arXiv:2609.07575v1 Announce Type: cross Abstract: This work introduces an alternative view of efficient exploration and studies its theoretical and empirical implications in the absence of extrinsic...
arXiv:2606. 20858v2 Announce Type: replace Abstract: The temporal structure of reward composition in reinforcement learning (RL) is typically hand-designed and held fixed throughout training, leaving the progression of motivational priorities largely unexplored.
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.
arXiv:2511. 22226v2 Announce Type: replace Abstract: The standard theory of model-free reinforcement learning assumes that the environment dynamics are stationary and that agents are decoupled from their environment, such that policies are treated as being separate from the world they inhabit.
The paper proposes a developmental framework for autonomous artificial agents that emphasizes learning social norms and alignment through direct interaction with dynamic environments. It argues that intrinsic motivations such as curiosity and competence can guide exploration, but also complicate alignment with human goals. By drawing parallels to child development, the authors suggest that regulatory sandboxes serve as pedagogical spaces where agents gradually acquire moral agency and adapt their behaviors through experience and cooperation.
arXiv:2609.17325v1 Announce Type: new Abstract: Biological cells can be viewed as individual, interacting agents whose collective dynamics give rise to adaptive behaviour at multiple levels of organi...
arXiv:2608. 02713v1 Announce Type: cross Abstract: Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow, unsafe, and hard to parallelize.
The paper introduces "environment evolution," a method that incrementally raises the difficulty of interactive environments off‑policy, scheduling their generation across training generations to supply continuous learning signals. It derives three evolution directions tied to a multi‑turn learning objective and implements them via a loop‑engineered multi‑agent harness. Experiments with models such as Hy4 preview, Claude Opus 5, GPT‑5.6 Sol, Qwen3.6‑27B, and Qwen3.6‑35B‑A3B demonstrate that this approach consistently creates harder environments and boosts terminal‑agent performance on Terminal‑Bench 2.1 by 14.4–18.0 percentage points.
The paper introduces "environment evolution," a method that incrementally raises the difficulty of interactive environments for terminal agents using off‑policy updates. It derives three evolution directions tied to a multi‑turn learning objective and implements them via a loop‑engineered multi‑agent harness. Experiments with models such as Hy4 preview, Claude Opus 5, GPT‑5.6 Sol, Qwen3.6‑27B, and Qwen3.6‑35B‑A3B demonstrate that this approach consistently generates harder environments and yields significant performance gains on Terminal‑Bench 2.1.
Darwin‑Claw is a new framework for large language model agents that enables environment‑adaptive, self‑evolving behavior. It systematically distills episodic experiences into prototype vectors through a hierarchical experience consolidation system, providing context‑sensitive perception patches and explicit optimization signals for skill refinement. The method is deployable with mainstream agent systems and, according to experiments on WildClawBench, delivers significant performance gains while maintaining controllability and stability.
arXiv:2607. 17560v1 Announce Type: new Abstract: Reinforcement learning (RL) provides a framework for sequential decision making under explicit objectives.
EvolvingBrain introduces an adaptive skill system that enables multi-modal agents to self‑evolve in open worlds. The system comprises Stratified Skill Self‑Evolution, which extracts procedural and problematic patterns from trajectories to build a multi‑granularity skill architecture, and State‑Aware Adaptive Execution, which uses structured memory to guide skill fusion based on the agent’s current state. Experiments on VAB‑Minecraft and DiscoveryWorld show improved success rates and generalization, with code available for public release.