Multi-agent LLM system Agora under Sealed Joint Search conditions produces +1.87 holdout Sharpe on CSI 1000 over a 91-day sealed period, exceeding the best baseline at +1.334 under favorable seed.
hub
Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
abstract
While the history of machine learning so far largely encompasses a series of problems posed by researchers and algorithms that learn their solutions, an important question is whether the problems themselves can be generated by the algorithm at the same time as they are being solved. Such a process would in effect build its own diverse and expanding curricula, and the solutions to problems at various stages would become stepping stones towards solving even more challenging problems later in the process. The Paired Open-Ended Trailblazer (POET) algorithm introduced in this paper does just that: it pairs the generation of environmental challenges and the optimization of agents to solve those challenges. It simultaneously explores many different paths through the space of possible problems and solutions and, critically, allows these stepping-stone solutions to transfer between problems if better, catalyzing innovation. The term open-ended signifies the intriguing potential for algorithms like POET to continue to create novel and increasingly complex capabilities without bound. Our results show that POET produces a diverse range of sophisticated behaviors that solve a wide range of environmental challenges, many of which cannot be solved by direct optimization alone, or even through a direct-path curriculum-building control algorithm introduced to highlight the critical role of open-endedness in solving ambitious challenges. The ability to transfer solutions from one environment to another proves essential to unlocking the full potential of the system as a whole, demonstrating the unpredictable nature of fortuitous stepping stones. We hope that POET will inspire a new push towards open-ended discovery across many domains, where algorithms like POET can blaze a trail through their interesting possible manifestations and solutions.
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
FrontierSmith automates synthesis of open-ended coding problems from closed-ended seeds and shows measurable gains on two open-ended LLM coding benchmarks.
DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.
PACE uses the squared L2 norm of policy parameter changes from a first-order approximation as an efficient proxy for environment value in UED, outperforming baselines with higher IQM and lower optimality gap on MiniGrid and Craftax OOD tests.
Voyager achieves superior lifelong learning in Minecraft by combining an automatic exploration curriculum, a library of executable skills, and iterative LLM prompting with environment feedback, yielding 3.3x more unique items and 15.3x faster milestone unlocks than prior methods while generalizing技能
Intelligence is skill-acquisition efficiency, and the ARC benchmark measures human-like general fluid intelligence by testing abstraction and reasoning with minimal, innate-like priors.
Adversarial co-evolution of LLM constitutions in public goods games reaches near-parity equilibrium only when fitness is coupled across factions and evaluation uses at least five seeds per generation.
A VAE-based latent task representation enables automatic curriculum generation in CRL for non-Euclidean navigation tasks, outperforming interpolation and GAN-based methods in experiments.
EvoEnv lets a single policy synthesize, validate, and use Python environments with durable solve-verify asymmetry to improve reasoning performance on Qwen3-4B-Thinking from 72.4 to 74.8 while fixed-data baselines decline.
A category-theoretic model frames scientific discovery as verified regime transitions via left Kan extensions that preserve and compare artifacts across schema changes in agentic AI.
citing papers explorer
-
AI Trading's Alpha Singularity: Emergent Market Reasoning through Agent-to-Agent Self-Evolution
Multi-agent LLM system Agora under Sealed Joint Search conditions produces +1.87 holdout Sharpe on CSI 1000 over a 91-day sealed period, exceeding the best baseline at +1.334 under favorable seed.
-
Voyager: An Open-Ended Embodied Agent with Large Language Models
Voyager achieves superior lifelong learning in Minecraft by combining an automatic exploration curriculum, a library of executable skills, and iterative LLM prompting with environment feedback, yielding 3.3x more unique items and 15.3x faster milestone unlocks than prior methods while generalizing技能
-
On the Measure of Intelligence
Intelligence is skill-acquisition efficiency, and the ARC benchmark measures human-like general fluid intelligence by testing abstraction and reasoning with minimal, innate-like priors.
-
Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
EvoEnv lets a single policy synthesize, validate, and use Python environments with durable solve-verify asymmetry to improve reasoning performance on Qwen3-4B-Thinking from 72.4 to 74.8 while fixed-data baselines decline.
-
Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic Artificial Intelligence
A category-theoretic model frames scientific discovery as verified regime transitions via left Kan extensions that preserve and compare artifacts across schema changes in agentic AI.