Structuring Collective Action with LLM-Guided Evolution: From Ill-Structured Problems to Executable Heuristics

UW-BioNLP presented their methods for extracting chemotherapy timelines from clinical notes at the ChemoTimelines 2025 shared task, focusing on strategies like chain-of-thought thinking and supervised fine-tuning. Their best-performing model, fine-tuned Qwen3-14B, achieved a score of 0.678 on the test set leaderboard.

The Natural Language Actor-Critic (NLAC) algorithm has been introduced to enhance the training of large language model (LLM) agents, which interact with environments over extended periods. This method addresses challenges in learning from sparse rewards and aims to stabilize training through a generative LLM critic that evaluates actions in natural language space.

A new framework called NITRO-D has been introduced for training deep convolutional neural networks (CNNs) using only integer operations, addressing the limitations of existing methods that rely on floating-point arithmetic. This advancement allows for both training and inference in environments where floating-point operations are unavailable, enhancing the applicability of deep learning models in resource-constrained settings.

A new framework called MSME has been proposed for zero-shot stance detection, addressing the limitations of large language models (LLMs) in understanding complex real-world scenarios. This Multi-Stage, Multi-Expert framework consists of three stages: Knowledge Preparation, Expert Reasoning, and Pragmatic Analysis, which aim to enhance the accuracy of stance detection by incorporating dynamic background knowledge and recognizing rhetorical cues.

Large language models (LLMs) have shown significant advancements in code generation, yet disparities remain in performance across various programming languages. To bridge this gap, a new approach called On-Policy Optimization with Group Equivalent Preference Optimization (GEPO) has been introduced, leveraging code translation tasks and a novel reinforcement learning framework known as OORL.

ExPairT-LLM has been introduced as an exact learning algorithm for code selection, addressing the challenges in code generation by large language models (LLMs). It utilizes pairwise membership and equivalence queries to enhance the accuracy of selecting the correct program from multiple outputs generated by LLMs, significantly improving success rates compared to existing algorithms.

Astra has been introduced as a pioneering multi-agent system designed for optimizing GPU kernel performance, addressing a long-standing challenge in high-performance computing and machine learning. This system leverages existing CUDA implementations from SGLang, a framework widely used for serving large language models (LLMs), marking a shift from traditional manual tuning methods.

CryptoBench has been introduced as the first expert-curated, dynamic benchmark aimed at evaluating the capabilities of Large Language Model (LLM) agents specifically in the cryptocurrency sector, addressing challenges such as time sensitivity and the need for data synthesis from specialized sources.