@_akhaliq: LongMINT Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
Summary
LongMINT is a benchmark for evaluating memory under multi-target interference in long-horizon agent systems.
View Cached Full Text
Cached at: 05/22/26, 11:46 AM
LongMINT
Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems https://t.co/LOxiZFHtQd
Similar Articles
@hyunji_amy_lee: LLM agents & memory systems operate in continuously updated environments (Git repos, evolving docs). They must process …
MINTEval is a new benchmark for evaluating LLM agents and memory systems in continuously updated environments with frequent context changes. It shows that current systems perform poorly, with an average accuracy of 27.9% across representative systems.
LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues
This paper introduces LongMemEval-V2, a benchmark for evaluating long-term memory systems in web agents, along with two memory methods: AgentRunbook-R and AgentRunbook-C.
Ground Truth First: A Longitudinal Evaluation Instrument for Agent Memory, and the Tenure Crossover in Memory-Architecture Rankings
This paper presents a longitudinal evaluation instrument for agent memory that avoids label-error and contamination by generating facts before text, and demonstrates that short-horizon benchmarks can mis-rank memory architectures compared to long-horizon performance. It also releases the Veracium open-source library for agent memory evaluation.
Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
This paper introduces a proactive memory agent that runs alongside an action agent to prevent behavioral state decay in long-horizon tasks, achieving significant improvements on Terminal-Bench2.0 and τ^2-Bench. The authors also train Qwen3.5-27B using SFT and GRPO as an early step toward open-weight memory policies.
MemGym: a Long-Horizon Memory Environment for LLM Agents
MemGym is a benchmark for evaluating memory formation in LLM agents over long-horizon tasks, unifying existing agent gyms and synthetic pipelines with memory-isolated scores. It spans tool-use dialogue, multi-turn search, coding, and computer use, and includes a lightweight reward model (MemRM) for efficient evaluation.