{"total":46,"rows":[{"id":"2607.22083","title":"Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model","created":"2026-07-24","cited_by_count":11,"area":"agents"},{"id":"2608.09096","title":"Evo-Bench: Can Language Models Improve Agent Harness?","created":"2026-08-10","cited_by_count":11,"area":"agents"},{"id":"2608.02287","title":"SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation","created":"2026-08-03","cited_by_count":3,"area":"agents"},{"id":"2608.16211","title":"BaT: Towards Self-Evolving Medical Research Agent with Stage Rubrics","created":"2026-08-17","cited_by_count":2,"area":"agents"},{"id":"2607.28175","title":"AgenticASR: Refining Speech Recognition in Real-World Scenarios via an Agentic Approach","created":"2026-07-30","cited_by_count":1,"area":"agents"},{"id":"2608.12547","title":"Do LLMs Beat Nash? Testing Decentralized Coordination in Self-Play Multi-Agent Games","created":"2026-08-12","cited_by_count":1,"area":"agents"},{"id":"2608.20631","title":"Weighted Memory Tree: Remembering What Matters for Long-Horizon LLM Agents","created":"2026-08-21","cited_by_count":1,"area":"agents"},{"id":"2609.15982","title":"The Router Within: Eliciting Native Skill Routing from a Frozen LLM","created":"2026-09-14","cited_by_count":1,"area":"agents"},{"id":"2609.20791","title":"StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation","created":"2026-09-17","cited_by_count":1,"area":"agents"},{"id":"2609.36777","title":"Code4Scene: Benchmarking Coding Agents for Constructing and Editing 3D Scenes","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2607.25431","title":"CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2609.07131","title":"AgentLeak: Cloning Stronger LLM Agent Capabilities onto Weaker Agents Beyond Skill Stealing","created":"2026-09-07","cited_by_count":0,"area":"agents"},{"id":"2609.14422","title":"Safety Signals to Verify NetOps Agents with Action-Level Granularity","created":"2026-09-13","cited_by_count":0,"area":"agents"},{"id":"2609.20734","title":"On-Demand Attention: Language Models Know When to Recall","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.26777","title":"SWE-Serve: Benchmarking Agentic Engineering For Production Inference Serving","created":"2026-09-22","cited_by_count":0,"area":"agents"},{"id":"2609.28003","title":"Learning from Failures: Heterogeneous Graph Memory for Small Language Model Tool-Using Agents","created":"2026-09-23","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":"2609.31939","title":"BioDyad: Synchronize Biomedical Discovery and Machine Learning Engineering","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.33885","title":"Prospective Interpretation Risk: Principled Communication Control Between LLMs","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.34444","title":"Social Circuits behind Multi-agent Echo Chambers","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.34686","title":"Jailbreak Context Lingers: Divergent Safety Routing and Its Cross-Task Predictability in Tool Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.34971","title":"Action-Space Shaping for LLM Agents: Measuring and Mitigating Tool-Schema Bias","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.38458","title":"PrivMeSA: Privacy-Aware Self-Evolving Multi-Agent System for Medicine via Local-Remote LLM Collaboration","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.39068","title":"SparseEngine: Sparse-First Inference Engine","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.01509","title":"Sharpening Tax in Post-Training","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.01569","title":"Managing Context and Communication in Distributed Agentic UAV Swarms","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.02702","title":"Silent Dissent: LLM Agents That Yield to the Majority Still Represent Their Original Premise","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.04137","title":"Dynamic Harness Search: Building Multi-Agent Systems Per-Query via Prediction","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.04544","title":"Label Agreement Does Not Measure Authorization","created":"2026-10-03","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"},{"id":"2610.06782","title":"T-Search: An Open Agentic Retriever and Playground for Hard Multi-Step Search","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.07089","title":"Towards a Unified Misuse Monitoring Benchmark","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.07509","title":"On Open-Ended Information Seeking for Information Elicitation Agents","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.08102","title":"DSV-Mem: Evaluating Multimodal Memory in Professional Workflows for MLLM Agents","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.09021","title":"Not Every Call Needs a Frontier Model: Per-Call-Site Evaluation of Small Language Models in a Deployed Agentic Home-Automation System","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.09115","title":"From Uncertainty to Action: Learning to Steer LLM Agents","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.09119","title":"Which Buildings Are Artificial Intelligence-Ready? A Measurement-Based Assessment Framework for AI Question Answering and Actuation","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.10478","title":"Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.11922","title":"Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Search","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.12452","title":"BrickBench: Evaluating Agentic Brick Design","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.15221","title":"HarnessNet: Feedback-driven Hierarchical Joint Harness Evolution for Multi-agent Systems","created":"2026-10-10","cited_by_count":0,"area":"agents"},{"id":"2610.16078","title":"Heterogeneous Agentic Coevolution","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.16117","title":"Beyond Perfect Teammates: Multi-Agent Collaboration with Unreliable Colleagues","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.19367","title":"Beyond Corrected Actions: Training LLM Agents on Textual Critiques","created":"2026-10-14","cited_by_count":0,"area":"agents"},{"id":"2610.19834","title":"Teaching Agents in their Own Style: Blackbox Teacher Distillation for Web Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"},{"id":"2610.19920","title":"MolHop: Scaffold-Hopping Molecular Design with Agentic Reinforcement Learning","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}