{"total":76,"rows":[{"id":"2407.11511","title":"Multi-Step Reasoning with Large Language Models, a Survey","created":"2024-07-16","cited_by_count":143,"area":"lr"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2410.03642","title":"Aligning LLMs with Individual Preferences via Interaction","created":"2024-10-04","cited_by_count":63,"area":"alignment"},{"id":"2506.09026","title":"e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs","created":"2025-06-10","cited_by_count":59,"area":"lr"},{"id":"2411.05990","title":"Game-theoretic LLM: Agent Workflow for Negotiation Games","created":"2024-11-08","cited_by_count":56,"area":"agents"},{"id":"2504.16078","title":"LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities","created":"2025-04-22","cited_by_count":41,"area":"agents"},{"id":"2403.16843","title":"Do LLM Agents Have Regret? A Case Study in Online Learning and Games","created":"2024-03-25","cited_by_count":35,"area":"agents"},{"id":"2410.06238","title":"EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration","created":"2024-10-08","cited_by_count":34,"area":"lr"},{"id":"2507.00310","title":"AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise","created":"2025-06-30","cited_by_count":33,"area":null},{"id":"2502.17543","title":"Training a Generally Curious Agent","created":"2025-02-24","cited_by_count":31,"area":"agents"},{"id":"2506.06303","title":"Reward Is Enough: LLMs Are In-Context Reinforcement Learners","created":"2025-05-21","cited_by_count":31,"area":null},{"id":"2406.00244","title":"Controlling Large Language Model Agents with Entropic Activation Steering","created":"2024-06-01","cited_by_count":29,"area":"agents"},{"id":"2408.14511","title":"Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods","created":"2024-08-25","cited_by_count":29,"area":"lr"},{"id":"2410.05362","title":"LLMs Are In-Context Bandit Reinforcement Learners","created":"2024-10-07","cited_by_count":29,"area":null},{"id":"2406.00092","title":"Heads, Tails, and AI Fails: LLMs, Randomness, and Human Judgments","created":"2024-05-31","cited_by_count":26,"area":null},{"id":"2405.16376","title":"STRIDE: A Tool-Assisted LLM Agent Framework for Strategic and Interactive Decision-Making","created":"2024-05-25","cited_by_count":22,"area":"lr"},{"id":"2512.16848","title":"Meta-RL Induces Exploration in Language Agents","created":"2025-12-18","cited_by_count":21,"area":"lr"},{"id":"2501.13896","title":"GUI-Bee: Align GUI Action Grounding to Novel Environments via Autonomous Exploration","created":"2025-01-23","cited_by_count":18,"area":null},{"id":"2504.20997","title":"Toward Efficient Exploration by Large Language Model Agents","created":"2025-04-29","cited_by_count":17,"area":"agents"},{"id":"2406.12125","title":"Efficient Sequential Decision Making with Large Language Models","created":"2024-06-17","cited_by_count":16,"area":null},{"id":"2506.10341","title":"Formalizing Learning from Language Feedback with Provable Guarantees","created":"2025-06-12","cited_by_count":13,"area":null},{"id":"2407.05377","title":"Collective Innovation in Groups of Large Language Models","created":"2024-07-07","cited_by_count":11,"area":null},{"id":"2408.07461","title":"Problem Solving Through Human-AI Preference-Based Cooperation","created":"2024-08-14","cited_by_count":11,"area":null},{"id":"2410.20357","title":"Dynamics as Prompts: In-Context Learning for Sim-to-Real System Identifications","created":"2024-10-27","cited_by_count":10,"area":null},{"id":"2503.18825","title":"EconEvals: Benchmarks and Litmus Tests for Economic Decision-Making by LLM Agents","created":"2025-03-24","cited_by_count":10,"area":"agents"},{"id":"2506.00751","title":"Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?","created":"2025-05-31","cited_by_count":10,"area":"alignment"},{"id":"2412.06438","title":"Can foundation models actively gather information in interactive environments to test hypotheses?","created":"2024-12-09","cited_by_count":8,"area":null},{"id":"2502.00225","title":"Should You Use Your Large Language Model to Explore or Exploit?","created":"2025-01-31","cited_by_count":8,"area":null},{"id":"2410.01735","title":"LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits","created":"2024-10-02","cited_by_count":7,"area":"alignment"},{"id":"2410.16270","title":"Reflection-Bench: Evaluating Epistemic Agency in Large Language Models","created":"2024-10-21","cited_by_count":7,"area":null},{"id":"2501.18009","title":"Large Language Models Think Too Fast To Explore Effectively","created":"2025-01-29","cited_by_count":7,"area":"lr"},{"id":"2502.00728","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2502.01118","title":"Large Language Model-Enhanced Multi-Armed Bandits","created":"2025-02-03","cited_by_count":7,"area":null},{"id":"2508.08641","title":"MiGrATe: Mixed-Policy GRPO for Adaptation at Test-Time","created":"2025-08-12","cited_by_count":7,"area":"lr"},{"id":"2510.08517","title":"CaRT: Teaching LLM Agents to Know When They Know Enough","created":"2025-10-09","cited_by_count":7,"area":"agents"},{"id":"2602.04089","title":"Scaling In-Context Online Learning Capability of LLMs via Cross-Episode Meta-RL","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2504.02273","title":"Reasoning Under 1 Billion: Memory-Augmented Reinforcement Learning for Large Language Models","created":"2025-04-03","cited_by_count":6,"area":"lr"},{"id":"2505.21372","title":"Improving LLM-based Global Optimization with Search Space Partitioning","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2605.11258","title":"Unlocking LLM Creativity in Science through Analogical Reasoning","created":"2026-05-11","cited_by_count":6,"area":"lr"},{"id":"2501.19398","title":"Do LLMs Strategically Reveal, Conceal, and Infer Information? A Theoretical and Empirical Analysis in The Chameleon Game","created":"2025-01-31","cited_by_count":5,"area":"agents"},{"id":"2507.09041","title":"Behavioral Exploration: Learning to Explore via In-Context Adaptation","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2508.06659","title":"In-Context Reinforcement Learning via Communicative World Models","created":"2025-08-08","cited_by_count":5,"area":"wm"},{"id":"2603.29010","title":"Improving Efficiency of GPU Kernel Optimization Agents using a Domain-Specific Language and Speed-of-Light Guidance","created":"2026-03-30","cited_by_count":5,"area":"agents"},{"id":"2501.04341","title":"Understanding Before Reasoning: Enhancing Chain-of-Thought with Iterative Summarization Pre-Prompting","created":"2025-01-08","cited_by_count":4,"area":"lr"},{"id":"2505.09901","title":"Comparing Exploration-Exploitation Strategies of LLMs and Humans: Insights from Standard Multi-armed Bandit Experiments","created":"2025-05-15","cited_by_count":4,"area":null},{"id":"2509.24923","title":"When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2509.25582","title":"Safe In-Context Reinforcement Learning","created":"2025-09-29","cited_by_count":3,"area":"deeprl"},{"id":"2604.13151","title":"Exploration and Exploitation Errors Are Measurable for Language Model Agents","created":"2026-04-14","cited_by_count":3,"area":"agents"},{"id":"2605.05755","title":"Transformers Provably Implement In-Context Reinforcement Learning with Policy Improvement","created":"2026-05-07","cited_by_count":3,"area":"deeprl"},{"id":"2607.29241","title":"RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems","created":"2026-07-31","cited_by_count":3,"area":"agents"},{"id":"2505.10861","title":"Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2508.03444","title":"An Auditable Agent Platform For Automated Molecular Optimisation","created":"2025-08-05","cited_by_count":2,"area":"lr"},{"id":"2511.06148","title":"Large Language Models Develop Novel Social Biases Through Adaptive Exploration","created":"2025-11-08","cited_by_count":2,"area":null},{"id":"2501.08925","title":"Disentangling Exploration of Large Language Models by Optimal Exploitation","created":"2025-01-15","cited_by_count":1,"area":null},{"id":"2510.01531","title":"Information Seeking for Robust Decision Making under Partial Observability","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2511.12755","title":"Prompt-Driven Domain Adaptation for End-to-End Autonomous Driving via In-Context RL","created":"2025-11-16","cited_by_count":1,"area":"driving"},{"id":"2601.12945","title":"A Component-Based Survey of Interactions between Large Language Models and Multi-Armed Bandits","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2601.13892","title":"Multi-Objective Hierarchical Optimization with Large Language Models","created":"2026-01-20","cited_by_count":1,"area":"lr"},{"id":"2602.16488","title":"Learning to Learn from Language Feedback with Social Meta-Learning","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2603.15871","title":"Counteractive RL: Rethinking Core Principles for Efficient and Scalable Deep Reinforcement Learning","created":"2026-03-16","cited_by_count":1,"area":"deeprl"},{"id":"2605.25267","title":"Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning","created":"2026-05-24","cited_by_count":1,"area":"deeprl"},{"id":"2504.09777","title":"Reasoning without Regret","created":"2025-04-14","cited_by_count":0,"area":"lr"},{"id":"2509.23209","title":"Context Value Informed In-Context Reinforcement Learning","created":"2025-09-27","cited_by_count":0,"area":"deeprl"},{"id":"2601.22397","title":"SAIR: Cost-Efficient Multi-Stage ML Pipeline Autoscaling via In-Context Reinforcement Learning","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2603.03295","title":"Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Task","created":"2026-02-06","cited_by_count":0,"area":"agents"},{"id":"2603.28499","title":"Next-Token Prediction and Regret Minimization","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.17244","title":"DORA Explorer: Improving the Exploration Ability of LLMs Without Training","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.23417","title":"An Open-Source Training Dataset for Foundation Models for Black-box Optimization","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.11470","title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2607.13396","title":"Set-shifting Behavioral Test for Harnessed Agents","created":"2026-07-15","cited_by_count":0,"area":"agents"},{"id":"2607.14574","title":"Collaborative Spatial Learning with Multi-LLM Agents in Networked Social Experiments","created":"2026-07-16","cited_by_count":0,"area":"agents"},{"id":"2607.23333","title":"Training with (Swap) Regret Loss in a Single-Layer Self-Attention Model: A Case Study on the Probability Simplex","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2607.27726","title":"Baikal: Structured Search for Deep Research over Data Lakes","created":"2026-07-30","cited_by_count":0,"area":"agents"},{"id":"2608.16707","title":"Semantic Bandits: In-Context Exploration-Exploitation is Biased by Semantic Priors","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.16309","title":"Agentic Search Spaces for Tabular Machine Learning","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2610.15738","title":"Visible but Not Avoided: State-Dependent Re-Proposal of Rejected Candidates in Catalog-Based LLM Optimization Loops","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}