7 papers
On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents
Gengsheng Li, Mao Zheng, Mingyang Song +8
Multi-turn agents that plan, invoke tools, and interact with environments offer a promising paradigm for solving complex tasks, yet their capabilities typically rely on very large…
AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts
Keyu Li, Junhao Shi, Yang Xiao +11
Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain f…
LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces
Yukang Feng, Jianwen Sun, Zelai Yang +16
Recent advances in AI-assisted programming have empowered agents to execute complex workflows via command-line interfaces, however, existing benchmarks are limited by short task ho…
daVinci-Dev: Agent-native Mid-training for Software Engineering
Ji Zeng, Dayuan Fu, Tiantian Mi +14
Recently, the frontier of Large Language Model (LLM) capabilities has shifted from single-turn code generation to agentic software engineering-a paradigm where models autonomously…
Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Training
Dayuan Fu, Yunze Wu, Xiaojie Cai +13
Large Language Model (LLM) agents have recently shown strong potential in domains such as automated coding, deep research, and graphical user interface manipulation. However, train…
InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research
Yunze Wu, Dayuan Fu, Weiye Si +13
AI agents could accelerate scientific discovery by automating hypothesis formation, experiment design, coding, execution, and analysis, yet existing benchmarks probe narrow skills…