{"total":52,"rows":[{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228,"area":"agents"},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135,"area":"agents"},{"id":"2605.21384","title":"SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents","created":"2026-05-20","cited_by_count":28,"area":"agents"},{"id":"2605.06078","title":"Milestone-Guided Policy Learning for Long-Horizon Language Agents","created":"2026-05-07","cited_by_count":19,"area":"agents"},{"id":"2503.06708","title":"Alignment for Efficient Tool Calling of Large Language Models","created":"2025-03-09","cited_by_count":17,"area":"agents"},{"id":"2503.21720","title":"Collab: Controlled Decoding using Mixture of Agents for LLM Alignment","created":"2025-03-27","cited_by_count":14,"area":"agents"},{"id":"2510.04284","title":"Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learning","created":"2025-10-05","cited_by_count":14,"area":"agents"},{"id":"2602.04634","title":"WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning","created":"2026-02-04","cited_by_count":9,"area":"agents"},{"id":"2405.12900","title":"Adversarial DPO: Harnessing Harmful Data for Reducing Toxicity with Minimal Impact on Coherence and Evasiveness in Dialogue Agents","created":"2024-05-21","cited_by_count":7,"area":"agents"},{"id":"2506.00042","title":"Enhancing Tool Learning in Large Language Models with Hierarchical Error Checklists","created":"2025-05-28","cited_by_count":7,"area":"agents"},{"id":"2603.08806","title":"Test-Driven AI Agent Definition (TDAD): Compiling Tool-Using Agents from Behavioral Specifications","created":"2026-03-09","cited_by_count":6,"area":"agents"},{"id":"2607.22368","title":"Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI","created":"2026-07-24","cited_by_count":6,"area":"agents"},{"id":"2602.18920","title":"DeepInnovator: Triggering the Innovative Capabilities of LLMs","created":"2026-02-21","cited_by_count":5,"area":"agents"},{"id":"2605.23989","title":"Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security","created":"2026-05-17","cited_by_count":5,"area":"agents"},{"id":"2609.20519","title":"SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness","created":"2026-09-17","cited_by_count":5,"area":"agents"},{"id":"2508.20755","title":"Provable Benefits of In-Tool Learning for Large Language Models","created":"2025-08-28","cited_by_count":4,"area":"agents"},{"id":"2606.15385","title":"Reward Hacking in Language Model Agents: Revisiting AI Safety Gridworlds","created":"2026-06-13","cited_by_count":4,"area":"agents"},{"id":"2606.21262","title":"ARCO: Adaptive Rubrics with Co-Evolution for Multi-Step LLM-Based Agents","created":"2026-06-19","cited_by_count":4,"area":"agents"},{"id":"2606.28430","title":"Building to the Test: Coding Agents Deliver What You Check, Not What You Requested","created":"2026-06-26","cited_by_count":4,"area":"agents"},{"id":"2607.25152","title":"When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops","created":"2026-07-27","cited_by_count":4,"area":"agents"},{"id":"2609.20812","title":"Quantifying Overclaiming Propensity in Frontier LLM Agents","created":"2026-09-17","cited_by_count":4,"area":"agents"},{"id":"2512.06196","title":"ARCANE: A Multi-Agent Framework for Interpretable and Configurable Alignment","created":"2025-12-05","cited_by_count":3,"area":"agents"},{"id":"2512.10665","title":"On the Dynamics of Multi-Agent LLM Communities Driven by Value Diversity","created":"2025-12-11","cited_by_count":3,"area":"agents"},{"id":"2606.29719","title":"A Diagnostic Framework and Multi-Evaluator Audit of Evaluator-Driven Preference Dynamics in Self-Adapting LLM Agents","created":"2026-06-29","cited_by_count":3,"area":"agents"},{"id":"2608.13867","title":"Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model","created":"2026-08-14","cited_by_count":3,"area":"agents"},{"id":"2609.02246","title":"LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails","created":"2026-09-02","cited_by_count":3,"area":"agents"},{"id":"2504.03185","title":"Learning Natural Language Constraints for Safe Reinforcement Learning of Language Agents","created":"2025-04-04","cited_by_count":2,"area":"agents"},{"id":"2606.20493","title":"Contagion Networks: Evaluator Preference Propagation in Multi-Agent LLM Systems","created":"2026-06-18","cited_by_count":2,"area":"agents"},{"id":"2607.12790","title":"Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents","created":"2026-07-14","cited_by_count":2,"area":"agents"},{"id":"2609.28614","title":"Reward Hacking Challenges Oversight of Autonomous Research Agents","created":"2026-09-23","cited_by_count":2,"area":"agents"},{"id":"2406.10590","title":"LLM-Mediated Domain-Specific Voice Agents: The Case of TextileBot","created":"2024-06-15","cited_by_count":1,"area":"agents"},{"id":"2602.04197","title":"From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agents","created":"2026-02-04","cited_by_count":1,"area":"agents"},{"id":"2604.19752","title":"Soft-Label Governance for Distributional Safety in Multi-Agent Systems","created":"2026-03-19","cited_by_count":1,"area":"agents"},{"id":"2608.09855","title":"The Greatness of Science Cannot Be Planned: Agentic Auto-Research is Fuzz Testing","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2608.11434","title":"Benchmarking LLM Judges for Mobile Agent Evaluation","created":"2026-08-11","cited_by_count":1,"area":"agents"},{"id":"2608.13564","title":"Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation","created":"2026-06-25","cited_by_count":1,"area":"agents"},{"id":"2608.29605","title":"Hindsight Memory-PRM: Supervising Memory Management with Auditable Hindsight Credit","created":"2026-08-30","cited_by_count":1,"area":"agents"},{"id":"2609.02889","title":"Where Does Harness-Optimization Value Live? Localized Gains and the Budget-Splitting Trap in Self-Evolving LLM Agents","created":"2026-06-25","cited_by_count":1,"area":"agents"},{"id":"2604.06392","title":"Qualixar OS: A Universal Operating System for AI Agent Orchestration","created":"2026-04-07","cited_by_count":0,"area":"agents"},{"id":"2605.16471","title":"From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI","created":"2026-05-15","cited_by_count":0,"area":"agents"},{"id":"2606.16682","title":"Multimodal Evaluator Preference Collapse: Cross-Modal Coupling in Self-Evolving Agents","created":"2026-06-15","cited_by_count":0,"area":"agents"},{"id":"2606.22495","title":"Grounded Scaling: Why Agentic AI Needs Deterministic Environments","created":"2026-06-21","cited_by_count":0,"area":"agents"},{"id":"2608.05990","title":"OPERA: Operator-residual feedback for reliable autonomous optical experiments with language-model agents","created":"2026-08-06","cited_by_count":0,"area":"agents"},{"id":"2608.11274","title":"Agent Safety Should Be a Runtime Contract","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2609.04217","title":"At Equal Inference Cost, Multi-Agent Structure Does Not Beat a Single Frozen Agent","created":"2026-06-25","cited_by_count":0,"area":"agents"},{"id":"2609.07910","title":"PRIMUS: Identity, Governance, and Verification for Multi-Agent Federations","created":"2026-09-07","cited_by_count":0,"area":"agents"},{"id":"2609.29578","title":"PartHackBench: Certified Equal-Progress Stress Tests for Partial-Credit Tool-Agent Evaluation","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"id":"2609.39958","title":"Better Deck or Different Judge? Evaluating Agentic Harness Gains in Corporate and Investment Banking","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.01508","title":"OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling Agents","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.03055","title":"hacktrace: behavior-supervised detection of reward hacking during code generation","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.05923","title":"VERA: Scaling Verifiable Environments for Agentic co-Evolution","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.06204","title":"Do Small Language Models Learn to Negotiate? A Controlled Scaling Study of RL-Trained Sellers","created":"2026-10-05","cited_by_count":0,"area":"agents"}],"next_cursor":null}