ReasoningBank distills generalizable reasoning strategies from agent successes and failures to enable self-evolution, with memory-aware test-time scaling amplifying gains over raw-trajectory or success-only memory on web and software benchmarks.
H i A gent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model
8 Pith papers cite this work, alongside 5 external citations. Polarity classification is still indexing.
8
Pith papers citing it
5
external citations · OpenAlex
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
SKILL.nb uses selective formalization and gate-conditioned execution in auditable notebooks to improve durability of agent workflows, achieving 53.7% success on WebArena-Verified with 91.7% retention across re-executions.
MemOp is a closed-loop memory augmentation framework for SE agents that defines memory utility via downstream task impact and reports gains of up to 5.25% success rate, 4.63% resolve efficiency, and 9.79% cost reduction.
SPIKE dual-controller framework raises success rates 5-9 points and cuts tokens 55% in StarDojo agents by reusing strategic plans across stable segments and escalating only at detected events.
A lightweight supervised router using frozen-LLM embeddings for memory admission decisions outperforms LLM-based memory managers in both F1 score and latency on the LoCoMo benchmark.
OSU-Mem shows overlapping memory helps retrieval when evidence shares tools or entities but hurts when steps are heterogeneous, with benefits on synthetic benchmarks vanishing on mixed real ones due to query mixing.
MINTEval benchmark shows current memory-augmented systems average 27.9% accuracy on long-horizon interference tasks, limited by retrieval and memory construction with degradation from intervening updates.
citing papers explorer
-
ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
ReasoningBank distills generalizable reasoning strategies from agent successes and failures to enable self-evolution, with memory-aware test-time scaling amplifying gains over raw-trajectory or success-only memory on web and software benchmarks.
-
SKILL.nb: Selective Formalization and Gated Execution for Durable Agent Workflows
SKILL.nb uses selective formalization and gate-conditioned execution in auditable notebooks to improve durability of agent workflows, achieving 53.7% success on WebArena-Verified with 91.7% retention across re-executions.
-
Enhancing Software Engineering Through Closed-Loop Memory Optimization
MemOp is a closed-loop memory augmentation framework for SE agents that defines memory utility via downstream task impact and reports gains of up to 5.25% success rate, 4.63% resolve efficiency, and 9.79% cost reduction.
-
SPIKE: An Adaptive Dual Controller Framework for Cost-Efficient Long-Horizon Game Agents
SPIKE dual-controller framework raises success rates 5-9 points and cuts tokens 55% in StarDojo agents by reusing strategic plans across stable segments and escalating only at detected events.
-
MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents
A lightweight supervised router using frozen-LLM embeddings for memory admission decisions outperforms LLM-based memory managers in both F1 score and latency on the LoCoMo benchmark.
-
When Does Overlap Help? OSU-Mem and a Cell-Conditional Analysis of Trajectory Memory for LLM Agents
OSU-Mem shows overlapping memory helps retrieval when evidence shares tools or entities but hurts when steps are heterogeneous, with benefits on synthetic benchmarks vanishing on mixed real ones due to query mixing.
-
MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
MINTEval benchmark shows current memory-augmented systems average 27.9% accuracy on long-horizon interference tasks, limited by retrieval and memory construction with degradation from intervening updates.
- Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework