CoALM shows that a single open-source model, trained on a mixture of TOD, function-calling, and ReAct data, can compete with specialized systems and GPT-4o on both multi-turn dialogue and tool-use benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Model
CoALM shows that a single open-source model, trained on a mixture of TOD, function-calling, and ReAct data, can compete with specialized systems and GPT-4o on both multi-turn dialogue and tool-use benchmarks.