arXiv AI September 17, 2026 By Riyaaz Shaik, Chandru Venkataraman

REVERSAL-BENCH: A Reversibility Axis and Reset Oracle for Measuring the Reset-Free RL Cliff

REVERSAL-BENCH is a benchmark that introduces a continuous reversibility parameter ρ∈[0,1] and a reset oracle to evaluate how well reinforcement learning agents can recover from irreversible states across eight manipulation tasks in five physics engines. Experiments show a sharp reversibility cliff: reset‑free agents become trapped in irrecoverable states as ρ increases, while episodic agents continue learning steadily. The benchmark also provides a large multi‑simulator dataset and demonstrates that safety shields can predict recoverability but only succeed when the agent can avoid the trap.

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.

arXiv Machine Learning

Jun 11

UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning

arXiv:2606. 12372v1 Announce Type: cross Abstract: Human-in-the-loop reinforcement learning (HiL-RL) has emerged as an effective paradigm for real-world robotic manipulation, enabling online policy improvement with human guidance.

By Haoyuan Deng, Yitong Gao, Yudong Lin, Haichao Liu, Zhenyu Wu, Ziwei Wang

agents reinforcement-learning robotics benchmarks

arXiv Machine Learning

Jul 21

Stochastic Resetting Accelerates Reinforcement Learning Beyond Random Search

arXiv:2603. 16842v2 Announce Type: replace Abstract: Stochastic resetting -- intermittently returning a process to a fixed reference state -- has emerged as an effective mechanism for optimizing first-passage properties.

By Jello Zhou, David J. Schwab, Vudtiwat Ngampruetikorn

agents reinforcement-learning

arXiv Machine Learning

Jun 16

Replay What Matters: Off-Policy Replay for Efficient LLM Reinforcement Unlearning

arXiv:2606. 15333v1 Announce Type: cross Abstract: LLM unlearning has emerged as a cost-effective alternative to full retraining for removing hazardous knowledge from pretrained models while preserving general utility.

By Zirui Pang, Chenlong Zhang, Haosheng Tan, Zhuoran Jin, Jiaheng Wei, Zixin Zhong

llms reinforcement-learning benchmarks

arXiv AI

3d ago

Loop-Free Inverse Reinforcement Learning via Sequential Value Recovery with Q-Score Matching

arXiv:2609.38955v1 Announce Type: cross Abstract: Inverse Reinforcement Learning (IRL) aims to recover a reward function that explains expert demonstrations. Existing IRL methods typically rely on a...

By Yang chen, Yitan Zhang, Michael Witbrock, Shuyue Hu

diffusion reinforcement-learning benchmarks

arXiv AI

Aug 13

Retry, Switch, or Abstain? Learning Strategy-Aware Tool-Use Policies via Controlled Error Injection

arXiv:2608. 11977v1 Announce Type: new Abstract: Tool-using LLM agents are commonly trained and evaluated in environments where tool calls succeed reliably, yet deployed tools can fail transiently, persistently, or silently.

By Chaoran Chen, Vy Nguyen, Ziji Zhang, Abhinav Gullapalli, Ziyi Wang, Yuxuan Lu, Dakuo Wang, Jing Huang, Zhou Yu, Jin Lai

llms agents reinforcement-learning benchmarks

arXiv AI

Sep 18

From Rollout to Reset: A Graph-Based Harness for Autonomous Long-Horizon Manipulation Evaluation

The paper introduces HALTER, a graph-based system that automates the reset and evaluation of long-horizon robot manipulation tasks. HALTER constructs a spatial scene graph from point clouds and vision models, uses an LLM to score rollouts, plan resets, and verify success, all without labeled success images. In experiments on a Franka arm, HALTER restores scenes in 76% of episodes, improves skill completion estimation, and reduces operator time by 72% compared to manual reset.

By Jing Jiang, Yue Yang, Xinkai Jiang, Gedas Bertasius, Daniel J. Szafir, Rudolf Lioutikov

llms agents robotics

One email a morning, machine-written

Related stories

UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning

Stochastic Resetting Accelerates Reinforcement Learning Beyond Random Search

Replay What Matters: Off-Policy Replay for Efficient LLM Reinforcement Unlearning

Loop-Free Inverse Reinforcement Learning via Sequential Value Recovery with Q-Score Matching

Retry, Switch, or Abstain? Learning Strategy-Aware Tool-Use Policies via Controlled Error Injection

From Rollout to Reset: A Graph-Based Harness for Autonomous Long-Horizon Manipulation Evaluation