AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

HippoCamp: Benchmarking Contextual Agents on Personal Computers

Zhe YANG, Shulin Tian, Kairui Hu, Shuai Liu, Hoang-Nhat Nguyen, Yichi Zhang, Zujin Guo, Mengying Yu, Zinan Zhang, Jingkang Yang, Chen Change Loy, Ziwei Liu

ECCV 2026 · Multi-agent systems and games › LLM agents · approach: Agentic benchmarks and orchestration · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use iterative search agent instead of single-pass RAGStandard RAG vs ReAct (Qwen3) · HippoCamp factual retention (overall)F1 (%): 30.0 -> 43.1Improved
use iterative search agent instead of single-pass RAGStandard RAG vs ReAct (Qwen3) · HippoCamp profiling (overall)accuracy (%): 26.7 -> 13.5Hurt
use autonomous ChatGPT Agent Mode instead of search agentsReAct (Qwen3) · HippoCamp profiling (overall)accuracy (%): 13.5 -> 48.3Improved
profiling vs factual retention task (Search-R1)Search-R1 · HippoCamp overallaccuracy (%): 25.3 -> 5.0Hurt
profiling vs factual retention task (ReAct Qwen3)ReAct (Qwen3-30B-A3B) · HippoCamp overallaccuracy (%): 28.5 -> 13.5Hurt
move from legal Adam profile to media-rich Bei profileChatGPT Agent Mode · HippoCamp factual retentionaccuracy (%): 90.3 -> 31.2Hurt
high search F1 but weak perceptionChatGPT Agent Mode · HippoCamp profilingaccuracy (%): search 56.5 vs perception 28.5Mixed
higher retrieval F1 does not give higher answer accuracyReAct (Qwen3-30B-A3B) · HippoCamp factual retentionaccuracy (%): 43.1 F1 vs 28.5 AccMixed
correct answers without grounding evidenceTerminal Agent (GPT-5.2) · HippoCamp factual retentionaccuracy (%): 24.6 F1 vs 48.2 AccMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy