JANUS is a framework that enhances long‑horizon autonomous research by integrating future outcome forecasting and past experience reflection through a Predict‑Verify‑Evolve loop powered by a co‑evolving world model. In this system, a research agent proposes candidate research paths while the world model evaluates them based on predicted value improvement, information gain, and exploration utility, guiding selection, refinement, or pruning before execution. After execution, JANUS distills feedback into evolving skills for both the agent and the world model, enabling continual co‑evolution and improved efficiency, as demonstrated by superior performance on MLS‑Bench‑Lite and real research tasks.
arXiv:2606. 05080v1 Announce Type: new Abstract: Scientific and engineering progress is fundamentally a long-horizon iterative process: proposing changes, running experiments, measuring outcomes, and continuously refining artifacts.
arXiv:2610.29784v1 Announce Type: new Abstract: Most contemporary artificial intelligence (AI) systems are released with frozen parameters and improve through external updates, whereas an ideal syste...
CoMAP introduces a framework that jointly evolves textual world models and agent policies through a closed‑loop interaction. At each decision step the world model forecasts future state feedback for candidate actions, while the agent reflects on the reliability of this feedback to refine its action. The resulting on‑policy trajectories are used to self‑distill and update the world model, improving prediction accuracy and long‑horizon decision‑making across embodied planning, web navigation, and tool‑use benchmarks.
arXiv:2606. 02372v1 Announce Type: new Abstract: Equipping language agents with world models enables them to anticipate environment dynamics and evaluate candidate actions before execution.
FREEEVOLVE automates the optimization loop used by agent evolvers, allowing the system to decide what to test, how much evidence to gather, which candidates to pursue, and when to stop, all within specified resource limits. By treating these decisions as an editable evolution skill and improving them through meta‑evolution, the method learns a capability that replaces hand‑crafted search loops. Experiments on several benchmarks show that FREEEVOLVE improves primary metrics by an average of 13.6 points and that meta‑evolved skills add further gains, indicating transferability across environments.
arXiv:2608. 14354v1 Announce Type: new Abstract: Enabling LLM agents to sustain productive, stable, and goal-aligned research over extended horizons is a central challenge for autonomous machine learning and scientific discovery, as progress hinges on continuously managing evolving state, exploration decisions, and computational resources.
Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction. Researchers test candidate directions, interpret the evidence, and carry the resulting lessons into later attempts.
arXiv:2606. 11926v1 Announce Type: cross Abstract: Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction.
Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow, unsafe, and hard to parallelize. World modeling offers a natural intermediate proxy that allows agents to query lower-cost, more controllable feedback before committing to real actions.
Many important forms of human learning begin with a vague goal, such as "become a better physicist" or "improve at research." Learners must interpret the goal, identify capability gaps, decide how to...
The paper introduces ASPIRE, a benchmark that challenges language model agents to self‑evolve from vague, natural‑language goals without explicit evaluation metrics. In ASPIRE, agents must interpret the goal, select data and update strategies, and decide when to evaluate, all while the downstream tasks remain hidden. Experiments show that while agents can complete training loops, weight‑level improvements are sparse and unstable, and the best evolved harness still falls short of a strong engineered baseline.
SpecEvo is a multi‑Large Language Model framework that uses lightweight models to generate and refine candidate programs while an Advisor consolidates evidence from successes and failures. At sparse checkpoints, a frontier‑model Navigator intervenes with synthesis or refinement to address search stagnation. Across 176 tasks in scientific and algorithmic domains, SpecEvo matches or surpasses frontier‑model baselines, cuts API cost by up to 80%, and improves evaluation efficiency and benchmark performance.