#graph representation

try —

6 papers match

cs.MA2026

Auditing Emergent LLM-Agent Collaboration through Cooperation-Obligation Coupling

Zuyuan Zhang, Hanqing Yang, Carlee Joe-Wong +1

The paper proposes iCORE, a unified representation that combines a cooperation graph, an obligation graph, and an audit map to let auditors verify that each step of an LLM‑agent wo…

#llm agents#auditability#multi-agent collaboration#graph representation
cs.CV2026

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation

Chi Kit Wong, Ye Pan, Yuanhuiyi Lyu +6

The paper proposes Ego Scene Augmentation (ESA), a framework that uses an Ego-element Graph to improve the spatial perception of multimodal large language models for egocentric vis…

#egocentric vision#visual question answering#spatial reasoning#multimodal language models
cs.CC2026

An Efficient Algorithm for Solving the 2-MAXSAT Problem

Yangjun Chen

The paper proposes a polynomial‑time algorithm for the NP‑complete 2‑MAXSAT problem by converting it to a DNF maximization task and using graph‑based (p*-graph) and trie‑like struc…

#maxsat#2-sat#algorithm design#graph representation
cs.CL2026

Conceptual Networks for Cross-Linguistic Idiomatic Expressions: A Feature-Based Graph Approach

Kiran Pala, Punam Silu, Luxin Yu

The paper introduces a graph-based framework that uses binary conceptual features to represent idiomatic expressions across eight languages, showing that idioms cluster by meaning…

#idiom detection#cross-linguistic semantics#graph representation#conceptual features
cs.LG2026

CA-DGCL: Dynamic Graph Continual Learning via Condensation and Attachment

Tingxu Yan Ye Yuan

The paper introduces CA-DGCL, a framework that compresses past graph snapshots into compact representations and uses tensor decomposition to create stable node features, which are…

#dynamic graphs#continual learning#graph representation#tensor decomposition
cs.AI2026

LP Mining with LP2Graph: A Use Case for Railway Rescheduling

Jörn Maurischat, Nikola Bešinović, Michael Färber

The paper presents LP2Graph, a method that automatically extracts the structure of linear and mixed‑integer programming formulations from published papers into a typed variable‑equ…

#linear programming#mixed-integer programming#model mining#graph representation

One search, two signals: results blend meaning (embedding similarity, so papers that never use your words still surface) with keyword matches on titles, abstracts and summaries. Free, no sign-in needed.