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
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative 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.
LMEB benchmark shows that embedding models' performance on traditional retrieval does not transfer to long-horizon memory tasks, larger models do not always perform better, and LMEB measures capabilities orthogonal to MTEB.
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.
-
LMEB: Long-horizon Memory Embedding Benchmark
LMEB benchmark shows that embedding models' performance on traditional retrieval does not transfer to long-horizon memory tasks, larger models do not always perform better, and LMEB measures capabilities orthogonal to MTEB.
-
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.