Large Language Model Policy Optimization

Follow this topic Ask about this topic

Momentum

13 papers in the last four weeks, against 2 the four weeks before. 0.2% of all new papers.

Jul 6Week of Sep 21

Latest papers 67

All topics

Grounding Large Language Models in DSGE Simulators for Policy Generation and Forecasting
Oct 1, 2026Aditya Dubey, Namah Gupta, Vinti AgarwalLarge Language Model Policy Optimization Simulation-Based Reinforcement Learning
Birla Institute of Technology and Science, Pilani, India
LLM Persona Unlearning
Sep 30, 2026Kemou Li, Zhuan Shi, Qizhou Wang +4Artificial Intelligence Personas Large Language Model Unlearning
State Key Laboratory of Internet of Things for Smart City, University of Macau · Mila – Québec AI Institute · McGill University +3
Explicit Trajectory Diversity for RL-Based Post-Training of LLM Agents
Sep 30, 2026Huaiyu Fu, Heng Cao, Hao Wang +2Large Language Model Policy Optimization Large Language Model Agents
Microsoft
BRIDGE: Bilevel Retrieval-Credit-Aware Agentic Reinforcement Learning
Sep 29, 2026Quan Xiao, Mingda Liu, Gaowen Liu +2Agentic Reinforcement Learning Large Language Model Policy Optimization
Department of Electrical and Computer Engineering, Cornell University · Institute of Integrated Research, Institute of Science Tokyo · Cisco Research
When Words Fall Short: Iterative Synergy Between Verbalized Reasoning and Hidden Features for LLM Confidence Estimation
Sep 28, 2026Yekun Xu, Ante Wang, Jingyi Ren +3Confidence Estimation Large Language Model Policy Optimization
College of AI, Tsinghua University, Beijing, China · Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China · Dept. of Comp. Sci. & Tech., Institute for AI, Tsinghua University, Beijing, China
RAISE: Reinforcing Access Control Policy Synthesis in LLMs via Symbolic Evaluation
Sep 27, 2026Yingming Zhou, Adarsh Vatsa, William EiersLarge Language Model Policy Optimization Access Control
Stevens Institute of Technology
NLPG: Natural-Language Policy Gradients for Self-Evolving Language Agents
Sep 27, 2026Xu Liu, WenZhang Wei, Jun Cao +4Large Language Model Policy Optimization Improvement
School of Electronic Information, Wuhan University, Wuhan 430079, China · School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China · State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China
From Policy Documents to Structured Survey Responses: Evaluating Large Language Models for Policy Monitoring
Sep 24, 2026Carolyn Cole, Matthias Deschryvere, Toqeer Ehsan +1Large Language Model Policy Optimization Survey
Reliable Intelligence Team, VTT Technical Research Centre of Finland Ltd., 02150 Espoo, Finland
onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction
Sep 21, 2026Lei Yang, Mengyin Liu, Jia Wang +9Large Language Model Annotations Large Language Model Alignment
StepFun · Xiamen University
Information-Time Proximal Policy Optimization
Sep 21, 2026Yongcheng Zeng, Xinyu Cui, Yan Song +9Frictive Policy Optimization Large Language Model Policy Optimization
Institute of Automation, Chinese Academy of Sciences, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, China · University College London +5
Smarter by the Moment: Environment-Driven Dynamic Policies for Continual LLM Improvement
Sep 15, 2026Ting-Wei Chang, Po-Chun Chen, Hen-Hsen Huang +1Large Language Model Policy Optimization Replay-Based Continual Learning
Department of Computer Science and Information Engineering, National Taiwan University, Taiwan · Institute of Information Science, Academia Sinica, Taiwan · AI Research Center (AINTU), National Taiwan University, Taiwan
Automated Design of Inventory Policy with Large Language Models: An Exploratory Study
Sep 8, 2026Fenghua Yang, Preet Baxi, Yi Zhang +4Inventory Control Large Language Model Policy Optimization
University of Michigan, Ann Arbor, MI 48109, USA · Stanford University, Stanford, CA 94305, USA · Queen’s University, Kingston, ON K7L 3N6, Canada +2
SiLR: Structure-Preserving Admission and Process Reward for LLM Tool Agents
Sep 7, 2026Chenyu Zhou, Qiliang Jiang, Shuning Wu +1Admissibility Large Language Model Policy Optimization
School of Engineering, Institute of Science Tokyo, Japan · College of Control Science and Engineering, Zhejiang University, China · Department of Electrical and Computer Engineering, National University of Singapore, Singapore
Can Large Language Models Anticipate Behavioral Responses to Social Policies? A Case of Pension Enrollment Prediction among China's Flexible Workers
Sep 4, 2026Yumiao Li, Peixin Liu, Donglin Di +2Large Language Model Policy Optimization Agent Behavior Modeling
School of Economics and Management, Tsinghua University, Beijing, China · Actuarial Science and Risk Management, University of Illinois Urbana-Champaign, Urbana, IL, USA · School of Computing, Harbin Institute of Technology, Harbin, China
GPS-Bench: A Governance Policy Benchmark for Automating Policy Analysis
Sep 3, 2026Linh Le, Melanie Bui, My Chiffon Nguyen +2Policy Evaluation Multi-Agent Simulations
1Lida Safety · 2ERA
Grounded, Compute-Efficient LLM Policy Agents for Energy-Poverty Equity in Physically-Constrained Peer-to-Peer Energy Markets
Sep 1, 2026Kunal Jadhav, Siddhesh MoreLarge Language Model Policy Optimization Natural Language Processing
Arizona State University
PersuaRL: Reinforcement Learning-Driven Multi-Expert Selection for Persuasive Dialogue Generation in Insurance
Sep 1, 2026Rohan Kirti, Akash Ghosh, Aryan Vats +5Persuasion Large Language Model Policy Optimization
Indian Institute of Technology Patna, India · Ramakrishna Mission Vivekananda Educational and Research Institute, India · Accenture Labs, Bangalore, India
An Agentic Retrobiosynthesis Framework with Learned Frontier Selection
Aug 31, 2026Philippe Meyer, Guillaume Gricourt, Thomas Duigou +2Large Language Model Policy Optimization Search-Augmented Reasoning
1Université Paris-Saclay, INRAE, AgroParisTech, Micalis Institute, Jouy-en-Josas, France
From Answers to Policies: Efficient In-Context Learning System through Emulating Expert Investigation
Aug 17, 2026Minh-Ha Nguyen, Ngoc-Ngo Quang Tran, Thuy Dung Nguyen +1Large Language Model Policy Optimization In-Context Learning
Department of Epidemiology, Vanderbilt University, Nashville, TN, USA · Department of Pediatrics, Vanderbilt University Medical Center, Nashville, TN, USA · Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN, USA +1
JustLLMGRPO: Radiographic Control for Chest X-Ray Generation
Aug 8, 2026Pengxiang Cai, Xiaohan Li, Anglin Liu +3Chest X-Ray Medical Image Generation
The Hong Kong University of Science and Technology (Guangzhou)
AdvPlan-Bench: Adversarial Evaluation of Structured Plan-Generation Agents
Aug 1, 2026Alina Kapanova, Arun Kanhai, Natan Vidra +1Adversarial Evaluation Multi-Agent Planning
Anote AI · Cornell University · CUNY +1
Learning an Interior Layout Policy in a Domain Specific Language Action Space
Jul 31, 2026Yuhao Lu, Weichen Zhang, Wenyi Xiao +23D Layout Generation Layouts
Taobao & Tmall Group of Alibaba
An Instrument to Evaluate Governance Proposals: AI Policy Analysis at Scale
Jul 30, 2026Paulo Carvao, Claudio Mayrink Verdun, Isabel Adler +1Artificial Intelligence Governance Eu Artificial Intelligence Act
Mossavar-Rahmani Center for Business and Government · Harvard Kennedy School · Harvard Kennedy School of Government +2
Compliance2LoRA: Personalizable On-Demand Safety Alignment on Arbitrary Policy Subsets via Hypernetwork-Generated LoRA Adapters
Jul 30, 2026Pankayaraj Pathmanathan, Furong HuangSafety Alignment Large Language Model Policy Optimization
University of Maryland College Park
Simulating Tenant Responses to Energy Policy Interventions with Transaction-Cost-Aware LLM Agent
Jul 27, 2026Weijie Xia, Stefanie Horian, Hanyue Huang +3User Simulation Large Language Model Policy Optimization
Delft University of Technology, Delft, The Netherlands · Technical University of Munich, Munich, Germany
ToolGuardian: Declarative Security for AI Agent-Tool Interactions
Jul 23, 2026Arun Ravindran, Saurabh DeochakeAuthorization Agentic Deployments
Department of Electrical and Computer Engineering University of North Carolina at Charlotte Charlotte, NC · SentinelOne Mountain View, CA
Co-Evolving LLM Evaluators and Policies via DynamicRubric
Jul 22, 2026Beining Wang, Weihang Su, Hongtao Tian +8Large Language Model Policy Optimization Large Language Model Evaluation
Department of Computer Science and Technology, Tsinghua University · 2WeChat, Tencent
A Formally Grounded ODRL Evaluator: Implementation and Comparison
Jul 17, 2026Jaime Osvaldo Salas, Paolo Pareti, Adeel Aslam +2Policy Evaluation Multi-Dimensional Evaluation
University of Southampton, University Road, Southampton, SO17 1BJ, UK
Pezego-HITL: A policy-grounded large language model architecture for agricultural extension in Ghana
Jul 15, 2026Shunbao Li, Zhipeng Yuan, Amoako Ofori +5Large Language Model Policy Optimization Precision Agriculture
School of Computer Science, University of Sheffield, Regent Court (CS), 211 Portobello, Sheffield, S1 4DP, United Kingdom · Institute for Environment and Sanitation Studies, College of Basic and Applied Sciences, University of Ghana, P. O. Box LG 209, Legon, Accra, Ghana · Mutus Tech Ltd, 54 St. James Street, Liverpool, L1 0AB, England
Agentic-V2X: Small Language Model Agents for Deadline-Aware V2X Scheduling in 5G/6G Networks
Jul 5, 2026Gerasimos Papanikolaou-Ntais, Alexandros Kaloxylos, Athanasios KanavosSchedulers Large Language Model Policy Optimization
Department of Informatics, University of Piraeus, 185 34 Piraeus, Greece · Department of Informatics and Telecommunications, University of Peloponnese, 221 31 Tripoli, Greece
AutoCedar: An Agentic Framework for Verifier-Guided Access Control Policy Synthesis
Jul 4, 2026Adarsh Vatsa, Sachi Shome, Yingming Zhou +1Access Control Large Language Model Policy Optimization
Stevens Institute of Technology
When Aggregate Alignment Misleads: Auditing Policy Repair Without Per-State Expert Actions
Jul 3, 2026Peiying Zhu, Sidi ChangLarge Language Model Policy Optimization Repair
Blossom AI San Francisco, USA · Blossom AI Labs Tokyo, Japan
DiPS: Dialogue Policy Selection for High-Stakes Persuasion Agents
Jul 2, 2026Tianyi Zhang, Mousumi Das, Abrar Anwar +2Persuasion Large Language Model Policy Optimization
University of Southern California
Joint Learning of Experiential Rules and Policies for Large Language Model Agents
Jun 25, 2026Shicheng Ye, Chao YuLarge Language Model Policy Optimization Large Language Model Agents
Sun Yat-sen University
AlgoEvolve: LLM-driven Meta-evolution of Algorithmic Trading Programs
Jun 24, 2026Dhruv Sharma, Gautam ShroffAlgorithmic Trading Evolutionary Search
Indraprastha Institute of Information Technology, Delhi
PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models
Jun 24, 2026Chang Wu, Junfeng Fang, Houcheng Jiang +5Safety Alignment Large Language Model Safety
Qwen Large Model Application Team, Alibaba · National University of Singapore · Zhongguancun Academy
A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions
Jun 15, 2026Jianghan Shen, Siqi Luo, Yue Li +9Large Language Model Policy Optimization Trajectory Generation
1Nanjing University · 2Shanghai Artificial Intelligence Laboratory · 3Shanghai Jiao Tong University +4
REFLEX: Reflective Evolution from LLM Experience
Jun 15, 2026Pan WangLarge Language Model Policy Optimization On-Policy Self-Evolution
University of Science and Technology of China, China.
CARE: Context-Aware Ranking Evolution with Executable Scoring Programs for Budgeted Reaction Optimization
Jun 12, 2026Guanyu Liu, Weiyi Kong, Chao Tang +5Large Language Model Policy Optimization Scientific Discovery
University of Macau · University of Toronto · UCLA +3
Carolina Guide: A Multi-Agent RAG System with Institutional Guardrails for Academic Policy Assistance
Jun 11, 2026Ben Torsion, Jun ZhouAcademic Integrity Agentic Retrieval-Augmented Generation Systems
University of South Carolina, Columbia, South Carolina, USA · University of South Carolina, Columbia, USA
Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents
Jun 11, 2026Saehun Chun, Wonje Choi, Sera Choi +2Large Language Model Policy Optimization Large Language Model Agents
Department of Computer Science and Engineering, Sungkyunkwan University, Suwon, Republic of Korea.
Trace2Policy: From Expert Behavior Traces to Self-Evolving Decision Agents
Jun 9, 2026Junli Zha, Jinbo Wang, Chao Zhou +1Large Language Model Policy Optimization Expert Demonstrations
SF Express
Capability-Aligned Hierarchical Learning for Tool-Augmented LLMs
Jun 8, 2026Haotong Yang, Ting Long, Yi ChangLarge Language Model Planning Large Language Model Policy Optimization
Jilin University
Distilling LLM Reasoning into an Interpretable Policy Tree for Human-AI Collaboration
Jun 7, 2026Beiwen Zhang, Yongheng Liang, Guowei Zou +2Large Language Model Policy Optimization Human-Ai Collaboration
Sun Yat-sen University
EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
Jun 2, 2026Guhong Chen, Yingcheng Shi, Yongbin Li +6On-Policy Self-Evolution Agentic Reinforcement Learning
1Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · 2Tongyi Lab , Alibaba Group · 3Alibaba Group +1
When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?
May 29, 2026Stephane Hatgis-Kessell, Emma BrunskillLarge Language Model Policy Optimization Frictive Policy Optimization
Department of Computer Science, Stanford University
Discovering Cooperative Pipelines: Autoresearch for Sequential Social Dilemmas
May 28, 2026Víctor GallegoLarge Language Model Policy Optimization
Komorebi AI Technologies
Diagnosing Live Within-Policy Instruction Conflicts in LLM Agents with Witnessed Resolution Profiles
May 27, 2026Lu Yan, Xuan Chen, Xiangyu ZhangLarge Language Model Policy Optimization Large Language Model Agents
Purdue University
UniMaia: Steering Chess Policies with Language for Human-like Play
May 26, 2026Sherman Siu, Lesley IsteadChess Large Language Model Policy Optimization
University of Waterloo · Carleton University
Reducing Political Manipulation with Consistency Training
May 21, 2026Long Phan, Devin Kim, Alexander Pan +3Large Language Model Bias Biases
Center for AI Safety · UC Berkeley
Modeling Pathology-Like Behavioral Patterns in Language Models Through Behavioral Fine-Tuning
May 21, 2026Nicola Milano, Davide MaroccoLarge Language Model Fine-Tuning Large Language Model Policy Optimization
University of Naples Federico II, Natural and Artificial Cognition Laboratory ”Orazio Miglino”, Department of Humanities
LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails
May 17, 2026Nanxi Li, Zhengyue Zhao, Chaowei XiaoStreaming Guardrails Large Language Model Policy Optimization
Johns Hopkins University
LLM4Branch: Large Language Model for Discovering Efficient Branching Policies of Integer Programs
May 11, 2026Zhinan Hou, Xingchen Li, Yankai Zhang +2Mixed-Integer Programming Large Language Model Policy Optimization
Department of Automation, BNRist, Tsinghua University, Beijing, China.
DRIP-R: A Benchmark for Decision-Making and Reasoning Under Real-World Policy Ambiguity in the Retail Domain
May 8, 2026Hsuvas Borkakoty, Sebastian Pohl, Cheng Wang +2Large Language Model Policy Optimization Agentic Benchmarks
Interdisciplinary Transformation University, Austria · Amazon, Berlin, Germany
Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective
May 8, 2026Yuheng Zhang, Chenlu Ye, Shuowei Jin +4Large Language Model Policy Optimization Bias-Variance Decomposition
UIUC · University of Michigan · Amazon
Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models
May 8, 2026Xiaoze Liu, Dhananjay Ram, Yuting Zhang +3Reinforcement Learning Post-Training Better Call Group Relative Policy Optimization
1Purdue University · *Work done during an internship at Amazon. · 2AWS Agentic AI
SHARP: A Self-Evolving Human-Auditable Rubric Policy for Financial Trading Agents
May 7, 2026Xiwen Chen, Wenhui Zhu, Songzhu Zheng +3Large Language Model Policy Optimization Credit Assignment
Morgan Stanley · Arizona State University · Columbia University +1
InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees
May 1, 2026Chenyu Huang, Jianghao Lin, Zhengyang Tang +4Inventory Control Large Language Model Policy Optimization
1Shanghai University of Finance and Economics · 2Shanghai Jiao Tong University · 3The Chinese University of Hong Kong, Shenzhen +2
Hybrid Policy Distillation for LLMs
Apr 22, 2026Wenhong Zhu, Ruobing Xie, Rui Wang +1Knowledge Distillation Large Language Model Policy Optimization
Department of Computer Science and Engineering, Shanghai Jiao Tong University · Shanghai Innovation Institute · Large Language Department, Tencent
Cognitive Policy-Driven LLM for Diagnosis and Intervention of Cognitive Distortions in Emotional Support Conversation
Apr 19, 2026Lin Zhong, Renjin Zhu, Shujuan Ma +4Emotional Support Conversation Task Cognitive Diagnosis
Harbin Institute of Technology, Shenzhen, China · City University of Macau, Macao SAR, China · Peng Cheng Laboratory, Shenzhen, China

Oct 1, 2026, cs.AIJ/K move · Enter open · S save

Grounding Large Language Models in DSGE Simulators for Policy Generation and Forecasting

Aditya Dubey, Namah Gupta, Vinti Agarwal

Birla Institute of Technology and Science, Pilani, India

Large Language Model Policy Optimization Simulation-Based Reinforcement Learning Economies Stochastic Reward Signal Data Generation

Open paper AskPDF arXiv

Large language models can produce economic policy responses that sound reasonable, but this does not show that their actions are consistent with economic dynamics. We test this by placing an instruction-tuned language model inside six Snowdrop-backed dynamic stochastic general equilibrium (DSGE) simulators. At each turn, the model observes the economy and a change in economic discourse, selects a bounded policy action, and receives the next simulated state and an economic reward. We implement a common Python interface for repeated rollouts, persistent shocks, state cloning, and rolling-horizon simulation. This setting creates a long-horizon credit-assignment problem. Policy effects may appear several quarters after an action is taken. PPO has a learned value function that can propagate delayed reward to earlier tokens through generalized advantage estimation. GRPO has no learned value function and instead assigns a group-relative advantage from complete rollout returns. It therefore cannot distinguish which earlier turn caused the outcome; if every rollout receives the same return, the normalized advantage is zero. We use PPO as the primary method and GRPO as a matched critic-free baseline. The experiments also test directional semantic signals, reward horizon, trajectory warm starts, cross-simulator transfer, and historically anchored pandemic and monetary-policy shocks. The objective is to judge policy actions by their simulated economic consequences rather than by plausible language alone.

Momentum

Related topics

Latest papers 67