LM-Provers, Yuxiao Qu, Amrith Setlur, Jasper Dekoninck, Edward Beeching, Jia Li · Apr 6, 2026 · Citations: 0
Rubric RatingAutomatic MetricsMathCoding
To support further research on open mathematical reasoning, we release the full QED-Nano pipeline, including the QED-Nano and QED-Nano-SFT models, the FineProofs-SFT and FineProofs-RL datasets, and the training and evaluation code.
Learning from experience is critical for building capable large language model (LLM) agents, yet prevailing self-evolving paradigms remain inefficient: agents learn in isolation, repeatedly rediscover similar behaviors from limited…
To address this problem, we propose SkillX, a fully automated framework for constructing a plug-and-play skill knowledge base that can be reused across agents and environments.
Andrew Ang, Nazym Azimbayev, Andrey Kim · Apr 2, 2026 · Citations: 0
Critique EditCoding
Agentic AI shifts the investor's role from analytical execution to oversight.
We present an agentic strategic asset allocation pipeline in which approximately 50 specialized agents produce capital market assumptions, construct portfolios using over 20 competing methods, and critique and vote on each other's output.
Extensive evaluations across 1.5B--14B parameter models demonstrate that APC reduces expected editing costs from 19% to 50% while preserving standard HC performance.
Using roughly 48 execution-verified HumanEval training solutions, tuning a single initial state matrix per recurrent layer, with zero inference overhead, outperforms LoRA by +10.8 pp (p < 0.001) on HumanEval.
Cross-domain transfer is significant on MATH-500 (+4.8 pp, p = 0.00002, 8 seeds) and GSM8K (+2.8 pp, p = 0.0003, 10 seeds); a text-to-SQL benchmark (Spider) shows no transfer, consistent with the trajectory-steering mechanism.
We introduce Paper Reconstruction Evaluation (PaperRecon), an evaluation framework in which an overview (overview.md) is created from an existing paper, after which an agent generates a full paper based on the overview and minimal…
For evaluation, we introduce PaperWrite-Bench, a benchmark of 51 papers from top-tier venues across diverse domains published after 2025.
As LLM agents transition from short, static problem solving to executing complex, long-horizon tasks in dynamic environments, the ability to handle user interruptions, such as adding requirement or revising goals, during mid-task execution…
In this paper, we present the first systematic study of interruptible agents in long-horizon, environmentally grounded web navigation tasks, where actions induce persistent state changes.
Experiments on LLaDA and Dream across math and coding benchmarks show that TRIMS significantly improves the accuracy-parallelism trade-off over both standard MDLM training and train-free acceleration baselines, while achieving competitive…
In this paper, we propose Agent Q-Mix, a reinforcement learning framework that reformulates topology selection as a cooperative Multi-Agent Reinforcement Learning (MARL) problem.
Across seven core benchmarks in coding, reasoning, and mathematics, Agent Q-Mix achieves the highest average accuracy compared to existing methods while demonstrating superior token efficiency and robustness against agent failure.
Ashish Rana, Chia-Chien Hung, Qumeng Sun, Julian Martin Kunkel, Carolin Lawrence · Mar 31, 2026 · Citations: 0
Automatic MetricsCoding
Human memory adapts through selective forgetting: experiences become less accessible over time but can be reactivated by reinforcement or contextual cues.
We evaluate on both static and dynamic long-horizon interaction benchmarks.
Extensive evaluations across diverse LLMs and mathematical reasoning benchmarks show that Hi-CoT consistently improves average accuracy by 6.2% (up to 61.4% on certain models and tasks) while reducing reasoning trace length by 13.9%…
Yahan Li, Chaohao Du, Zeyang Li, Christopher Chun Kuizon, Shupeng Cheng, Angel Hsing-Chi Hwang · Mar 31, 2026 · Citations: 0
Rubric RatingExpert VerificationHuman EvalCoding
The system integrates two families of evaluation signals: (i) 12 model-based metrics produced by task-specific predictors, and (ii) rubric-based metrics that extend coverage via a literature-derived library (69 metrics) and user-defined…
Human evaluation includes a user study with 20 participants and an expert review with 6 mental-health professionals, suggesting that CounselReflect supports understandable, usable, and trustworthy auditing.
Masnun Nuha Chowdhury, Nusrat Jahan Beg, Umme Hunny Khan, Syed Rifat Raiyan, Md Kamrul Hasan, Hasan Mahmud · Mar 30, 2026 · Citations: 0
Automatic MetricsLawCoding
We propose a courtroom-style multi-agent framework, PROClaim, that reformulates verification as a structured, adversarial deliberation.
In zero-shot evaluations on the Check-COVID benchmark, PROClaim achieves 81.7% accuracy, outperforming standard multi-agent debate by 10.0 percentage points, with P-RAG driving the primary performance gains (+7.5 pp).
We introduce PRBench, a benchmark of 30 expert-curated tasks spanning 11 subfields of physics.
Using an agentified assessment pipeline, we evaluate a set of coding agents on PRBench and analyze their capabilities across key dimensions of scientific reasoning and execution.
Heng Wang, Pengcheng Jiang, Jiashuo Sun, Zhiyi Shi, Haofei Yu, Jiawei Han · Mar 28, 2026 · Citations: 0
Human EvalAutomatic MetricsMathCoding
Across Llama-3.1 and Qwen2.5 models, future-aligned tuning improves future alignment over unaligned baselines (up to +10.6% overall FAS), and domain-expert human evaluation corroborates improved proposal quality.
Finally, we demonstrate practical impact by implementing two model-generated proposals with a code agent, obtaining 4.17% accuracy gain on MATH from a new prompting strategy and consistent improvements for a novel model-merging method.
