Self-Regulation and Requesting Interventions
- URL: http://arxiv.org/abs/2502.04576v1
- Date: Fri, 07 Feb 2025 00:06:17 GMT
- Title: Self-Regulation and Requesting Interventions
- Authors: So Yeon Min, Yue Wu, Jimin Sun, Max Kaufmann, Fahim Tajwar, Yonatan Bisk, Ruslan Salakhutdinov,
- Abstract summary: We propose an offline framework that trains a "helper" policy to request interventions.<n>We score optimal intervention timing with PRMs and train the helper model on these labeled trajectories.<n>This offline approach significantly reduces costly intervention calls during training.
- Score: 63.5863047447313
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Human intelligence involves metacognitive abilities like self-regulation, recognizing limitations, and seeking assistance only when needed. While LLM Agents excel in many domains, they often lack this awareness. Overconfident agents risk catastrophic failures, while those that seek help excessively hinder efficiency. A key challenge is enabling agents with a limited intervention budget $C$ is to decide when to request assistance. In this paper, we propose an offline framework that trains a "helper" policy to request interventions, such as more powerful models or test-time compute, by combining LLM-based process reward models (PRMs) with tabular reinforcement learning. Using state transitions collected offline, we score optimal intervention timing with PRMs and train the helper model on these labeled trajectories. This offline approach significantly reduces costly intervention calls during training. Furthermore, the integration of PRMs with tabular RL enhances robustness to off-policy data while avoiding the inefficiencies of deep RL. We empirically find that our method delivers optimal helper behavior.
Related papers
- Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner [31.033131727230277]
Large reasoning models (LRMs) have recently shown promise in solving complex math problems when optimized with Reinforcement Learning (RL)<n>We propose a novel intrinsic signal-driven generative process evaluation mechanism operating at the thought level to address major bottlenecks in RL-based training.<n>Experiments on 1.5B and 7B parameter LRMs demonstrate that our method achieves higher problem-solving accuracy with significantly fewer training samples than outcome-only reward baselines.
arXiv Detail & Related papers (2025-07-31T07:54:58Z) - Agentic Reinforced Policy Optimization [66.96989268893932]
Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
arXiv Detail & Related papers (2025-07-26T07:53:11Z) - Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems [54.709976343045824]
Current offline reinforcement learning (RL) methods face substantial challenges when applied to sparse advertising scenarios.<n>We propose MTORL, a novel multi-task offline RL model that targets two key objectives.<n>We employ multi-task learning to decode actions and rewards, simultaneously addressing channel recommendation and budget allocation.
arXiv Detail & Related papers (2025-06-29T05:05:13Z) - Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay [61.823835392216544]
Reinforcement learning (RL) has become an effective approach for fine-tuning large language models (LLMs)<n>We propose two techniques to improve data efficiency in LLM RL fine-tuning: difficulty-targeted online data selection and rollout replay.<n>Our method reduces RL fine-tuning time by 25% to 65% to reach the same level of performance as the original GRPO algorithm.
arXiv Detail & Related papers (2025-06-05T17:55:43Z) - Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL [62.984693936073974]
Large language models (LLMs) excel in tasks like question answering and dialogue.<n>Complex tasks requiring interaction, such as negotiation and persuasion, require additional long-horizon reasoning and planning.<n>We propose a novel approach that uses goal-conditioned value functions to guide the reasoning of LLM agents.
arXiv Detail & Related papers (2025-05-23T16:51:54Z) - Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing [14.114970711442512]
This paper introduces Attention Pruning, a fairness-aware simulated annealing approach to prune attention heads in large language models (LLMs)
Our experiments show that Attention Pruning achieves up to $40%$ reduction in gender bias and outperforms the state-of-the-art bias mitigation strategies.
arXiv Detail & Related papers (2025-03-20T03:02:32Z) - From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process.<n>We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
arXiv Detail & Related papers (2024-11-06T10:35:11Z) - OffRIPP: Offline RL-based Informative Path Planning [12.705099730591671]
IPP is a crucial task in robotics, where agents must design paths to gather valuable information about a target environment.
We propose an offline RL-based IPP framework that optimized information gain without requiring real-time interaction during training.
We validate the framework through extensive simulations and real-world experiments.
arXiv Detail & Related papers (2024-09-25T11:30:59Z) - Augmenting Unsupervised Reinforcement Learning with Self-Reference [63.68018737038331]
Humans possess the ability to draw on past experiences explicitly when learning new tasks.
We propose the Self-Reference (SR) approach, an add-on module explicitly designed to leverage historical information.
Our approach achieves state-of-the-art results in terms of Interquartile Mean (IQM) performance and Optimality Gap reduction on the Unsupervised Reinforcement Learning Benchmark.
arXiv Detail & Related papers (2023-11-16T09:07:34Z) - Action-Quantized Offline Reinforcement Learning for Robotic Skill
Learning [68.16998247593209]
offline reinforcement learning (RL) paradigm provides recipe to convert static behavior datasets into policies that can perform better than the policy that collected the data.
In this paper, we propose an adaptive scheme for action quantization.
We show that several state-of-the-art offline RL methods such as IQL, CQL, and BRAC improve in performance on benchmarks when combined with our proposed discretization scheme.
arXiv Detail & Related papers (2023-10-18T06:07:10Z) - BCRLSP: An Offline Reinforcement Learning Framework for Sequential
Targeted Promotion [8.499811428928071]
We propose the Budget Constrained Reinforcement Learning for Sequential Promotion framework to determine the value of cash bonuses to be sent to users.
We show that BCRLSP achieves a higher long-term customer retention rate and a lower cost than various baselines.
arXiv Detail & Related papers (2022-07-16T00:10:12Z) - Learning Cooperative Multi-Agent Policies with Partial Reward Decoupling [13.915157044948364]
One of the preeminent obstacles to scaling multi-agent reinforcement learning is assigning credit to individual agents' actions.
In this paper, we address this credit assignment problem with an approach that we call textitpartial reward decoupling (PRD)
PRD decomposes large cooperative multi-agent RL problems into decoupled subproblems involving subsets of agents, thereby simplifying credit assignment.
arXiv Detail & Related papers (2021-12-23T17:48:04Z) - Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement
Learning with Actor Rectification [74.10976684469435]
offline reinforcement learning (RL) algorithms can be transferred to multi-agent settings directly.
We propose a simple yet effective method, Offline Multi-Agent RL with Actor Rectification (OMAR), to tackle this critical challenge.
OMAR significantly outperforms strong baselines with state-of-the-art performance in multi-agent continuous control benchmarks.
arXiv Detail & Related papers (2021-11-22T13:27:42Z) - Contingency-Aware Influence Maximization: A Reinforcement Learning
Approach [52.109536198330126]
influence (IM) problem aims at finding a subset of seed nodes in a social network that maximize the spread of influence.
In this study, we focus on a sub-class of IM problems, where whether the nodes are willing to be the seeds when being invited is uncertain, called contingency-aware IM.
Despite the initial success, a major practical obstacle in promoting the solutions to more communities is the tremendous runtime of the greedy algorithms.
arXiv Detail & Related papers (2021-06-13T16:42:22Z) - Believe What You See: Implicit Constraint Approach for Offline
Multi-Agent Reinforcement Learning [16.707045765042505]
Current offline RL algorithms are ineffective in multi-agent systems due to the accumulated extrapolation error.
We propose a novel offline RL algorithm, named Implicit Constraint Q-learning (ICQ), which effectively alleviates the extrapolation error.
Experimental results demonstrate that the extrapolation error is reduced to almost zero and insensitive to the number of agents.
arXiv Detail & Related papers (2021-06-07T08:02:31Z) - Hybrid Imitation Learning for Real-Time Service Restoration in Resilient
Distribution Systems [4.634828363888443]
Self-healing capability is one of the most critical factors for a resilient distribution system.
These agents should be equipped with a predesigned decision policy to meet real-time requirements.
In this paper, we propose the imitation learning (IL) framework to train such policies.
arXiv Detail & Related papers (2020-11-29T22:51:05Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.