AutoTIR applies GRPO with a hand-designed action reward so a 7B instruct model learns to mix search and code tools, beating tool-using baselines on ten benchmarks.
H.; Meade, N.; and Reddy, S
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning
AutoTIR applies GRPO with a hand-designed action reward so a 7B instruct model learns to mix search and code tools, beating tool-using baselines on ten benchmarks.