Biased long-term memories in LLM agents cause measurable deviations in tool parameters across 105 scenarios, seven models, and 608 real tools, persisting under standard memory architectures.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
Goal clarifications lose nearly all value after 10% of execution while input clarifications retain value until roughly 50%, and asking any type past mid-trajectory hurts performance more than never asking.
DADL is a declarative YAML format that lets a single runtime handle many REST API tools for LLM agents, cutting tool advertisement context cost by 142x from 142,000 to 1,000 tokens on a catalog of 1,833 definitions.
Bits-over-Random (BoR) is a chance-corrected metric for tool shortlist evaluation that enables query-adaptive depth selection via RL, matching fixed-list coverage with shorter lists on BFCL and ToolBench.
LMEB is a new benchmark that evaluates embedding models on long-horizon memory retrieval and shows this skill is largely orthogonal to traditional passage-retrieval performance.
Grep retrieval generally outperforms vector retrieval in agentic search tasks, with performance varying strongly by agent harness and tool-calling style.
citing papers explorer
-
Memory-Induced Tool-Drift in LLM Agents
Biased long-term memories in LLM agents cause measurable deviations in tool parameters across 105 scenarios, seven models, and 608 real tools, persisting under standard memory architectures.
-
Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?
Goal clarifications lose nearly all value after 10% of execution while input clarifications retain value until roughly 50%, and asking any type past mid-trajectory hurts performance more than never asking.
-
DADL: A Declarative Description Language for Enterprise Tool Libraries in LLM Agent Systems
DADL is a declarative YAML format that lets a single runtime handle many REST API tools for LLM agents, cutting tool advertisement context cost by 142x from 142,000 to 1,000 tokens on a catalog of 1,833 definitions.
-
How Many Tools Should an LLM Agent See? A Chance-Corrected Answer
Bits-over-Random (BoR) is a chance-corrected metric for tool shortlist evaluation that enables query-adaptive depth selection via RL, matching fixed-list coverage with shorter lists on BFCL and ToolBench.
-
LMEB: Long-horizon Memory Embedding Benchmark
LMEB is a new benchmark that evaluates embedding models on long-horizon memory retrieval and shows this skill is largely orthogonal to traditional passage-retrieval performance.
-
Is Grep All You Need? How Agent Harnesses Reshape Agentic Search
Grep retrieval generally outperforms vector retrieval in agentic search tasks, with performance varying strongly by agent harness and tool-calling style.