Large language model agents are increasingly used for scientific discovery. However, existing benchmarks mix law inference with programming, score data fitting instead of prediction on unseen inputs, and do not separate empirical evidence from pretrained priors. We introduce SciGame, a controlled benchmark that converts scientific literature into structured scientific cards. Each card yields a pair of Original and dimensionally consistent Counterfactual environments with the same task interface. SciGame contains a Historical collection of canonical laws and a live Temporal collection curated from papers published after model knowledge cutoffs. It evaluates agents in candidate-guided Identification and open-ended Discovery settings. Each setting runs under Prior-only, Fixed, and Adaptive protocols. Experiments on five frontier models yield three findings. First, familiar priors hurt performance once the governing relation is altered. Second, adaptive experimentation helps the strongest models but harms weaker ones under limited budgets. Third, good explanations can hide quantitative failures. Recovering the exact symbolic form remains the main bottleneck, even when agents interpret evidence correctly. Current agents can investigate systems actively, but inducing exact laws in unfamiliar settings remains an open challenge.
Large language models (LLMs) have demonstrated abilities to perform complex tasks in multiple domains, including mathematical and scientific reasoning. In this work, we construct a novel agent framework for solving representative problems in scientific computing. The proposed agent incorporates a "rewriting-resolution-review-revision" logical chain via three reasoning LLMs (the Consultant, Reviewer, and Programmer) in a collaborative and interactive manner. The Consultant module enables knowledge transfer to link problems to professional domain insights, thereby rewriting problem descriptions through text augmentation. The Programmer module generates and executes well-structured code to solve problems. The Reviewer module enables self-debugging and self-refinement through interactive feedback with code runtime outputs. Through the end-to-end review mechanism, the Programmer's executable code undergoes iterative revision. We comprehensively evaluate the framework on typical partial differential equations (PDEs), engineering-oriented flow past a cylinder, ill-conditioned linear systems, and data-driven physical analysis problems. Compared with a single-model approach, this collaborative framework significantly improves the bug-free code generation rate and reduces non-physical solutions, establishing a reliable framework for autonomous code generation from natural language descriptions. The review mechanism improved the average execution success (bug-free code and non-NaN solutions) rate of DeepSeek R1 from 59% to 82%, while ChatGPT 4.1-mini improved from 66% to 87% and Gemini-2.5 improved from 60% to 84%. Automatic code generation and review provide a promising workflow for scientific computing; analysis of solver-development trajectories further reveals recurring implementation difficulties in boundary treatment, array indexing, and the preservation of numerical constraints.
Feichen Song, Boyi Zeng, Yiqin Hao, Shixiang Song, He Li, Yizhou Yang, Zitong Wang, Yifan Liu 等 10 位作者
Looped Transformers increase computation per token by repeatedly applying a shared backbone, offering a way to improve language modeling and downstream task performance at a fixed backbone parameter count. However, each loop depends on the preceding loop, so increasing recurrent depth also increases decoding latency. Existing approaches include Parallel Loop Transformers, which reduce latency by overlapping loop computation across token positions, but yield rapidly diminishing marginal accuracy gains at larger depths. To address this challenge, we introduce LoopFold, which folds computation at multiple recurrent depths into parallel batches for the same token prefix. A lightweight predictor estimates inputs to later loops so they can start before earlier loops finish. A corrector then refines the outputs of these later loops using newly available results from earlier loops. All components are trained jointly using only the final next-token prediction loss. In experiments with 1.4B models, deeper LoopFold configurations achieve progressively higher average zero-shot accuracy across eight tasks, rising from 53.41% to 56.38%. Vanilla looped models and PLT show limited gains over the same depth range. Compared with a nine-loop vanilla model, LoopFold uses five sequential stages and additional parallel computation to reduce decoding latency by 46%.
Feichen Song, Boyi Zeng, He Li, Shixiang Song, Yiqin Hao, Zitong Wang, Yizhou Yang, Yifan Liu 等 10 位作者
Looped Transformers offer a parameter-efficient approach to language modeling by repeatedly applying a shared backbone. Vanilla looped Transformers use each backbone output directly as the input to the next iteration. These outputs may contain information useful several iterations later, but retaining it across the loop depends entirely on the single hidden state. We introduce StateLoop, which maintains one additional persistent state per token to retain information across iterations. At each iteration, a learned gate controls how much of the previous state is retained and how much information from the backbone output is incorporated. The updated state is projected back and added to the backbone output for subsequent iterations and final prediction. This design reduces Pile perplexity and improves average accuracy across eight zero-shot tasks over Vanilla Looped. Its perplexity advantage over Vanilla Looped grows with trained loop depth, consistent with persistent state becoming increasingly useful as recurrent computation deepens.
Work agents operate over digital artifacts to execute professional knowledge-intensive work, requiring training environments that support long-horizon interaction and trustworthy verification. However, hand-crafted environments incur prohibitive engineering overhead that prevents environment scaling, whereas synthesis methods sacrifice workspace complexity, realism, or grounded verifiability. To bridge this gap, we introduce WorkForge, a scalable synthesis framework for constructing verifiable work-agent environments from real-world resources. Starting from expert workflows, WorkForge first identifies the resources, decisions, and deliverables required by each workflow. It then retrieves relevant real-world files and organizes them into a workspace. WorkForge inspects the workspace to extract concrete, checkable facts about its content. These factual anchors fix which task types the workspace can support and how their outcomes can be verified. Therefore, WorkForge derives each task's instructions, solution plan, and complementary programmatic and semantic verifiers directly from these factual anchors, keeping verification traceable to observable workspace evidence. Furthermore, we construct 16.7K verifiable environments across 40 professional domains, with workspaces collectively covering 60 file types. Post-training Qwen3.5-35B-A3B-Base improves GDPVal from 45.5 to 73.6 and APEX Score from 5.0 to 21.3, while enabling Qwen3.5-27B to achieve highly competitive performance and outperform strong competitors. Our analyses confirm the efficacy of the proposed method and reveal consistent scaling behaviors across both data volume and interaction horizons.
Fan Liu, Yanhao Wang East China Normal University, Min Zhang East China Normal University, Zhikang Chen University of Oxford, Zeyuan Li, Lewei He, Jiahui Pan South China Normal University
This paper proposes shortcut decoding, an efficient framework for accelerating Chain-of-Thought (CoT) reasoning in Large Language Models (LLMs). Existing methods that prune or employ early stopping to reduce latency often compromise reasoning reliability. Motivated by the observation that LLMs frequently converge to correct solutions internally before completing explicit textual reasoning, we propose a dual-signal adaptive controller that integrates lightweight probes over internal hidden states with step-level entropy. This controller detects convergence of reasoning during generation and adaptively selects between a fast-exit path and a stability-verified path to remove redundant steps while preserving answer correctness. Experiments across multiple mathematical reasoning benchmarks demonstrate that shortcut decoding reduces token usage by approximately 35%, maintains accuracy comparable to full CoT decoding, and achieves final-answer accuracy comparable to the full CoT baseline, outperforming existing early-stopping methods without updating the base model. Our code is available at https://github.com/kuromi9527/shortcut_decoding.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Zihan Zheng South China Normal University, Tianle Cui, Taoran Wang South China Normal University, Fengtao Wang South China Normal University, Jiahui Pan South China Normal University, Lewei He, Qianglong Chen
Despite significant advances in LLM-driven GUI agents, the field remains constrained by the challenge of reconciling high-fidelity realism with verifiable evaluation accuracy. To address this, we introduce NaturalGAIA, a verifiable evaluation dataset grounded in real-world human GUI interaction intents. By decoupling logical causal pathways from linguistic narratives, it rigorously simulates natural human intent, characterized by cognitive non-linearity and contextual dependencies. Furthermore, we propose LightManus-Jarvis, a hierarchical collaborative framework where LightManus manages dynamic topological planning and context evolution, while Jarvis ensures execution precision via hybrid visual-structural perception. Experiments demonstrate that our approach achieves a Weighted Pathway Success Rate of 45.6%, significantly outperforming the state-of-the-art baseline (21.1%), while reducing token consumption by 75% and execution time by 76%. These results validate the efficacy of the macro-planning and micro-execution paradigm in handling complex naturalized tasks. Our code is publicly available at: https://anonymous.4open.science/r/NatureGAIA-721F/.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Vision-Language Models (VLMs) excel at photorealistic generation, yet often struggle to represent abstract meaning such as idiomatic interpretations of noun compounds. To study whether high visual fidelity interferes with idiomatic compositionality under visual abstraction, we introduce DIVA, a controlled benchmark that replaces high-fidelity visual detail with schematic iconicity by generating paired, sense-anchored visualizations for literal and idiomatic readings.We further propose Semantic Alignment Gap (\Delta), an architecture-agnostic metric that quantifies divergence between literal and idiomatic visual grounding.We additionally introduce a directional signed bias b(t) to separately measure the direction and strength of literal preference.Evaluating 8 recent VLMs, we reveal a consistent Literal Superiority Bias: model scale alone does not resolve literal preference, and increased visual fidelity is associated with weaker symbolic alignment, suggesting cognitive interference from hyper-realistic imagery. Our findings suggest that improving compositional understanding requires iconographic abstraction of visual input and anchoring interpretation and generation in intended meaning.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表