AI & ML
Multi-Agent Memory Inconsistency: Where Factual Conflicts Disappear in LLM Agents
arXiv cs.MA0 views
arXiv:2611.22245v1 Announce Type: cross Abstract: Multi-agent delegation lets LLM systems distribute evidence collection across workers with separate contexts. This creates a consistency challenge: facts retrieved by workers may be missing from the evidence available to the lead for a joint conclusion. We introduce a benchmark and evidence-flow profiler for studying multi-agent memory inconsistency through controlled factual conflicts in Harvey LAB document-review tasks. Pooled across three models with comparable generation spending, requiring delegation increases retrieval of both conflicting claims from 50.2% to 68.7% relative to single-agent execution, yet conflict detection falls from 16.2% to 13.2%. Within this setting, workers report both claims for only 35.2% of retrieved pairs, and pooled matched comparisons show higher detection than single-agent execution when one worker reads both claims but lower detection when the claims are split across workers. Worker-to-lead handoffs are a central target for improving conflict detection in multi-agent LLMs.
Source:https://arxiv.org/abs/2611.22245PreviousThe Only Edge Was Memorized in Training: LLM Trading Agents Around Earnings and Bad NewsNextBad Apples in the Kitchen: How LLM Teams Detect, Correct, and Calibrate Against Their Misaligned Members
Related posts
Show HN: I cut an LLM's screen-watching cost to ~138 tokens per step
0Hacker News New
Codeberg's Domain Was Suspended
0Hacker News New
Gemini AI agents repeatedly bypassed safeguards to attack real website
0Hacker News New
A new AI agent builder. No-code visual builder with customer support platform
0Hacker News New
Jacob Tsimerman on AI can supercharge mathematics [video]
0Hacker News New
Show HN: Production Grammar-Guided Decoding in vLLM with Xgrammar Benchmarks
0Hacker News Show