SafeEvolve is an experience-driven framework that co‑evolves a harness and policy to improve safety alignment for LLM‑based agents. It uses on‑policy trajectory safety evidence to update safety prompts and hierarchical skills, producing auditable harness artifacts. The policy is trained via a two‑stage SFT‑RL pipeline that bootstraps with the evolved harness and then refines behavior through verifier‑decomposed rewards, yielding a better safety‑utility tradeoff on benchmarks such as AgentDojo.
Agentic ESOpt proposes using evolution strategies (ES) instead of reinforcement learning to fine‑tune large language‑model agents for long‑horizon tasks. ES offers model scalability, flexibility, and better long‑horizon credit assignment, enabling full‑parameter optimization with minimal GPU memory. The framework samples parameter perturbations, evaluates agents with rewards, and updates online, achieving notable performance gains on WebArena‑Lite and in test‑time prompt‑parameter co‑evolution.
By Zhi Zheng, Rongsheng Chen, Yunpeng Ba, Zhenkun Wang, Yee Whye Teh, Wee Sun Lee
arXiv:2606. 19236v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards algorithms like GRPO have emerged as the dominant post-training paradigm for complex reasoning in LLMs, yet commonly suffer from policy entropy collapse during training.
By Haipeng Luo, Qingfeng Sun, Songli Wu, Can Xu, Wenfeng Deng, Han Hu, Yansong Tang
arXiv:2602. 10429v2 Announce Type: replace-cross Abstract: AIvilization v0 is a publicly deployed large-scale artificial society that couples a resource-constrained sandbox with a unified LLM-agent architecture, aiming to sustain long-horizon autonomy while remaining executable under a rapidly changing environment.
By Wenkai Fan, Shurui Zhang, Xiaolong Wang, Haowei Yang, Tsz Wai Chan, Xingyan Chen, Junquan Bi, Zirui Zhou, Jia Liu, Kani Chen
arXiv:2608. 01548v2 Announce Type: replace Abstract: Language-first intelligence is constrained by which distinctions enter its symbolic record, which mappings its language--interpreter--environment complex can execute, and which possibilities can be realized with finite resources.
By Yi Liu
Hindsight relabeling which retroactively replacing a transition's goal with the outcome the agent actually achieved is an effective tool for improving sample-efficiency in Reinforcement Learning (RL)....
arXiv:2602. 07764v2 Announce Type: replace-cross Abstract: Multi-objective reinforcement learning (MORL) seeks to train agents capable of balancing conflicting objectives.
By Tanmay Ambadkar, Sourav Panda, Shreyash Kale, Jonathan Dodge, Abhinav Verma
arXiv:2605. 30719v2 Announce Type: replace-cross Abstract: We study when large language models (LLMs) can serve as effective black-box policy optimizers for reinforcement learning (RL) tasks, i.
By Stephane Hatgis-Kessell, Emma Brunskill
arXiv:2606. 30068v1 Announce Type: new Abstract: Joint-embedding predictive (JEPA-style) objectives learn representations by predicting future latents.
By Ayan Pendharkar
arXiv:2607. 04470v1 Announce Type: cross Abstract: Large Language Models (LLMs) offer a natural interface for translating human objectives into reward signals for cooperative multi-agent reinforcement learning (MARL), yet the training-time dynamics of this integration remain poorly understood.
By Faid Keddouri, Sohaib Houhou, Aissa Boulmerka, Nadir Farhi
The paper investigates hindsight relabeling in preference‑conditioned multi‑objective reinforcement learning (MORL). It finds that relabeling transitions with the achieved preference direction often harms performance, causing a phenomenon called Preference Coverage Collapse where the critic’s coverage narrows to a small region of the preference space. The authors propose a simple method, her_mix, that blends achieved and requested preferences, which restores performance across most settings and dramatically reduces abandoned preference mass.
By Baptiste Bonin, Caro Strickland, Audrey Durand
arXiv:2608. 09629v1 Announce Type: new Abstract: Self-evolving agents are usually built around prescribed optimization pipelines: the framework decides how to gather evidence, revise a persistent artifact, select candidates, and stop.
By Hui Xue, Fan Yang