← Back to all news
arXiv AI By Molly Wang (Imperial Business School)

Spawn Freely, Act Sparingly: Progressive Risk Vesting for Recursive LLM-Agent Trees

Read the original on arXiv AI →

The paper introduces Progressive Risk Vesting (PRV), a framework for controlling the authority of recursive large language model agents that spawn specialist branches. PRV maintains a risk budget in escrow, debiting it as branches are activated, and provides theoretical guarantees on harm bounds for adaptively generated trees. The authors analyze how risk behaves relative to an authority reproduction number, derive risk and compute shadow prices, and suggest a design rule to search broadly in a sandbox while granting recursive authority sparingly.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Oct 28

CASEL: Consequence-Aware Selective Execution for Reliable Long-Horizon Tool-Using Agents

CASEL (Consequence-Aware Selective Execution Layer) is a runtime allocation policy for tool‑using language agents that chooses among direct execution, verification, sandboxing, clarification, approval, and abstention for each proposed tool call. It combines calibrated failure probability, state‑dependent consequence, reversibility, ambiguity, and evidence freshness to minimize a per‑mode cost. In controlled simulations, CASEL cuts harmful‑side‑effect trajectories from 14.75 % to 7.02 % and reduces mean normalized harm from 0.184 to 0.123 compared to an uncertainty‑ranked gate.

By Yanyan Zhang, Fei Shen, Ting Yan, Hao Zhang
agents
More like this →
arXiv AI
Aug 28

Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents

The paper demonstrates that safety mechanisms for autonomous large language model agents fail to compose across iterative loops, as trajectory‑scoped monitors cannot detect attacks whose evidence is spread over multiple iterations. It introduces LoopHarness, a system that maintains a persistent, non‑decaying safety state across loops, bounding unauthorized actions with a constant that does not grow with the number of iterations. The authors provide a comprehensive evaluation protocol, including attacks that require cross‑iteration evidence, module ablations, and adaptive white‑box red‑team testing.

By Chenhao Wu, Haoxuan Jia, Yang Liu, Yingguang Yang, Yuhan Lin, Chongyang Zhang, Hao Zheng, Yulin Huang, Jianshen Zhang, Yongzhi Qi, Shang Luo, Kefu Xu, Jifeng Zhu, Bin Chong
llmsagentssafety
More like this →
arXiv Computation and Language
Oct 1

OPTS-TTPO: Enhancing Finite-Sample Policy-Gradient Learning with Tree Search

arXiv:2609.40035v1 Announce Type: new Abstract: The policy-gradient theorem gives the exact gradient under the current policy, but finite on-policy samples may miss rare high-return trajectories. We...

By Junyu Lu, Shichao Weng, Zhiqiang Wang, Haojie Luo, Jingfan Zhang, Yuhua Zhou, Cheng Du, Yuzhuo Zhang, Xi Li, Jinwei Du, Tiancheng Feng, Chuan Xiao, Shuyuan Zheng
reinforcement-learningsafety
More like this →
arXiv AI
Oct 2

Authorization for Self-Modifying AI Agent Populations: Conserving Authority across Replacement, Forking, and Rollback

The paper introduces "authorization succession," a framework that preserves authority across self‑modifying AI agent populations that can replace, fork, or roll back. It defines a protocol binding each generation to a manifest, root, unique parent, lineage, and population sequence, and establishes invariants that control root‑lifetime consumption and population exposure. The authors prove properties such as population‑safe succession, fork conservation, and rollback non‑reminting, and validate the approach with an executable evaluation covering 32 decisions and external adapters for two mutation systems.

By Genliang Zhu, Chu Wang
agents
More like this →