6 papers
Generalizable End-to-End Tool-Use RL with Synthetic CodeGym
Weihua Du, Hailei Gong, Zhan Ling +7
Tool-augmented large language models (LLMs), hereafter LLM agents, leverage external tools to solve diverse tasks and interface with the real world. However, current training pract…
Natural Language Actor-Critic: Scalable Off-Policy Learning in Language Space
Joey Hong, Kang Liu, Zhan Ling +2
Large language model (LLM) agents -- LLMs that dynamically interact with an environment over long horizons -- have become an increasingly important area of research, enabling autom…
LongReason: A Synthetic Long-Context Reasoning Benchmark via Context Expansion
Zhan Ling, Kang Liu, Kai Yan +6
Large language models (LLMs) have demonstrated remarkable progress in understanding long-context inputs. However, benchmarks for evaluating the long-context reasoning abilities of…
MIR-Bench: Can Your LLM Recognize Complicated Patterns via Many-Shot In-Context Reasoning?
Kai Yan, Zhan Ling, Kang Liu +5
The ability to recognize patterns from examples and apply them to new ones is a primal ability for general intelligence, and is widely studied by psychology and AI researchers. Man…
Scaling Long-Horizon LLM Agent via Context-Folding
Weiwei Sun, Miao Lu, Zhan Ling +4
Large language model (LLM) agents are fundamentally constrained by context length on long-horizon tasks. We introduce Context-Folding, a framework that empowers agents to actively…
Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
Miao Lu, Weiwei Sun, Weihua Du +4
We study reinforcement learning (RL) fine-tuning of large language model (LLM) agents for long-horizon multi-turn tool use, where context length quickly becomes a fundamental bottl…