7 papers
EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium
Yuqiao Meng, Sakshi Sunil Narvekar, Luoxi Tang +4
Multi-agent debate (MAD) systems increasingly rely on shared memory to support long-horizon reasoning, but this convenience opens a critical vulnerability: a single corrupted entry…
When Engineering Outruns Intelligence: Rethinking Instruction-Guided Navigation
Matin Aghaei, Lingfeng Zhang, Mohammad Ali Alomrani +2
Recent ObjectNav systems credit large language models (LLMs) for sizable zero-shot gains, yet it remains unclear how much comes from language versus geometry. We revisit this quest…
ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation
Kunquan Li, Yingxue Zhang, Fandong Meng +1
Recent years have witnessed growing interest in applying Large Reasoning Models (LRMs) to Machine Translation (MT). Existing approaches predominantly adopt a "think-first-then-tran…
One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models
Chris Cameron, Wangzheng Wang, Nikita Ivanov +3
Looped transformers scale computational depth without increasing parameter count by repeatedly applying a shared transformer block and can be used for iterative refinement, where e…
InvertiTune: High-Quality Data Synthesis for Cost-Effective Single-Shot Text-to-Knowledge Graph Generation
Faezeh Faez, Marzieh S. Tahaei, Yaochen Hu +4
Large Language Models (LLMs) have revolutionized the ability to understand and generate text, enabling significant progress in automatic knowledge graph construction from text (Tex…
Logic Synthesis Optimization with Predictive Self-Supervision via Causal Transformers
Raika Karimi, Faezeh Faez, Yingxue Zhang +4
Contemporary hardware design benefits from the abstraction provided by high-level logic gates, streamlining the implementation of logic circuits. Logic Synthesis Optimization (LSO)…