{"total":66,"rows":[{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251,"area":"agents"},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912,"area":"alignment"},{"id":"2104.05218","title":"FUDGE: Controlled Text Generation With Future Discriminators","created":"2021-04-12","cited_by_count":376,"area":null},{"id":"2507.11473","title":"Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety","created":"2025-07-15","cited_by_count":249,"area":"lr"},{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237,"area":"safety"},{"id":"2210.13312","title":"Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs","created":"2022-10-24","cited_by_count":220,"area":"wm"},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2208.07998","title":"What Artificial Neural Networks Can Tell Us About Human Language Acquisition","created":"2022-08-17","cited_by_count":99,"area":null},{"id":"2407.14622","title":"BOND: Aligning LLMs with Best-of-N Distillation","created":"2024-07-19","cited_by_count":76,"area":"alignment"},{"id":"2112.07544","title":"Modeling Strong and Human-Like Gameplay with KL-Regularized Search","created":"2021-12-14","cited_by_count":50,"area":"offlinerl"},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2106.02668","title":"Emergent Communication of Generalizations","created":"2021-06-04","cited_by_count":42,"area":null},{"id":"2401.01312","title":"LLM Harmony: Multi-Agent Communication for Problem Solving","created":"2024-01-02","cited_by_count":35,"area":"agents"},{"id":"2312.07551","title":"Language Model Alignment with Elastic Reset","created":"2023-12-06","cited_by_count":34,"area":"alignment"},{"id":"2108.01828","title":"Emergent Discrete Communication in Semantic Spaces","created":"2021-08-04","cited_by_count":20,"area":null},{"id":"2404.19409","title":"Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning","created":"2024-04-30","cited_by_count":20,"area":"alignment"},{"id":"2203.13344","title":"Linking Emergent and Natural Languages via Corpus Transfer","created":"2022-03-24","cited_by_count":19,"area":null},{"id":"2409.17348","title":"Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication","created":"2024-09-25","cited_by_count":17,"area":"agents"},{"id":"2303.01502","title":"Computational Language Acquisition with Theory of Mind","created":"2023-03-02","cited_by_count":15,"area":null},{"id":"2405.21028","title":"LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models","created":"2024-05-31","cited_by_count":15,"area":null},{"id":"2408.04220","title":"Diffusion Guided Language Modeling","created":"2024-08-08","cited_by_count":15,"area":"diffusion"},{"id":"2203.13685","title":"Learning to Mediate Disparities Towards Pragmatic Communication","created":"2022-03-25","cited_by_count":14,"area":null},{"id":"2308.02541","title":"Towards More Human-like AI Communication: A Review of Emergent Communication Research","created":"2023-08-01","cited_by_count":13,"area":null},{"id":"2301.13083","title":"Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-off","created":"2023-01-30","cited_by_count":12,"area":null},{"id":"2311.04453","title":"Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments","created":"2023-11-08","cited_by_count":11,"area":null},{"id":"2509.15714","title":"Once Upon a Time: Interactive Learning for Storytelling with Small Language Models","created":"2025-09-19","cited_by_count":11,"area":null},{"id":"2110.14241","title":"Dynamic population-based meta-learning for multi-agent communication with natural language","created":"2021-10-27","cited_by_count":10,"area":null},{"id":"2110.05422","title":"Calibrate your listeners! Robust communication-based training for pragmatic speakers","created":"2021-10-11","cited_by_count":9,"area":null},{"id":"2510.20411","title":"Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction","created":"2025-10-23","cited_by_count":9,"area":null},{"id":"2104.07219","title":"Multitasking Inhibits Semantic Drift","created":"2021-04-15","cited_by_count":8,"area":null},{"id":"2407.13999","title":"NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communication","created":"2024-07-19","cited_by_count":8,"area":null},{"id":"2201.01816","title":"Hidden Agenda: a Social Deduction Game with Diverse Learned Equilibria","created":"2022-01-05","cited_by_count":7,"area":null},{"id":"2211.02412","title":"Emergent Quantized Communication","created":"2022-11-04","cited_by_count":7,"area":null},{"id":"2301.05149","title":"Define, Evaluate, and Improve Task-Oriented Cognitive Capabilities for Instruction Generation Models","created":"2022-12-21","cited_by_count":7,"area":null},{"id":"2305.19933","title":"Speaking the Language of Your Listener: Audience-Aware Adaptation via Plug-and-Play Theory of Mind","created":"2023-05-31","cited_by_count":7,"area":null},{"id":"2510.24023","title":"Success and Cost Elicit Convention Formation for Efficient Communication","created":"2025-10-28","cited_by_count":7,"area":null},{"id":"2206.03139","title":"Intra-agent speech permits zero-shot task acquisition","created":"2022-06-07","cited_by_count":5,"area":null},{"id":"2305.12777","title":"Evaluating Pragmatic Abilities of Image Captioners on A3DS","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2311.05740","title":"Generating Pragmatic Examples to Train Neural Program Synthesizers","created":"2023-11-09","cited_by_count":5,"area":null},{"id":"2505.06904","title":"EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation","created":"2025-05-11","cited_by_count":5,"area":"agents"},{"id":"2110.11404","title":"Statistical discrimination in learning agents","created":"2021-10-21","cited_by_count":4,"area":null},{"id":"2207.07025","title":"Learning to translate by learning to communicate","created":"2022-07-14","cited_by_count":4,"area":null},{"id":"2306.08818","title":"Pragmatic Inference with a CLIP Listener for Contrastive Captioning","created":"2023-06-15","cited_by_count":4,"area":null},{"id":"2502.05892","title":"A Distributional Perspective on Word Learning in Neural Language Models","created":"2025-02-09","cited_by_count":4,"area":null},{"id":"2505.05970","title":"Towards Developmentally Plausible Rewards: Communicative Success as a Learning Signal for Interactive Language Models","created":"2025-05-09","cited_by_count":4,"area":null},{"id":"2206.08349","title":"Know your audience: specializing grounded language models with listener subtraction","created":"2022-06-16","cited_by_count":3,"area":null},{"id":"2310.11282","title":"ChapGTP, ILLC's Attempt at Raising a BabyLM: Improving Data Efficiency by Automatic Task Formation","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2407.06486","title":"Optimal Decision Making Through Scenario Simulations Using Large Language Models","created":"2024-07-09","cited_by_count":3,"area":null},{"id":"2601.12535","title":"Improving Low-Resource Machine Translation via Round-Trip Reinforcement Learning","created":"2026-01-18","cited_by_count":3,"area":"alignment"},{"id":"2604.00010","title":"Can LLMs Perceive Time? An Empirical Investigation","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2109.09371","title":"Learning Natural Language Generation from Scratch","created":"2021-09-20","cited_by_count":2,"area":null},{"id":"2303.04544","title":"Models of symbol emergence in communication: a conceptual review and a guide for avoiding local minima","created":"2023-03-08","cited_by_count":2,"area":null},{"id":"2410.05851","title":"Communicating with Speakers and Listeners of Different Pragmatic Levels","created":"2024-10-08","cited_by_count":2,"area":"lr"},{"id":"2506.02739","title":"Why do AI agents communicate in human language?","created":"2025-06-03","cited_by_count":2,"area":"agents"},{"id":"2108.05799","title":"Scalable pragmatic communication via self-supervision","created":"2021-08-12","cited_by_count":1,"area":null},{"id":"2209.08206","title":"Selective Token Generation for Few-shot Natural Language Generation","created":"2022-09-17","cited_by_count":1,"area":null},{"id":"2309.11753","title":"Improve the efficiency of deep reinforcement learning through semantic exploration guided by natural language","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2601.10169","title":"CtD: Composition through Decomposition in Emergent Communication","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2101.10369","title":"Effective Communications: A Joint Learning and Communication Framework for Multi-Agent Reinforcement Learning over Noisy Channels","created":"2021-01-02","cited_by_count":0,"area":null},{"id":"2311.04474","title":"Emergent Communication for Rules Reasoning","created":"2023-11-08","cited_by_count":0,"area":null},{"id":"2408.01877","title":"Improving Zero-Shot ObjectNav with Generative Communication","created":"2024-08-03","cited_by_count":0,"area":null},{"id":"2503.04940","title":"VQEL: Enabling Self-Play in Emergent Language Games via Agent-Internal Vector Quantization","created":"2025-03-06","cited_by_count":0,"area":null},{"id":"2509.12179","title":"Co-Alignment: Rethinking Alignment as Bidirectional Human-AI Cognitive Adaptation","created":"2025-09-15","cited_by_count":0,"area":"alignment"},{"id":"2606.10582","title":"Drawing with Strangers: Population Scaling Drives Zero-Shot Mutual Intelligibility in Emergent Sketching","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2610.02015","title":"On Language Drift during RLVR Post-Training","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.18727","title":"On the Monitorability of Natural Language Autoencoders: Identification vs Discrimination","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}