A new dataset and multi-agent framework for legal consultation question answering that outperforms standard LLMs.
arXiv preprint arXiv:2602.14038 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
background 2representative citing papers
Introduces Active Task Driving Memory (ATMem) and STR-GRPO to move GUI agents from passive record storage to actively maintained task states, tested on a new mobile benchmark with progress and scope-aware metrics.
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.
SkillPCF is a closed-loop agent framework with a physics-guided memory skill bank, reinforcement-learned skill selection, and simulator-grounded evolution that improves design quality and efficiency for photonic crystal fiber inverse design under limited simulation budgets.
CPO++ adapts reinforcement fine-tuning of MLLMs to endogenous multi-modal concept drift through counterfactual reasoning and preference optimization, yielding better coherence and cross-domain robustness in safety-critical settings.
MemForest reformulates agent memory as a temporal data management problem using a hierarchical index (MemTree) for parallel construction and localized updates, reporting 79.8% accuracy and 6x throughput on LongMemEval-S and LoCoMo benchmarks.
citing papers explorer
-
From Query to Counsel: Structured Reasoning with a Multi-Agent Framework and Dataset for Legal Consultation
A new dataset and multi-agent framework for legal consultation question answering that outperforms standard LLMs.
-
What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States
Introduces Active Task Driving Memory (ATMem) and STR-GRPO to move GUI agents from passive record storage to actively maintained task states, tested on a new mobile benchmark with progress and scope-aware metrics.
-
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.
-
Learning Design Skills as Memory Policies for Agentic Photonic Inverse Design
SkillPCF is a closed-loop agent framework with a physics-guided memory skill bank, reinforcement-learned skill selection, and simulator-grounded evolution that improves design quality and efficiency for photonic crystal fiber inverse design under limited simulation budgets.
-
Towards Robust Endogenous Reasoning: Unifying Drift Adaptation in Non-Stationary Tuning
CPO++ adapts reinforcement fine-tuning of MLLMs to endogenous multi-modal concept drift through counterfactual reasoning and preference optimization, yielding better coherence and cross-domain robustness in safety-critical settings.
-
MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing
MemForest reformulates agent memory as a temporal data management problem using a hierarchical index (MemTree) for parallel construction and localized updates, reporting 79.8% accuracy and 6x throughput on LongMemEval-S and LoCoMo benchmarks.