{"total":86,"rows":[{"id":"2504.21798","title":"SWE-smith: Scaling Data for Software Engineering Agents","created":"2025-04-30","cited_by_count":285,"area":"agents"},{"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":"2511.13646","title":"Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?","created":"2025-11-17","cited_by_count":95,"area":"agents"},{"id":"2506.11791","title":"SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks","created":"2025-06-13","cited_by_count":75,"area":"agents"},{"id":"2512.18470","title":"SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios","created":"2025-12-20","cited_by_count":59,"area":"agents"},{"id":"2509.19199","title":"Agentic Reinforcement Learning with Implicit Step Rewards","created":"2025-09-23","cited_by_count":47,"area":"agents"},{"id":"2509.09265","title":"Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents","created":"2025-09-11","cited_by_count":46,"area":"agents"},{"id":"2505.14668","title":"ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions","created":"2025-05-20","cited_by_count":45,"area":"agents"},{"id":"2512.22087","title":"Context as a Tool: Context Management for Long-Horizon SWE-Agents","created":"2025-12-26","cited_by_count":43,"area":"agents"},{"id":"2509.06216","title":"Agentic Software Engineering: Foundational Pillars and a Research Roadmap","created":"2025-09-07","cited_by_count":41,"area":"agents"},{"id":"2509.23045","title":"Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents","created":"2025-09-27","cited_by_count":41,"area":"agents"},{"id":"2512.24873","title":"Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem","created":"2025-12-31","cited_by_count":30,"area":"agents"},{"id":"2602.03419","title":"SWE-World: Building Software Engineering Agents in Docker-Free Environments","created":"2026-02-03","cited_by_count":25,"area":"agents"},{"id":"2508.00910","title":"Cyber-Zero: Training Cybersecurity Agents without Runtime","created":"2025-07-29","cited_by_count":22,"area":"agents"},{"id":"2512.03262","title":"Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks","created":"2025-12-02","cited_by_count":22,"area":"agents"},{"id":"2602.09892","title":"Immersion in the GitHub Universe: Scaling Coding Agents to Mastery","created":"2026-02-10","cited_by_count":22,"area":"agents"},{"id":"2603.03194","title":"BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?","created":"2026-03-03","cited_by_count":22,"area":"agents"},{"id":"2506.10974","title":"AutoMind: Adaptive Knowledgeable Agent for Automated Data Science","created":"2025-06-12","cited_by_count":20,"area":"agents"},{"id":"2509.09853","title":"SWE-Effi: Re-Evaluating Software AI Agent System Effectiveness Under Resource Constraints","created":"2025-09-11","cited_by_count":17,"area":"agents"},{"id":"2506.08311","title":"Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study","created":"2025-06-10","cited_by_count":16,"area":"agents"},{"id":"2508.18370","title":"Training Language Model Agents to Find Vulnerabilities with CTF-Dojo","created":"2025-08-25","cited_by_count":15,"area":"agents"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2606.28434","title":"SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents","created":"2026-06-26","cited_by_count":15,"area":"agents"},{"id":"2602.12268","title":"CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use","created":"2026-02-12","cited_by_count":14,"area":"agents"},{"id":"2605.22781","title":"DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback","created":"2026-05-21","cited_by_count":12,"area":"agents"},{"id":"2512.10398","title":"Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases","created":"2025-12-11","cited_by_count":11,"area":"agents"},{"id":"2601.16206","title":"Computer Environments Elicit General Agentic Intelligence in LLMs","created":"2026-01-22","cited_by_count":11,"area":"agents"},{"id":"2601.05930","title":"Can We Predict Before Executing Machine Learning Agents?","created":"2026-01-09","cited_by_count":10,"area":"agents"},{"id":"2601.20789","title":"SERA: Soft-Verified Efficient Repository Agents","created":"2026-01-28","cited_by_count":10,"area":"agents"},{"id":"2604.17931","title":"LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent","created":"2026-04-20","cited_by_count":10,"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":"2602.23647","title":"SGAgent: Suggestion-Guided LLM-Based Multi-Agent Framework for Repository-Level Software Repair","created":"2026-02-27","cited_by_count":9,"area":"agents"},{"id":"2606.07412","title":"Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills","created":"2026-06-05","cited_by_count":9,"area":"agents"},{"id":"2607.22724","title":"Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks","created":"2026-07-22","cited_by_count":9,"area":"agents"},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2508.02921","title":"PentestJudge: Judging Agent Behavior Against Operational Requirements","created":"2025-08-04","cited_by_count":7,"area":"agents"},{"id":"2605.12913","title":"Revisiting DAgger in the Era of LLM-Agents","created":"2026-05-13","cited_by_count":7,"area":"agents"},{"id":"2606.13995","title":"Dialogue SWE-Bench: A Benchmark for Dialogue-Driven Coding Agents","created":"2026-06-12","cited_by_count":7,"area":"agents"},{"id":"2512.22256","title":"Agentic Software Issue Resolution with Large Language Models: A Survey","created":"2025-12-24","cited_by_count":6,"area":"agents"},{"id":"2602.10356","title":"Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents","created":"2026-02-10","cited_by_count":6,"area":"agents"},{"id":"2602.16819","title":"Hybrid-Gym: Training Coding Agents to Generalize Across Tasks","created":"2026-02-18","cited_by_count":6,"area":"agents"},{"id":"2605.27209","title":"Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments","created":"2026-05-26","cited_by_count":6,"area":"agents"},{"id":"2606.05684","title":"AdaMEM: Test-Time Adaptive Memory for Language Agents","created":"2026-06-04","cited_by_count":6,"area":"agents"},{"id":"2509.21891","title":"AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans","created":"2025-09-26","cited_by_count":5,"area":"agents"},{"id":"2604.10493","title":"SWE-Shepherd: Advancing PRMs for Reinforcing Code Agents","created":"2026-04-12","cited_by_count":5,"area":"agents"},{"id":"2605.08703","title":"RewardHarness: Self-Evolving Agentic Post-Training","created":"2026-05-09","cited_by_count":5,"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":"2609.07925","title":"FrogNano: Training a 4B Coding Agent via Online Task Synthesis","created":"2026-09-07","cited_by_count":4,"area":"agents"},{"id":"2510.17862","title":"When \"Correct\" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?","created":"2025-10-15","cited_by_count":3,"area":"agents"},{"id":"2609.09133","title":"ExecCritic: Learn to Test, Test to Improve for Coding Agents","created":"2026-09-08","cited_by_count":3,"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":"2604.07341","title":"ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories","created":"2026-04-08","cited_by_count":2,"area":"agents"},{"id":"2606.14179","title":"CacheRL:Multi-Turn Tool-Calling Agents via Cached Rollouts and Hybrid Reward","created":"2026-06-12","cited_by_count":2,"area":"agents"},{"id":"2607.23332","title":"AllocBench: Measuring Online Tool Allocation Capability in LLM Agents","created":"2026-07-25","cited_by_count":2,"area":"agents"},{"id":"2609.19801","title":"DeliveryGym: An RL Environment for Long-Horizon Embodied Agent Planning with Adaptive Curriculum","created":"2026-09-17","cited_by_count":2,"area":"agents"},{"id":"2609.22068","title":"CodeMidas: Scaling Agentic Coding RL Environments from Code Itself","created":"2026-09-18","cited_by_count":2,"area":"agents"},{"id":"2510.26287","title":"Empowering RepoQA-Agent based on Reinforcement Learning Driven by Monte-carlo Tree Search","created":"2025-10-30","cited_by_count":1,"area":"agents"},{"id":"2510.27630","title":"Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Training","created":"2025-10-31","cited_by_count":1,"area":"agents"},{"id":"2511.03925","title":"Collaborative Agents for Automated Program Repair in Ruby","created":"2025-11-06","cited_by_count":1,"area":"agents"},{"id":"2603.07927","title":"SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training","created":"2026-03-09","cited_by_count":1,"area":"agents"},{"id":"2604.07789","title":"ORACLE-SWE: Quantifying the Contribution of Oracle Information Signals on SWE Agents","created":"2026-04-09","cited_by_count":1,"area":"agents"},{"id":"2605.01208","title":"Faithful Mobile GUI Agents with Guided Advantage Estimator","created":"2026-05-02","cited_by_count":1,"area":"agents"},{"id":"2605.15565","title":"AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs","created":"2026-05-15","cited_by_count":1,"area":"agents"},{"id":"2607.05188","title":"Latent Programming Horizons in Coding Agents","created":"2026-07-06","cited_by_count":1,"area":"agents"},{"id":"2607.26656","title":"Graph Is the Verifier: Agentic Reinforcement Learning for Interprocedural Vulnerability Detection","created":"2026-07-29","cited_by_count":1,"area":"agents"},{"id":"2608.04317","title":"Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2608.07147","title":"DiDPO: Diff-in-Diff Policy Optimization for Coding Agent Training","created":"2026-08-07","cited_by_count":1,"area":"agents"},{"id":"2609.33146","title":"LiteEvo: Automated, Cost-Efficient Harness Evolution for Generalization to Unseen Tasks","created":"2026-09-27","cited_by_count":1,"area":"agents"},{"id":"2601.21649","title":"SWE-Spot: Building Small Repo-Experts with Repository-Centric Learning","created":"2026-01-29","cited_by_count":0,"area":"agents"},{"id":"2604.06762","title":"ARuleCon: Agentic Security Rule Conversion","created":"2026-04-08","cited_by_count":0,"area":"agents"},{"id":"2607.00016","title":"Libra: Training the Environment for Agentic Information Retrieval","created":"2026-05-26","cited_by_count":0,"area":"agents"},{"id":"2607.26591","title":"MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs","created":"2026-07-29","cited_by_count":0,"area":"agents"},{"id":"2608.14863","title":"Evaluating Agentic Code Repair Capabilities in Distributed Systems","created":"2026-08-14","cited_by_count":0,"area":"agents"},{"id":"2608.20771","title":"CAS: Conformalized Agentic Search via Adaptive Retrieval and Policy Weighting","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2609.29051","title":"From Self-Distillation to Self-Practice: Privileged Information for Multi-Turn Agents","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2610.00890","title":"Cross-Benchmark Transfer from RL on Agentic Coding Tasks","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.02163","title":"AutoCompact: Learning When to Compact Context in Long-Horizon Coding Agents","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.04074","title":"IdeaScientist: Orchestrating Agents for Grounded Scientific Ideation","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.05935","title":"ThunderSyncRL: Lossless Acceleration of Agentic Reinforcement Learning","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.07898","title":"FC-SWE: Failure-Conditioned RL for Long-Horizon Software Engineering Agents","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.12569","title":"SWE-Duel: Towards a Self-Scaling Arena for Coding Agents","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.12598","title":"Beyond Binary Verifiable Rewards: Behavioral Self-Rewarding for SWE Agents","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.13152","title":"Quality, Not Just Outcome: A Structural Scoring Framework for Selecting Coding-Agent Trajectories for Supervised Fine-Tuning","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.14163","title":"AutoEnvScaling: Automating the Data Flywheel with Terminal Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.16592","title":"Prorsa: Unleashing the Potential of Prefill-Decode Disaggregation in Agentic Reinforcement Learning","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.18868","title":"Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}