paper-with-me

홈 › Papers

Composing Agents to Minimize Worst-case Risk

2025-06-05 · Guruprerana Shabadi, Rajeev Alur

From software development to robot control, modern agentic systems decompose complex objectives into a sequence of subtasks and choose a set of specialized AI agents to complete them. We formalize an agentic workflow as a directed acyclic graph, called an agent graph, where edges represent AI agents and paths correspond to feasible compositions of agents. When deploying these systems in the real world, we need to choose compositions of agents that not only maximize the task success, but also minimize risk where the risk captures requirements like safety, fairness, and privacy. This additionally requires carefully analyzing the low-probability (tail) behaviors of compositions of agents. In this work, we consider worst-case risk minimization over the set of feasible agent compositions. We define worst-case risk as the tail quantile -- also known as value-at-risk -- of the loss distribution of the agent composition where the loss quantifies the risk associated with agent behaviors. We introduce an efficient algorithm that traverses the agent graph and finds a near-optimal composition of agents by approximating the value-at-risk via a union bound and dynamic programming. Furthermore, we prove that the approximation is near-optimal asymptotically for a broad class of practical loss functions. To evaluate our framework, we consider a suite of video game-like control benchmarks that require composing several agents trained with reinforcement learning and demonstrate our algorithm's effectiveness in approximating the value-at-risk and identifying the optimal agent composition.

📄 PDF Abstract BibTeX arXiv:2506.04632

Code (1)

guruprerana/worm 공식 구현

Tasks

Fairness

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Robustness and risk-sensitivity in Markov decision processes

2012-12-01 · NeurIPS 2012 12 · Takayuki Osogami

We uncover relations between robust MDPs and risk-sensitive MDPs. The objective of a robust MDP is to minimize a function, such as the expectation of cumulative cost, for the worst case when the parameters have uncertai…

Sensitivity

Principled learning method for Wasserstein distributionally robust optimization with local perturbations

2020-06-05 · ICML 2020 1 · Yongchan Kwon, Wonyoung Kim, Joong-Ho Won, Myunghee Cho Paik

Wasserstein distributionally robust optimization (WDRO) attempts to learn a model that minimizes the local worst-case risk in the vicinity of the empirical data distribution defined by Wasserstein ball. While WDRO has re…

image-classificationImage Classification

Learning Robust Options by Conditional Value at Risk Optimization

2019-05-22 · NeurIPS 2019 12 · Takuya Hiraoka, Takahisa Imagawa, Tatsuya Mori, Takashi Onishi 외

Options are generally learned by using an inaccurate environment model (or simulator), which contains uncertain model parameters. While there are several methods to learn options that are robust against the uncertainty o…

Worst-case values of target semi-variances with applications to robust portfolio selection

2024-10-02 · Jun Cai, Zhanyi Jiao, Tiantian Mao

The expected regret and target semi-variance are two of the most important risk measures for downside risk. When the distribution of a loss is uncertain, and only partial information of the loss is known, their worst-cas…

Optimal Decision-Making Based on Prediction Sets

2026-02-01 · Tao Wang, Edgar Dobriban arxiv

Prediction sets can wrap around any ML model to cover unknown test outcomes with a guaranteed probability. Yet, it remains unclear how to use them optimally for downstream decision-making. Here, we propose a decision-the…

Medical Diagnosis