Tag: Coding

Yutong Wang, Siyuan Xiong, Xuebo Liu, Wenkang Zhou, Liang Ding, Miao Zhang · Feb 26, 2026 · Citations: 0

• While Multi-Agent Systems (MAS) excel in complex reasoning, they suffer from the cascading impact of erroneous information generated by individual participants.
• We propose AgentDropoutV2, a test-time rectify-or-reject pruning framework designed to dynamically optimize MAS information flow without retraining.

Roy Miles, Aysim Toker, Andreea-Maria Oncescu, Songcen Xu, Jiankang Deng, Ismail Elezi · Feb 26, 2026 · Citations: 0

• This modular pipeline separates exploration (diffusion) from evaluation and solution synthesis, avoiding monolithic unified hybrids while preserving broad search.
• Across math reasoning benchmarks, we find that step-level recombination is most beneficial on harder problems, and ablations highlight the importance of the final AR solver in converting stitched but imperfect rationales into accurate answe

Hyunwoo Kim, Hanau Yi, Jaehee Bae, Yumin Kim · Feb 26, 2026 · Citations: 0

• NLD-P is formalized as a modular control abstraction that separates provenance, constraint logic, task content, and post-generation evaluation, encoded directly in natural language without reliance on external orchestration code.
• All conceptual framing, methodological claims, and final revisions were directed, reviewed, and approved by the human author under a documented human-in-the-loop protocol.

Rui Yang, Qianhui Wu, Zhaoyang Wang, Hanyang Chen, Ke Yang, Hao Cheng · Feb 25, 2026 · Citations: 0

• Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks.
• This gap stems from two limitations: a shortage of high-quality, action-aligned reasoning data, and the direct adoption of generic post-training pipelines that overlook the unique challenges of GUI agents.

Patrick Tser Jern Kon, Archana Pradeep, Ang Chen, Alexander P. Ellis, Warren Hunt, Zijian Wang · Feb 25, 2026 · Citations: 0

• Our approach combines supervised fine-tuning on expert-augmented trajectories with agentic reinforcement learning that explicitly discourages degenerative looping and unproductive expert collaboration.

Boqi Chen, Xudong Liu, Jiachuan Peng, Marianne Frey-Marti, Bang Zheng, Kyle Lam · Feb 25, 2026 · Citations: 0

• Multimodal large language models (MLLMs) have shown great potential in medical applications, yet existing benchmarks inadequately capture real-world clinical complexity.
• We introduce MEDSYN, a multilingual, multimodal benchmark of highly complex clinical cases with up to 7 distinct visual clinical evidence (CE) types per case.

Bitan Majumder, Anirban Sen · Feb 25, 2026 · Citations: 0

Guanyi Qin, Xiaozhen Wang, Zhu Zhuo, Chang Han Low, Yuancan Xiao, Yibing Fu · Feb 25, 2026 · Citations: 0

• Existing AI systems offer binary safety verification or static detection, ignoring the phase-dependent nature of intraoperative reasoning.
• We introduce ResGo, a benchmark of laparoscopic frames annotated with Go Zone bounding boxes and clinician-authored rationales covering phase, exposure quality reasoning, next action and risk reminder.

Chenyv Liu, Wentao Tan, Lei Zhu, Fengling Li, Jingjing Li, Guoli Yang · Feb 25, 2026 · Citations: 0

• Reinforcement learning enhances physical grounding through exploration yet typically relies on external reward signals that remain isolated from the agent's internal states.
• Evaluations on challenging robot manipulation tasks from simulation benchmarks and real-world settings demonstrate that SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher s

Kangning Shen, Jingyuan Zhang, Chenxi Sun, Wencong Zeng, Yang Yue · Feb 25, 2026 · Citations: 0

• Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents.
• Recent work has further explored augmenting these agents with memory mechanisms to support long-horizon reasoning.

Kazi Samin Yasar Alam, Md Tanbir Chowdhury, Tamim Ahmed, Ajwad Abrar, Md Rafid Haque · Feb 25, 2026 · Citations: 0

• We benchmark transformer-based models and evaluate zero-shot large language models under structured prompting.

Sweta Karlekar, Carolina Zheng, Magnus Saebo, Nicolas Beltran-Velez, Shuyang Yu, John Bowlan · Feb 25, 2026 · Citations: 0

• Building on this observation, we introduce Duel-Evolve, an evolutionary optimization algorithm that replaces external scalar rewards with pairwise preferences elicited from the same LLM used to generate candidates.
• Results show that pairwise self-preferences provide strong optimization signal for test-time improvement over large, discrete output spaces.

Dmitrii Pantiukhin, Ivan Kuznetsov, Boris Shapkin, Antonia Anna Jost, Thomas Jung, Nikolay Koldunov · Feb 24, 2026 · Citations: 0

• Here we present PANGAEA-GPT, a hierarchical multi-agent framework designed for autonomous data discovery and analysis.
• Unlike standard Large Language Model (LLM) wrappers, our architecture implements a centralized Supervisor-Worker topology with strict data-type-aware routing, sandboxed deterministic code execution, and self-correction via execution feedbac

Debjit Paul, Daniel Murphy, Milan Gritta, Ronald Cardenas, Victor Prokhorov, Lena Sophia Bolliger · Feb 24, 2026 · Citations: 0

• Large language model (LLM)-based agents are increasingly used to solve complex tasks involving tool use, such as web browsing, code execution, and data analysis.
• However, current evaluation benchmarks do not adequately assess their ability to solve real-world tasks that require synthesizing information from multiple sources and inferring insights beyond simple fact retrieval.

David Anugraha, Vishakh Padmakumar, Diyi Yang · Feb 24, 2026 · Citations: 0

• Based on this formulation, we introduce SparkMe, a multi-agent LLM interviewer that performs deliberative planning via simulated conversation rollouts to select questions with high expected utility.
• The code, datasets, and evaluation protocols for SparkMe are available as open-source at https://github.com/SALT-NLP/SparkMe.

Kun Yuan, Junyu Bi, Daixuan Cheng, Changfa Wu, Shuwen Xiao, Binbin Cao · Feb 24, 2026 · Citations: 0

• Modern recommender systems leverage ultra-long user behavior sequences to capture dynamic preferences, but end-to-end modeling is infeasible in production due to latency and memory constraints.
• While summarizing history via interest centers offers a practical alternative, existing methods struggle to (1) identify user-specific centers at appropriate granularity and (2) accurately assign behaviors, leading to quantization errors an

Yanna Jiang, Delong Li, Haiyu Deng, Baihe Ma, Xu Wang, Qin Wang · Feb 24, 2026 · Citations: 0

• Agentic systems increasingly rely on reusable procedural capabilities, \textit{a.k.a., agentic skills}, to execute long-horizon workflows reliably.
• This paper maps the skill layer across the full lifecycle (discovery, practice, distillation, storage, composition, evaluation, and update) and introduces two complementary taxonomies.

Peter Hase, Christopher Potts · Feb 24, 2026 · Citations: 0

Rakshit Trivedi, Kartik Sharma, David C Parkes · Feb 24, 2026 · Citations: 0

• Effective human-AI coordination requires artificial agents capable of exhibiting and responding to human-like behaviors while adapting to changing contexts.
• Imitation learning has emerged as one of the prominent approaches to build such agents by training them to mimic human-demonstrated behaviors.

Wanyong Feng, Andrew Lan · Feb 23, 2026 · Citations: 0

• We train the model in a two-step process, first via Supervised Fine-Tuning and then via preference optimization for knowledge-response alignment.