Monitored Markov Decision Processes
Paper • 2402.06819 • Published
Read Later 📚
Interesting papers on AI, LLMs, etc. to add to reading list
-
-
Generalization in Monitored Markov Decision Processes (Mon-MDPs)
Paper • 2505.08988 • Published -
Bayesian Risk Markov Decision Processes
Paper • 2106.02558 • Published -
Sotopia-RL: Reward Design for Social Intelligence
Paper • 2508.03905 • Published • 23 -
RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents
Paper • 2507.03112 • Published • 34 -
LIFELONG SOTOPIA: Evaluating Social Intelligence of Language Agents Over Lifelong Social Interactions
Paper • 2506.12666 • Published -
A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning
Paper • 2507.14295 • Published • 14 -
Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
Paper • 2507.17746 • Published • 5 -
Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback
Paper • 2410.19133 • Published • 11 -
Eliciting Human Preferences with Language Models
Paper • 2310.11589 • Published -
Deep reinforcement learning from human preferences
Paper • 1706.03741 • Published • 4 -
Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
Paper • 2502.19328 • Published • 23 -
MetaMetrics: Calibrating Metrics For Generation Tasks Using Human Preferences
Paper • 2410.02381 • Published • 1 -
OpenAgents: An Open Platform for Language Agents in the Wild
Paper • 2310.10634 • Published • 9 -
Language Agents as Optimizable Graphs
Paper • 2402.16823 • Published • 3 -
SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals
Paper • 2406.04784 • Published • 2 -
Aviary: training language agents on challenging scientific tasks
Paper • 2412.21154 • Published -
One STEP at a time: Language Agents are Stepwise Planners
Paper • 2411.08432 • Published -
Language agents achieve superhuman synthesis of scientific knowledge
Paper • 2409.13740 • Published -
ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy
Paper • 2403.14589 • Published -
A Trembling House of Cards? Mapping Adversarial Attacks against Language Agents
Paper • 2402.10196 • Published -
Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game
Paper • 2310.18940 • Published -
Reinforcing Language Agents via Policy Optimization with Action Decomposition
Paper • 2405.15821 • Published -
Reflexion: Language Agents with Verbal Reinforcement Learning
Paper • 2303.11366 • Published • 6 -
Hi-Agent: Hierarchical Vision-Language Agents for Mobile Device Control
Paper • 2510.14388 • Published -
Emergent Social Intelligence Risks in Generative Multi-Agent Systems
Paper • 2603.27771 • Published • 50 -
SocialVeil: Probing Social Intelligence of Language Agents under Communication Barriers
Paper • 2602.05115 • Published • 20 -
AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios
Paper • 2410.19346 • Published -
TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence
Paper • 2505.24500 • Published • 12 -
Digital Life Project: Autonomous 3D Characters with Social Intelligence
Paper • 2312.04547 • Published -
One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence
Paper • 2602.03109 • Published -
MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems
Paper • 2505.18943 • Published • 25 -
SOTOPIA-Ï€: Interactive Learning of Socially Intelligent Language Agents
Paper • 2403.08715 • Published • 21 -
Rethinking Theory of Mind Benchmarks for LLMs: Towards A User-Centered Perspective
Paper • 2504.10839 • Published -
AI Can Learn Scientific Taste
Paper • 2603.14473 • Published • 415 -
InCoder-32B: Code Foundation Model for Industrial Scenarios
Paper • 2603.16790 • Published • 306 -
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning
Paper • 2603.04597 • Published • 210 -
MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification
Paper • 2603.15726 • Published • 184 -
Qianfan-OCR: A Unified End-to-End Model for Document Intelligence
Paper • 2603.13398 • Published • 152 -
OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
Paper • 2603.15594 • Published • 148 -
Efficient Reasoning with Balanced Thinking
Paper • 2603.12372 • Published • 143 -
MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
Paper • 2603.17187 • Published • 136 -
Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning
Paper • 1810.03043 • Published