improving-agents

Tag

Cards List
#self-improving-agents

Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents

arXiv cs.AI · 2d ago Cached

This paper introduces SkillMisevo-Gym and SkillMisevo-Bench to study how self-improving LLM agents can evolve unsafe skills from compromised experience, plus SafeEvolve as a mitigation wrapper. Experiments across 25 agent-method configurations show skill misevolution is widespread and can persist across sessions, though SafeEvolve reduces fresh-session harm significantly.

0 favorites 0 likes
#self-improving-agents

Towards Researcher Agents for Knowledge-Graph Question Answering

arXiv cs.AI · 5d ago Cached

This paper presents a self-improving 'researcher agent' for Text-to-SPARQL question answering over knowledge graphs, which iteratively refines its own prompts and tools. Evaluated on DBpedia, it achieves 0.22 accuracy and identifies predicate selection as the main bottleneck.

0 favorites 0 likes
#self-improving-agents

@Xudong07452910: Recently discovered that Stanford Online posted the full lecture recordings of the graduate course CS329A: Self-Improving AI Agents to YouTube, 9 lectures in total. The course basically revolves around one question: how AI agents can continuously improve through interaction with their environment...

X AI KOLs Timeline · 6d ago Cached

Stanford University has released the full recordings of the graduate course CS329A: Self-Improving AI Agents on YouTube, with 9 lectures covering topics such as test-time compute, verifiers, reinforcement learning, tool feedback, and multi-step reasoning, systematically organizing the direction of agent self-improvement.

0 favorites 0 likes
#self-improving-agents

@rohanpaul_ai: A self-improving agent can keep its weights frozen and still get worse through the memories it learns to trust. These a…

X AI KOLs Following · 6d ago Cached

The paper 'Memory Reward Inflation in Self-Improving LLM Agents' shows that self-improving agents with frozen weights can still degrade by trusting flawed LLM-generated memory scores, with models endorsing 31–54% of their own wrong answers. This 'Echo Gap' persists across stronger LLMs.

0 favorites 0 likes
#self-improving-agents

@rvaniaaaa: Almost every self-improving agent i looked at had the same missing piece. People build the discovery part. Scout finds …

X AI KOLs Following · 2026-08-08 Cached

A tweet discusses the missing piece in self-improving agents: a strict review gate where an experienced engineer must approve each skill. It explains how a growing library improves discovery and extraction quality, with humans approving all merges to keep the system trustworthy.

0 favorites 0 likes
#self-improving-agents

Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents

arXiv cs.AI · 2026-07-15 Cached

This paper proposes a method for co-evolving evaluation metrics and skills in self-improving LLM agent systems, demonstrating that metrics can be evolved and that a co-evolution approach recovers most of the performance of a ground-truth-driven oracle across code generation, text-to-SQL, and report generation tasks.

0 favorites 0 likes
#self-improving-agents

Today, we are releasing verifiers v1 (3 minute read)

TLDR AI · 2026-07-14 Cached

Prime Intellect Lab is out of beta, offering a platform to train models with support for various architectures and modalities, enabling self-improving agents.

0 favorites 0 likes
#self-improving-agents

@loganthorneloe: https://x.com/loganthorneloe/status/2075684831233757275

X AI KOLs Timeline · 2026-07-10 Cached

A curated list of five notable AI articles from the past week, covering self-improving agents, Bun's migration to Rust, vLLM architecture, coding evaluation benchmarks, and agent autonomy levels.

0 favorites 0 likes
#self-improving-agents

@zodchiii: Anthropic x Google just released 3 workshops on building self-improving agentic systems from scratch: 00:01 – Why multi…

X AI KOLs Timeline · 2026-07-10 Cached

Anthropic and Google released three free workshops on building self-improving agentic systems, covering multi-agent pitfalls, skill gaps, and building autonomous agents.

0 favorites 0 likes
#self-improving-agents

@dair_ai: // MetaSkill-Evolve // Great paper on self-improving agents. Most self-improving agents rewrite what the agent does and…

X AI KOLs Following · 2026-07-07 Cached

MetaSkill-Evolve introduces a recursive two-timescale framework for LLM agents to evolve both task skills and the improvement procedure itself, achieving notable accuracy gains on OfficeQA, SealQA, and ALFWorld benchmarks.

0 favorites 0 likes
#self-improving-agents

Autoresearch: The feedback loop behind self-improving agents (11 minute read)

TLDR AI · 2026-07-02 Cached

Introspection, a new AI startup founded by ex-xAI engineers, introduces 'autoresearch' – a feedback loop system where agents maintain and improve themselves using signals, evals, and human input, moving beyond traditional agent harnesses.

0 favorites 0 likes
#self-improving-agents

@DeRonin_: How to naturally build your own self-improving agents: a self-improving agent learns from its own mistakes and rewrites…

X AI KOLs Timeline · 2026-06-29 Cached

A practical guide explaining three levels of building self-improving AI agents, from manual loops to automated design, with recommended tools and frameworks.

0 favorites 0 likes
#self-improving-agents

@Saboo_Shubham_: This is HOW you run a one-person AI Agent company in 2026. 7 AI agents. 10 cron jobs. 0 human employees. Every role is …

X AI KOLs Following · 2026-06-29 Cached

A one-person company runs entirely with 7 AI agents, 10 cron jobs, and no human employees. The agents self-evaluate and improve, operating through Telegram.

0 favorites 0 likes
#self-improving-agents

@zostaff: This paper completely changed how I think about self-improving agents: Initialize -> Run -> Analyze -> Branch -> Update…

X AI KOLs Timeline · 2026-06-28 Cached

This paper presents a novel blueprint for self-improving agents that combines scaffold editing and weight training through a meta-agent and feedback-agent, achieving a 14x speedup on a CUDA kernel for AlphaFold.

0 favorites 0 likes
#self-improving-agents

The Red Queen G\"odel Machine: Co-Evolving Agents and Their Evaluators

arXiv cs.LG · 2026-06-26 Cached

This paper introduces the Red Queen Gödel Machine (RQGM), an evolutionary framework for recursive self-improvement under non-stationary utilities, where agents and evaluators co-evolve, improving performance on coding tasks, scientific writing, and Olympiad-level proof grading.

0 favorites 0 likes
#self-improving-agents

@yoheinakajima: in arxiv paper #2, i tackle the last topic from paper #1: @activegraphai as an architectural affordance for self-improv…

X AI KOLs Following · 2026-06-10 Cached

This paper introduces Regimes, an auditable, held-out-gated improvement loop built on the ActiveGraph runtime for self-improving agents. It demonstrates modest improvements on the LongMemEval dataset by autonomously discovering prompt repairs that pass static checks, sandbox execution, and held-out validation.

0 favorites 0 likes
#self-improving-agents

EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents

Hugging Face Daily Papers · 2026-06-09 Cached

EEVEE is a novel test-time prompt learning framework for LLM agents that handles heterogeneous data streams through task clustering and co-evolving router-prompt optimization, achieving significant improvements over existing methods across multiple benchmarks.

0 favorites 0 likes
#self-improving-agents

@dair_ai: Great paper on self-improving agents:

X AI KOLs Following · 2026-06-07 Cached

A prominent AI paper from the week addresses whether self-improving agents are truly discovering new knowledge or merely remixing existing information.

0 favorites 0 likes
#self-improving-agents

@omarsar0: This was one of the standout AI papers of the week. (bookmark it) It tackles a question most self-improving AI agents i…

X AI KOLs Following · 2026-06-07 Cached

This paper introduces a categorical framework for distinguishing genuine scientific discovery from mere retrieval or search in self-improving AI agents, using category theory to formalize regime transitions. The authors demonstrate the framework with a protein mechanics example where an agent's accuracy drops as it tackles harder problems, but its theory compresses more data, indicating real discovery.

0 favorites 0 likes
#self-improving-agents

@rohanpaul_ai: Better self-improving agents need better solvers, not bigger update-writing models. This challenges the common habit of…

X AI KOLs Following · 2026-06-05 Cached

This paper disentangles the roles of evolver and agent in self-improving LLM agents, showing that a small evolver can write sufficiently good updates, while a mid-tier agent benefits most from using them. It recommends using the strongest model as the task executor, not the update writer.

0 favorites 0 likes
Next →
← Back to home

Submit Feedback