6 papers
Synthesize and Reward -- Reinforcement Learning for Multi-Step Tool Use in Live Environments
Ibrahim Abdelaziz, Asim Munawar, Kinjal Basu +4
Training LLMs to orchestrate multi-step tool calls is held back by three coupled obstacles: realistic stateful execution environments are costly to build, synthetic training querie…
Simulating Complex Multi-Turn Tool Calling Interactions in Stateless Execution Environments
Maxwell Crouse, Ibrahim Abdelaziz, Kshitij Fadnis +6
Synthetic data has proven itself to be a valuable resource for tuning smaller, cost-effective language models to handle the complexities of multi-turn tool calling conversations. W…
ToolRM: Outcome Reward Models for Tool-Calling Large Language Models
Mayank Agarwal, Ibrahim Abdelaziz, Kinjal Basu +4
As large language models (LLMs) increasingly interact with external tools, reward modeling for tool use has emerged as a critical yet underexplored area of research. Existing rewar…
R2D2: Remembering, Replaying and Dynamic Decision Making with a Reflective Agentic Memory
Tenghao Huang, Kinjal Basu, Ibrahim Abdelaziz +3
The proliferation of web agents necessitates advanced navigation and interaction strategies within complex web environments. Current models often struggle with efficient navigation…
NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls
Kinjal Basu, Ibrahim Abdelaziz, Kiran Kate +10
The resurgence of autonomous agents built using large language models (LLMs) to solve complex real-world tasks has brought increased focus on LLMs' fundamental ability of tool or f…
Putting It All into Context: Simplifying Agents with LCLMs
Mingjian Jiang, Yangjun Ruan, Luis Lastras +2
Recent advances in language model (LM) agents have demonstrated significant potential for automating complex real-world tasks. To make progress on these difficult tasks, LM agent a…