Simulated environments enable scalable training data generation for embodied agents, but more data does not necessarily provide what a particular agent needs to learn. Existing environment-generation...
arXiv:2609.22592v1 Announce Type: cross Abstract: Training agents with reinforcement learning requires a gym, comprising a task, an executable environment in which the task can be attempted, and a ve...
ActiveSaddler introduces automated curriculum learning for harness optimization, treating the evolving training curriculum as a non‑stationary bandit problem. It identifies reusable failure patterns, estimates learning progress for each, and balances revisiting known weaknesses with exploring new scenarios, allowing the curriculum to co‑evolve with the harness. Experiments on GAIA2 and Terminal‑Bench 2.0 show consistent improvements in harness performance, with Pass@1 gains of 4.4 and 7.5 percentage points over fixed‑order baselines.
arXiv:2605. 22166v3 Announce Type: replace Abstract: LLM agents are shaped not only by their language models, but also by the runtime harness that mediates observation, tool use, action execution, feedback interpretation, and trajectory control.
arXiv:2610.16523v1 Announce Type: new Abstract: Training LLM agents to interact with users over multiple turns is challenging because the learning signal depends not only on the agent, but also on th...
arXiv:2608.05446v2 Announce Type: replace Abstract: Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, recover from failures, and reuse experie...
arXiv:2610.08761v1 Announce Type: new Abstract: Self-improving policies continually expose new failure patterns, changing what their judges must be able to verify. However, current fixed judges const...
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.
arXiv:2606.03963v4 Announce Type: replace-cross Abstract: Deep reinforcement learning enables autonomous robots to learn complex navigation tasks, but still relies heavily on time consuming manual re...
arXiv:2610.15691v1 Announce Type: new Abstract: Existing reinforcement learning (RL) largely focuses on optimizing learning algorithms within a pre-defined task formulation, while applying RL to new...
EvoBelief is a self‑evolving world model that represents environment knowledge as falsifiable hypotheses, allowing an LLM agent to update its beliefs during deployment. The system generates hypotheses when unexpected outcomes or unknowns arise, validates them through observations and controlled experiments, and then uses the confirmed rules to guide predictions or plans. Across benchmarks such as ALFWorld, MiniGrid, and DiscoveryWorld, EvoBelief improves task performance, revises stale rules, and discovers quantitative laws, outperforming baseline frozen world models.
arXiv:2510.15047v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) as agents often fail to improve in new environments. We identify and characterize a failure mode we call explora...