10 papers
SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents
Amirhossein Abaskohi, Mahdi Mostajabdaveh, Zirui Zhou
Large language model (LLM)-driven evolutionary search is a powerful paradigm for automated program and algorithm discovery, yet existing systems are largely memoryless: each run ex…
DeepRewind: Predicting and Repairing Premature Commitments in Deep Research Agents
Amirhossein Abaskohi, Amirhossein Dabiriaghdam, Lele Wang +2
Deep-research agents conduct long-horizon investigations through iterative search, evidence evaluation, belief revision, and synthesis. However, they may commit to claims before su…
UnpredictaBench: A Benchmark for Evaluating Distributional Randomness in LLMs
Amirhossein Abaskohi, Amirhossein Dabiriaghdam, Liang Luo +4
We introduce UnpredictaBench, an evaluation that tests the ability of large language models (LLMs) to capture true underlying distributions. As LLMs are increasingly used as substi…
Dual-Confidence Contrastive Decoding for Retrieval-Augmented Generation
Raymond Li, Md Tawkat Islam Khondaker, Amirhossein Abaskohi +3
Retrieval-augmented generation (RAG) increasingly requires models to answer questions from multiple retrieved documents, where only some sources are relevant and the retrieved bund…
SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference
Amirhossein Abaskohi, Giuseppe Carenini, Peter West +1
Large language models increasingly operate over long contexts, where the KV cache becomes a dominant memory bottleneck: its size grows linearly with sequence length and must be ret…
MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval
Amirhossein Abaskohi, Raymond Li, Gaetano Cimino +3
Retrieval-augmented generation (RAG) systems depend critically on how documents are chunked and searched. Fine-grained chunks can improve retrieval precision but expand the search…
SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG
Amirhossein Abaskohi, Issam H. Laradji, Peter West +1
Retrieval-augmented generation (RAG) systems must balance retrieval granularity with contextual coherence, a challenge that existing methods address through LLM-guided chunking, si…
ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction
Amirhossein Abaskohi, Yuhang He, Peter West +3
Computer-use agents (CUAs) rely on visual observations of graphical user interfaces, where each screenshot is encoded into a large number of visual tokens. As interaction trajector…
Improving Topic Modeling by Distilling Soft Labels from Language Models
Raymond Li, Amirhossein Abaskohi, Chuyuan Li +2
Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with…
DRBench: A Realistic Benchmark for Enterprise Deep Research
Amirhossein Abaskohi, Tianyi Chen, Miguel Muñoz-Mármol +11
We introduce DRBench, a benchmark for evaluating AI agents on complex, open-ended deep research tasks in enterprise settings. Unlike prior benchmarks that focus on simple questions…