arxiv arXiv cs.CL · 65d ago · src: 66d ago · research

MODE-RAG: Evaluating and Reducing Hallucinations in M-RAG

from English

MODE-RAG proposes a multi-agent system using Variational Free Energy to dynamically gate interventions and reduce cross-modal hallucinations in retrieval-augmented generation. It integrates Monte Carlo Tree Search and logit perturbations to address causal fabrications and sycophancy, with dedicated agents ensuring factual verification and formatting stability. Evaluated via ModeVent, a subset of MultiVent, the system significantly improves robustness against logical fabrications.

Importance 2/3 New feature vs. leaders New harness with differentiators arXiv cs.CL Mistral AI Google DeepMind OpenAI AI agents Reasoning models Retrieval & RAG

Read original

arxiv arXiv cs.AI · 62d ago · 6 views

LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents

LedgerAgent introduces a structured ledger to maintain task states separately in tool-calling agents. It renders states into prompts and enforces policy constraints before tool execution, reducing policy violations and improving performance across customer-service domains.

arxiv arXiv cs.CL · 62d ago · 10 views

LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents

LedgerAgent introduces a structured ledger to maintain task states separately in tool-calling agents. It renders these states into prompts and enforces policy constraints before tool execution, reducing policy violations and improving performance across customer-service domains.

arxiv arXiv cs.AI · 62d ago · 8 views

Dual-Agent Framework for Cross-Model Verified Translation

A dual-agent framework converts natural-language experiment protocols into executable commands for robotic lab platforms. It uses a Parser Agent and a rule-based mapping engine to translate protocols, with a heterogeneous LLM Validation Agent ensuring accuracy and triggering self-correction. The framework successfully enables end-to-end autonomous execution of microplate-based experiments like the Bradford assay.

arxiv arXiv cs.CL · 63d ago · 5 views

AtomMem: Simple and Effective Memory System for LLM Agents

AtomMem introduces a memory system that stores high-value atomic facts from long-form interactions. It uses hierarchical event structures and temporal profiles to capture coherent episodic contexts and track evolving user attributes, enabling stable and efficient memory evolution. Experiments on the LoCoMo benchmark show AtomMem achieves state-of-the-art performance in reasoning tasks.

arxiv arXiv cs.CL · 63d ago · 8 views

GEMS: Geometric Constraints Enable Multi-Semantic Superposition in LLMs

GEMS enables training-free superposition of multiple semantic directions in LLMs by addressing distributional deviation and directional interference through geometric constraints. On GSM8K, it maintains 98% accuracy with three non-mathematical directions, while unconstrained addition drops to 4%; on Wikitext-2, it increases PPL by only 2.2%.