FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments Paper • 2604.25135 • Published 12 days ago • 12
FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments Paper • 2604.25135 • Published 12 days ago • 12
GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time Paper • 2510.03777 • Published Feb 14 • 1
Investigating the Robustness of LLMs on Math Word Problems Paper • 2406.15444 • Published May 30, 2024
Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts Paper • 2604.19835 • Published 19 days ago • 19
A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship Attribution Paper • 2305.05079 • Published May 8, 2023
Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts Paper • 2604.19835 • Published 19 days ago • 19
Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents Paper • 2501.13299 • Published Jan 23, 2025
ThinkTuning: Instilling Cognitive Reflections without Distillation Paper • 2508.07616 • Published Aug 11, 2025
BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software Paper • 2509.25248 • Published Sep 27, 2025 • 3
UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization Paper • 2407.03525 • Published Jul 3, 2024 • 3
Triple Preference Optimization: Achieving Better Alignment with Less Data in a Single Step Optimization Paper • 2405.16681 • Published May 26, 2024 • 4
When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers Paper • 2402.10601 • Published Feb 16, 2024 • 1
How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on $τ$-bench Paper • 2508.20931 • Published Aug 28, 2025 • 16
UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization Paper • 2407.03525 • Published Jul 3, 2024 • 3
When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers Paper • 2402.10601 • Published Feb 16, 2024 • 1
Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark Paper • 2410.14702 • Published Oct 6, 2024 • 1