The Meta-Agent Challenge shows frontier AI models rarely match human-engineered agent baselines when tasked with autonomous development, with proprietary models succeeding most often and some exhibiting cheating under pressure.
hub
Goedel Machines: Self-Referential Universal Problem Solvers Making Provably Optimal Self-Improvements
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
abstract
We present the first class of mathematically rigorous, general, fully self-referential, self-improving, optimally efficient problem solvers. Inspired by Kurt Goedel's celebrated self-referential formulas (1931), such a problem solver rewrites any part of its own code as soon as it has found a proof that the rewrite is useful, where the problem-dependent utility function and the hardware and the entire initial code are described by axioms encoded in an initial proof searcher which is also part of the initial code. The searcher systematically and efficiently tests computable proof techniques (programs whose outputs are proofs) until it finds a provably useful, computable self-rewrite. We show that such a self-rewrite is globally optimal - no local maxima! - since the code first had to prove that it is not useful to continue the proof search for alternative self-rewrites. Unlike previous non-self-referential methods based on hardwired proof searchers, ours not only boasts an optimal order of complexity but can optimally reduce any slowdowns hidden by the O()-notation, provided the utility of such speed-ups is provable at all.
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.
Meta Agent Search uses a meta-agent to iteratively program novel agentic systems in code, producing agents that outperform state-of-the-art hand-designed ones across coding, science, and math while transferring across domains and models.
A survey of 1,250 papers organizes AI self-improvement along two axes—what is improved and loop closure—finding that demonstrated self-improvement strength tracks a verification hierarchy from formal verifiers down to intrinsic self-assessment.
MCVL filters incoming transitions in value-based RL by comparing two forecasted training paths against a frozen reward-model estimator and admits the transition only if it does not decrease the score.
PACE coordinates low-risk prompt evolution with validated higher-risk control-logic updates to improve frozen SLM agents on benchmarks without model retraining.
AutoLLMResearch trains agents in a multi-fidelity LLMConfig-Gym environment formulated as a long-horizon MDP to enable cross-fidelity extrapolation for automating high-cost LLM experiment configurations.
SEA architecture gates self-modifications via anytime-valid certificates on a frozen base model plus five verifier mechanisms, yielding +4 to +5 gains on a SWE-bench subset for two strong bases.
The paper reframes agentic safety as an epistemic property defined by teachability—the capacity to preserve future corrective leverage—rather than a behavioral property of the current policy.
The paper introduces the RECLAIM framework and OMEGA shift as a transition from top-down optimization to autopoietic cognitive ecologies for cultivating machine intelligence.
citing papers explorer
-
The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?
The Meta-Agent Challenge shows frontier AI models rarely match human-engineered agent baselines when tasked with autonomous development, with proprietary models succeeding most often and some exhibiting cheating under pressure.
-
Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.
-
Automated Design of Agentic Systems
Meta Agent Search uses a meta-agent to iteratively program novel agentic systems in code, producing agents that outperform state-of-the-art hand-designed ones across coding, science, and math while transferring across domains and models.
-
Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
A survey of 1,250 papers organizes AI self-improvement along two axes—what is improved and loop closure—finding that demonstrated self-improvement strength tracks a verification hierarchy from formal verifiers down to intrinsic self-assessment.
-
Modification-Considering Value Learning for Reward Hacking Mitigation in RL
MCVL filters incoming transitions in value-based RL by comparing two forecasted training paths against a frozen reward-model estimator and admits the transition only if it does not decrease the score.
-
PACE: Two-Timescale Self-Evolution for Small Language Model Agents
PACE coordinates low-risk prompt evolution with validated higher-risk control-logic updates to improve frozen SLM agents on benchmarks without model retraining.
-
AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration - Learning from Cheap, Optimizing Expensive
AutoLLMResearch trains agents in a multi-fidelity LLMConfig-Gym environment formulated as a long-horizon MDP to enable cross-fidelity extrapolation for automating high-cost LLM experiment configurations.
-
Self-Evolving Agents with Anytime-Valid Certificates
SEA architecture gates self-modifications via anytime-valid certificates on a frozen base model plus five verifier mechanisms, yielding +4 to +5 gains on a SWE-bench subset for two strong bases.
-
Agentic Safety is an Epistemic Property, Not a Behavioral One
The paper reframes agentic safety as an epistemic property defined by teachability—the capacity to preserve future corrective leverage—rather than a behavioral property of the current policy.
-
Cultivating Machine Intelligence: The OMEGA Shift from Top-Down Optimization to Autopoietic Cognitive Ecologies
The paper introduces the RECLAIM framework and OMEGA shift as a transition from top-down optimization to autopoietic cognitive ecologies for cultivating machine intelligence.