{"total":12,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2510.10197","title":"Don't Just Fine-tune the Agent, Tune the Environment","created":"2025-10-11","cited_by_count":19,"area":"agents"},{"id":"2509.25084","title":"Scaling Generalist Data-Analytic Agents","created":"2025-09-29","cited_by_count":11,"area":"agents"},{"id":"2605.08060","title":"The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents","created":"2026-05-08","cited_by_count":10,"area":"agents"},{"id":"2509.24107","title":"Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs","created":"2025-09-28","cited_by_count":5,"area":"agents"},{"id":"2602.11351","title":"Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization","created":"2026-02-11","cited_by_count":2,"area":"agents"},{"id":"2602.22523","title":"Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents","created":"2026-02-26","cited_by_count":2,"area":"agents"},{"id":"2608.22631","title":"Learning Generalizable Behaviors for Terminal Agents","created":"2026-08-23","cited_by_count":2,"area":"agents"},{"id":"2510.04089","title":"SPOGW: a Score-based Preference Optimization method via Group-Wise comparison for workflows","created":"2025-10-05","cited_by_count":1,"area":"agents"},{"id":"2601.22491","title":"SSL: Sweet Spot Learning for Differentiated Guidance in Agentic Optimization","created":"2026-01-30","cited_by_count":0,"area":"agents"},{"id":"2609.40221","title":"PhantomEnvironments: Training LLM Agents in Fictional Worlds","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.05367","title":"AIProver: Agentic Auto-Formalization of Mathematical Research via Certificate-Driven Evolving Harness","created":"2026-10-04","cited_by_count":0,"area":"agents"}],"next_cursor":null}