pith. sign in

How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on tau-bench

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents

cs.AI · 2026-06-18 · unverdicted · novelty 6.0

LedgerAgent is an inference-time method that uses a structured ledger to track task states and enforce domain policies in tool-calling agents, improving average pass^k over standard prompt-based approaches across four domains.

citing papers explorer

Showing 1 of 1 citing paper.

  • LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents cs.AI · 2026-06-18 · unverdicted · none · ref 25

    LedgerAgent is an inference-time method that uses a structured ledger to track task states and enforce domain policies in tool-calling agents, improving average pass^k over standard prompt-based approaches across four domains.