paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

SimSD: Simple Speculative Decoding in Diffusion Language Models

Junxia Cui, Haotian Ye, Runchu Tian, Hongcan Guo, Jinya Jiang, Haoru Li, Chaojie Ren, Yiming Huang, Kaijie Zhu, Zhongkai Yu, Kun Zhou, Jingbo Shang

Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs, offering faster inference through parallel or blockwise decoding. However, their masked language modeling formulation remains incompatible with standard token-level speculative decoding, one of the most effective acceleration techniques for AR models. In AR decoding, the causal mask preserves temporally valid token-level contexts, enabling a target model to verify multiple drafted tokens in a single forward pass. In contrast, dLLMs rely on mask tokens and bidirectional attention, causing the effective context to change across denoising steps and preventing direct token-level speculative verification. To bridge this gap, we propose a simple but effective speculative decoding algorithm for diffusion language models, named SimSD, which mainly adopts a plug-and-play masking strategy that equips dLLMs with temporally valid token-level contexts for speculative decoding. Our method explicitly introduces reference tokens from draft-model predictions and designs an attention mask that regulates their interaction with current-step tokens, allowing dLLMs to compute valid logits for drafted tokens in a single forward pass. This restores the key verification ability provided by causal masking in AR models while preserving the parallel decoding advantages of dLLMs. The proposed method is training-free and can be flexibly integrated with other acceleration techniques such as KV cache and blockwise decoding. Experiments on SDAR-family dLLMs across four benchmarks show that our method achieves up to 7.46x higher decoding throughput while maintaining and even improving average generation quality.

arXiv

Citation Grounding Measures the Oracle: Graph Coverage Determines Reported LLM Hallucination Rates in Law

Volodymyr Ovcharov

Verifying LLM-generated legal citations against a graph of citations extracted from real court decisions is an appealing way to measure hallucination at scale: no annotators, no reference answers. We show that what such a metric reports is governed by the coverage of the graph it queries rather than by the model it evaluates, and that at the coverage where its verdicts become trustworthy it stops distinguishing models at all. We score 400 responses (100 Ukrainian legal queries x four commercial LLMs) against two snapshots of the same national citation graph, holding responses, extractor and metric fixed. Against a sparse snapshot (4.7e5 records) citation grounding ranges 0.791-0.855, apparently showing 15-21% of citations hallucinated. Against a dense snapshot of the same registry re-derived ten weeks later (3.3e8 records, 5.8e7 decisions) the identical responses score 0.989-0.999. Subsampling shows the cause is coverage: harvesting modelled as uniform record sampling, calibrated on nothing but the record count, reproduces the sparse scores to within 0.018 while knowing nothing about the models. Bootstrapping over the queries shows the other half, which no version of this work reported: no pair of systems is separable at 95% at any oracle size tested. The metric is caught between two failures. Sparse oracles discriminate, but what they discriminate is harvesting coverage; dense oracles are trustworthy and separate nothing. Densifying the graph, the obvious remedy for the first, produces the second. An independent legislation registry adjudicates: all 54 citations flagged by the sparse oracle name real articles, a 100% false-positive rate; of the four flagged by the dense oracle, two are fabrications, one a coverage gap, and one we cannot classify - it looks like a repealed provision, which is the argument in miniature.

arXiv

DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation

Jaehun Jung, Hyunwoo Kim, Brandon Cui, Ximing Lu, David Acuna, Prithviraj Ammanabrolu, Yejin Choi

Distillation enables compact Vision-Language Models (VLMs) to obtain strong reasoning capabilities, yet the prompts driving this process are typically chosen via simple heuristics or aggregated from off-the-shelf datasets. We reveal a critical inefficiency in this approach: up to 69% of the prompts in standard chart / document reasoning datasets are effectively zero-delta, meaning the teacher and student already induce the exact same answer distribution. Training on these prompts provides minimal learning signal, causing student improvement to rapidly saturate regardless of data scale. To escape the zero-delta trap, we return to first principles: distillation fundamentally minimizes distributional divergence, and thus a prompt is valuable only if it exposes a functional capability gap between the teacher and student. We quantify this gap through answer divergence ($Δ$), demonstrating that non-zero divergence is critical for effective scaling. Building on this insight, we propose a staged synthesis pipeline that repurposes existing datasets as seeds, actively targeting student failure modes to produce better prompts. The result is DeltaPrompts, a diverse dataset of 200k synthetic, high-divergence reasoning problems. We evaluate DeltaPrompts across three distinct settings: on-policy distillation with the target teacher-student pair, transfer to a novel model family without regenerating the data, and off-policy fine-tuning of a non-reasoning model. Across all scenarios, DeltaPrompts drives substantial gains, yielding up to 15% relative improvement even on top of a highly-optimized reasoning model (e.g., Qwen3-VL-8B-Thinking) -- averaged over 10 benchmarks spanning chart, document and perception-centric reasoning.

arXiv

One Word at a Time: Incremental Completion Decomposition Breaks LLM Safety

Samee Arif, Naihao Deng, Zhijing Jin, Rada Mihalcea

Large Language Models (LLMs) are trained to refuse harmful requests, yet they remain vulnerable to jailbreak attacks that exploit weaknesses in conversational safety mechanisms. We introduce Incremental Completion Decomposition ICD, a trajectory-based jailbreak strategy that elicits a sequence of single-word continuations related to a malicious request before eliciting the full response. In addition, we propose ICD variants that use model-generated or attacker-injected intermediate continuations, as well as final-response prefilling. We evaluate these variants across a broad set of open-weight model families, demonstrating superior Attack Success Rate (ASR) on AdvBench, JailbreakBench, and StrongREJECT compared to existing methods. In addition, we provide a theoretical account of why ICD is effective and present mechanistic evidence that successful attack trajectories suppress refusal-related representations and shift activations away from safety-aligned states.

arXiv

Source-Modality Monitoring in Vision-Language Models

Etha Tianze Hua, Tian Yun, Ellie Pavlick

We define and investigate source-modality monitoring -- the ability of multimodal models to track and communicate the input source from which pieces of information originate. We consider source-modality monitoring as an instance of the more general binding problem, and evaluate the extent to which models exploit syntactic vs. semantic signals in order to bind words like image in a user-provided prompt to specific components of their input and context (i.e., actual images). Across experiments spanning 11 vision-language models (VLMs) performing target-modality information retrieval tasks, we find that both syntactic and semantic signals play an important role, but that the latter tend to outweigh the former in cases when modalities are highly distinct distributionally. We discuss the implications of these findings for model robustness, and in the context of increasingly multimodal agentic systems.

arXiv

The Cost of Language: Centroid Erasure Exposes and Exploits Modal Competition in Multimodal Language Models

Akshay Paruchuri, Ishan Chatterjee, Henry Fuchs, Ehsan Adeli, Piotr Didyk

Multimodal language models systematically underperform on visual perception tasks, yet the structure underlying this failure remains poorly understood. We propose centroid replacement, mapping tokens to their nearest K-means centroid and removing within-cluster residual structure, as a controlled probe for modal dependence. Across seven models spanning four architecture families, post-image text replacement costs 4x more accuracy than visual replacement on six BLINK tasks; VPBench and MedBLINK preserve this aggregate ordering. Since text replacement also disrupts the task and answer interface, the gap measures relative dependence. Text centroid contrastive decoding (TCCD) exploits this asymmetry without retraining, recovering up to +16.9% accuracy on an individual task at oracle best-per-task $α_\text{interp}$; every model gains on at least one task, although gains vary across tasks and models. Together, centroid replacement provides a retraining-free audit of modal dependence on labeled data, while TCCD offers a reusable inference-time intervention. Code and artifacts are available at: https://github.com/yahskapar/centroid-erasure

arXiv

Multi-objective Evolutionary Merging Enables Efficient Reasoning Models

Mario Iacobelli, Adrian Robert Minut, Tommaso Mencattini, Donato Crisostomi, Andrea Santilli, Iacopo Masi, Emanuele Rodolà

Reasoning models achieve strong performance on complex problems by leveraging long chains of thought, but this deliberate reasoning incurs substantial inference-time cost. The Long-to-Short (L2S) reasoning problem seeks to preserve accuracy while reducing generated tokens. Yet, current training-free model merging approaches rely on brittle, fixed-hyperparameter arithmetic methods that force suboptimal compromises. We introduce \textbf{Evo-L2S}, a multi-objective evolutionary model merging framework that explicitly optimizes accuracy and output length to recover a Pareto front of merged models. To make this search computationally tractable, we propose an entropy-based subset sampling technique that substantially reduces fitness-estimation overhead. Across six mathematical reasoning benchmarks, Evo-L2S reduces reasoning length by over 50\% at the 1.5B and 7B scales while preserving or improving problem-solving accuracy; at 14B, the steeper Pareto front reveals that attainable compression depends on the intrinsic compressibility of the reasoning model. Overall, Evo-L2S shows that reasoning models can be made substantially more concise while preserving strong problem-solving performance.

arXiv

BibTeX Citation Errors in Scientific Publishing Agents: Evaluation and Mitigation

Delip Rao, Chris Callison-Burch

Large language models with web search are increasingly used in scientific publishing agents, yet they produce BibTeX entries with pervasive field-level errors stemming from omission, partial corruption, substitution, and hallucination. We construct a benchmark of 931 papers across four domains and three citation tiers---popular, low-citation, and recent post-cutoff---with version-aware ground truth. Three search-enabled frontier models (GPT-5, Claude Sonnet-4.6, Gemini-3 Flash) generate approximately 23,000 field-level observations. Overall accuracy is 83.6%, but only 50.9% of entries are fully correct; accuracy drops 27.7 pp from popular to recent papers, revealing heavy reliance on parametric memory even when search is available. Co-occurrence analysis identifies two failure modes: wholesale entry substitution and isolated field error. We present clibib, an open-source tool for deterministic BibTeX retrieval, as a mitigation mechanism. Two-stage integration raises accuracy to 91.5% (+8.0 pp) and fully correct entries to 78.3%, with a 0.8% regression rate. Separating search from revision yields larger gains and lower regression than single-stage tool loops (0.8% vs. 4.8%), demonstrating that integration architecture matters independently of model/tool capability. We release clibib and an accompanying agent skill under the MIT License to improve citation accuracy in increasingly automated scientific workflows.

arXiv

Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines

Jingjie Ning, Xueqi Li, Chengyu Yu

Multi-LLM revision pipelines, in which a second model reviews and improves a draft produced by a first, are widely assumed to derive their gains from genuine error correction. We question this assumption with a controlled decomposition experiment that uses four matched conditions to separate second-pass gains into three additive components: re-solving, scaffold, and content. We evaluate this design across two model pairs on three benchmarks spanning knowledge-intensive MCQ and competitive programming. Our results show that the gains of multi-LLM revision are not monolithic, but depend on task structure, draft quality, and the type of draft information. On MCQ tasks, where the answer space is constrained and drafts provide little structural guidance, most gains are consistent with stronger-model re-solving, and directly routing queries to the stronger model can be more effective than revising a weak draft. On code generation tasks, however, two-stage prompting remains useful because even semantically null drafts can provide substantial structural scaffolding, while weak draft content can be harmful. Finally, role-reversed experiments show that strong drafts clearly benefit weak reviewers. Ultimately, our findings demonstrate that the utility of multi-LLM revision is dynamically bottlenecked by task structure and draft quality, necessitating more targeted pipeline designs rather than blanket revision strategies.

arXiv

Thinking Is Not Telling: Information Disclosure in User-Service LLM Agents

Jiatong Li, Changdae Oh, Hyeong Kyu Choi, Jindong Wang, Sharon Li

User-engaged LLM agents increasingly operate in service scenarios where task success depends on coordination between the agent, the user, and a stateful environment. In such interactions, the agent often has access to task policies, tool results, and environment states that the user does not observe. This makes agent-user communication a central component of task completion. In this work, we study a communication-level failure mode of user-service agents: user-invisible reasoning does not necessarily translate into timely user-facing information disclosure. We introduce information disclosure as a measurable communication mechanism, covering state corrections, available options, constraints, consequences, and proactively retrieved environment information. We use this perspective to analyze the widely used user-invisible ``think'' tool, which allows agents to reason internally before responding or acting. Across five models and three user-service scenarios, we first show that enforced thinking has unstable utility. We then analyze response scaling under different think efforts and find that more internal thinking does not reliably translate into richer user-facing communication. Using evidence-grounded probing and turn-level counterfactual intervention, we show that injecting golden decision-relevant information produces the clearest improvement in First Edit Correction Rate, outperforming verbosity and direct think-content controls. This indicates that missing disclosure can causally affect the agent's immediate downstream environment-edit behavior. We further find that a lightweight disclosure-aware prompt mitigates degradation from enforced thinking. These results suggest that the key challenge is not simply making agents think more, but ensuring that private reasoning and environment knowledge are externalized as timely, user-facing information disclosure.

arXiv

Memorization Dynamics in Knowledge Distillation for Language Models

Jaydeep Borkar, Karan Chadha, Niloofar Mireshghallah, Yuchen Zhang, Irina-Elena Veliche, Archi Mitra, David A. Smith, Zheng Xu, Diego Garcia-Olano

Knowledge Distillation (KD) is increasingly adopted to transfer capabilities from large language models to smaller ones, offering significant improvements in efficiency and utility while often surpassing standard fine-tuning. Beyond performance, KD is also explored as a privacy-preserving mechanism to mitigate the risk of training data leakage. While training data memorization has been extensively studied in standard pre-training and fine-tuning settings, its dynamics in a knowledge distillation setup remain poorly understood. In this work, we study memorization across the KD pipeline using three large language model (LLM) families (Pythia, OLMo-2, Qwen-3) and three datasets (FineWeb, Wikitext, Nemotron-CC-v2). We find: (1) distilled models memorize significantly less training data than standard fine-tuning (reducing memorization by more than 50%); (2) some examples are inherently easier to memorize and account for a large fraction of memorization during distillation (over ~95%); (3) student memorization is predictable prior to distillation using features based on zlib entropy, KL divergence, and perplexity; and (4) while soft and hard distillation have similar overall memorization rates, hard distillation poses a greater risk: it inherits $2.7\times$ more teacher-specific examples than soft distillation. Overall, we demonstrate that distillation can provide both improved generalization and reduced memorization risks compared to standard fine-tuning.

arXiv

Length-MAX Tokenizer for Language Models

Dong Dong, Weijie Su

We introduce a new tokenizer for language models that minimizes the average tokens per character, thereby reducing the number of tokens needed to represent text during training and to generate text during inference. Our method, which we refer to as the Length-MAX tokenizer, obtains its vocabulary by casting a length-weighted objective maximization as a graph partitioning problem and developing a greedy approximation algorithm. On FineWeb and diverse domains, it yields 14--18\% fewer tokens than Byte Pair Encoding (BPE) across vocabulary sizes from 10K to 50K, and the reduction is 13.0\% when the size is 64K. Training GPT-2 models at 124M, 355M, and 1.3B parameters from scratch with five runs each shows 18.5\%, 17.2\%, and 18.5\% fewer steps, respectively, to reach a fixed validation loss, and 13.7\%, 12.7\%, and 13.7\% lower inference latency, together with a 16\% throughput gain at 124M, while consistently improving on downstream tasks including reducing LAMBADA perplexity by 11.7\% and enhancing HellaSwag accuracy by 4.3\%. Moreover, the Length-MAX tokenizer achieves 99.62\% vocabulary coverage and the out-of-vocabulary rate remains low at 0.12\% on test sets. These results demonstrate that optimizing for average token length, rather than frequency alone, offers an effective approach to more efficient language modeling without sacrificing -- and often improving -- downstream performance. The tokenizer is compatible with production systems and reduces embedding and KV-cache memory by 18\% at inference.

arXiv

Reasoning about Intent for Ambiguous Requests

Irina Saparina, Mirella Lapata

Large language models often respond to ambiguous requests by implicitly committing to one interpretation, frustrating users and creating safety risks when that interpretation is wrong. We propose generating a single structured response that enumerates the different ways an ambiguous request can be interpreted, each coupled with a corresponding answer. Our models are trained with reinforcement learning using a dual reward objective: recall on ambiguous inputs to maximise coverage of valid interpretations, and precision on unambiguous ones to suppress spurious alternatives. Training requires only multiple valid answers per input as supervision, no clarification questions or explicit interpretations are needed. Experiments on conversational question answering and semantic parsing demonstrate that our method achieves higher coverage of valid answers than baseline approaches. Human evaluation confirms that predicted interpretations are meaningful and explain their corresponding answers. Our approach promotes transparency with explicit interpretations, avoids additional interaction rounds by producing all interpretations in a single generation, and supports downstream applications through its structured output format.

arXiv

Routesplain: Towards Faithful and Intervenable Routing for Software-related Tasks

Adam Štorek, Vikas Upadhyay, Marianne Menglin Liu, Daniel W. Peterson, Anshul Mittal, Sujeeth Bharadwaj, Fahad Shah, Sujith Ravi, Dan Roth

LLMs now tackle a wide range of software-related tasks, yet we show that their performance varies markedly both across and within these tasks. Routing user queries to the appropriate LLMs can therefore help improve response quality while reducing cost. Prior work, however, has focused mainly on general-purpose LLM routing via black-box models. We introduce Routesplain, the first LLM router for software-related tasks, including multilingual code generation and repair, input/output prediction, and computer science QA. Unlike existing routing approaches, Routesplain first extracts human-interpretable concepts from each query (e.g., task, domain, reasoning complexity) and only routes based on these concepts, thereby providing intelligible, faithful rationales. We evaluate Routesplain on 16 state-of-the-art LLMs across eight software-related tasks; Routesplain outperforms individual models both in terms of accuracy and cost, and equals or surpasses all black-box baselines, with concept-level intervention highlighting avenues for further router improvements.

arXiv

The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperation

Tim R. Davidson, Adam Fourney, Saleema Amershi, Robert West, Eric Horvitz, Ece Kamar

The trajectory of AI development suggests that we will increasingly rely on agent-based systems powered by language models, composed of independently developed agents with different information, privileges, and tools. The success of these systems will depend critically on effective collaboration among these heterogeneous agents, even under partial observability. Despite intense interest, the literature lacks empirical studies evaluating agentic collaboration without relying on fixed communication protocols, limiting insights for open-world deployments. We propose an illustrative collaborative maze-solving benchmark that (i) isolates collaborative capabilities, (ii) modulates problem complexity, (iii) enables scalable automated grading, and (iv) imposes no output-format constraints, benchmarking unguided, natural communication. Using this benchmark, we evaluate 32 leading open- and closed-source models in solo, homogeneous, and heterogeneous pairings. Our results reveal a surprising collaboration gap: models that perform well solo often degrade substantially when required to collaborate. We identify mitigations that show remarkable influence. For example, a small nudge via a relay inference approach, where a stronger agent leads before handing off to a weaker one, closes much of the gap. Our findings argue for (1) collaboration-aware evaluation, (2) training strategies to enhance collaborative capabilities, and (3) deliberate interaction design to elicit agents' collaboration skills, principles relevant to AI-AI and human-AI settings where agents must establish common ground.

arXiv

Quokka: Accelerating Program Verification with LLMs via Invariant Synthesis

Anjiang Wei, Tianran Sun, Tarun Suresh, Haoze Wu, Ke Wang, Alex Aiken

Program verification relies on loop invariants, yet automatically discovering strong invariants remains a long-standing challenge. We investigate whether large language models (LLMs) can accelerate program verification by generating useful loop invariants. We introduce Quokka, a framework for LLM-based invariant synthesis with soundness guarantees and state-of-the-art performance. Unlike prior work that treats LLM outputs as noisy symbolic material requiring substantial post-processing, Quokka adopts a simpler algorithm design that directly validates whether each LLM-generated invariant helps prove the target assertion. We construct a benchmark of 866 evaluation instances and 3589 training instances derived from SV-COMP, and evaluate 9 LLMs spanning multiple model families. We demonstrate that supervised fine-tuning and Best-of-N sampling yield measurable improvements, and we show that Quokka consistently outperforms prior LLM-based verifiers. Our code and data are publicly available at https://github.com/Anjiang-Wei/Quokka

arXiv

Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models

Guangyu Yang, Jinghong Chen, Jingbiao Mei, Weizhe Lin, Bill Byrne

Large Language Models (LLMs) remain vulnerable to jailbreak attacks, which attempt to elicit harmful responses from LLMs. The evolving nature and diversity of these attacks pose many challenges for defense systems, including (1) adaptation to counter emerging attack strategies without costly retraining, and (2) control of the trade-off between safety and utility. To address these challenges, we propose Retrieval-Augmented Defense (RAD), a novel framework for jailbreak detection that incorporates a database of known attack examples into Retrieval-Augmented Generation, which is used to infer the underlying, malicious user query and jailbreak strategy used to attack the system. RAD enables training-free updates for newly discovered jailbreak strategies and provides a mechanism to balance safety and utility. Experiments on StrongREJECT show that RAD substantially reduces the effectiveness of strong jailbreak attacks such as PAP and PAIR while maintaining low rejection rates for benign queries. We propose a novel evaluation scheme and show that RAD achieves a robust safety-utility trade-off across a range of operating points in a controllable manner.

arXiv

LogicIF: Towards Complex Logic Instruction Following

Mian Zhang, Shujian Liu, Sixun Dong, Ming Yin, Yebowen Hu, Xun Wang, Simin Ma, Song Wang, Sathish Reddy Indurthi, Haoyun Deng, Zhiyu Zoey Chen, Kaiqiang Song

Instruction following has catalyzed the recent era of Large Language Models (LLMs) and is the foundational skill underpinning more advanced capabilities such as reasoning and agentic behaviors. As tasks grow more challenging, the logic structures embedded in natural language instructions becomes increasingly intricate. However, how well LLMs perform on such logic-intensive instructions remains under-explored. We propose Logic Instruction Following (LogicIF), a task requiring models to precisely follow and simulate every logic step within complex instructions. To generate these instructions, we construct LogicIFGen, a scalable, automated framework for generating verifiable instructions from code functions, which can naturally express rich logic such as conditions, loops, nesting, and function calls. Using this framework, we curate a collection of complex code functions to construct LogicIFEval, a benchmark comprising 426 verifiable, human-examined, logic-rich instructions. Our experiments demonstrate that current state-of-the-art LLMs still struggle to correctly follow the instructions in LogicIFEval. Most LLMs can only follow fewer than 60% of the instructions, revealing significant deficiencies in their capacity to handle instructions that involve complex logic structures. To further demonstrate the efficacy of our framework, we collect an extensive set of code functions across a wide range of logic difficulties to generate LogicIFTrain, a fully synthesized training set featuring 27,324 verifiable instructions. Our results show that a model trained on LogicIFTrain using reinforcement learning significantly outperforms the base model on both in-domain and out-of-domain benchmarks. All the data, codes and models are released at https://github.com/mianzhang/LogicIF.

arXiv

WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks

Atsuyuki Miyai, Zaiying Zhao, Kazuki Egashira, Atsuki Sato, Tatsumi Sunada, Shota Onohara, Hiromasa Yamanishi, Mashiro Toyooka, Kunato Nishina, Ryoma Maeda, Kiyoharu Aizawa, Toshihiko Yamasaki

Powered by large language models (LLMs), web browsing agents operate graphical user interfaces in a human-like manner, offering a transparent and general framework for automating web-based tasks. As these agents rapidly improve and achieve strong performance on existing benchmarks such as WebArena, a key question arises: $\textit{Can current benchmarks still accurately evaluate the capabilities of increasingly powerful agents, especially for more tedious and cognitively demanding tasks?}$ In this paper, we present $\textbf{WebChoreArena}$, a substantial extension of WebArena designed to push beyond general browsing scenarios. WebChoreArena introduces 532 carefully curated tasks developed over 300+ hours, explicitly targeting more labor-intensive and complex web chores. It systematically expands the evaluation space along three critical dimensions: (i) $\textbf{Massive Memory}$, requiring agents to accurately retain and retrieve large amounts of information from observations; (ii) $\textbf{Calculation}$, demanding precise mathematical reasoning over collected information; and (iii) $\textbf{Long-Term Memory}$, necessitating consistent information tracking across multiple webpages. Built directly on top of the four reproducible WebArena environments, WebChoreArena ensures strict compatibility and enables fair, controlled comparisons with prior work. Our experimental results demonstrate that as LLMs evolve, significant performance improvements are observed on WebChoreArena. These findings suggest that WebChoreArena is well-suited to measure the advancement of state-of-the-art LLMs with greater clarity. Nevertheless, the results also indicate that even with GPT-5, there remains substantial room for improvement compared to WebArena, highlighting the increased challenges posed by WebChoreArena.

arXiv

SuperCoder: Assembly Program Superoptimization with Large Language Models

Anjiang Wei, Tarun Suresh, Huanmi Tan, Yinglun Xu, Gagandeep Singh, Ke Wang, Alex Aiken

Superoptimization is the task of transforming a program into a faster one, and ideally the very fastest possible one, while preserving its input-output behavior. In this work, we investigate whether large language models (LLMs) can serve as superoptimizers, generating assembly programs that outperform code already optimized by industry-standard compilers in end-to-end runtime. We construct the first large-scale benchmark for this problem, consisting of 8,072 assembly programs averaging 130 lines, in contrast to prior datasets restricted to 2-15 straight-line, loop-free programs. We evaluate 23 LLMs on this benchmark and find that the strongest baseline, Claude-opus-4, achieves a 51.5% test-passing rate and a 1.43x average speedup over gcc -O3. To further enhance performance, we fine-tune models with reinforcement learning, optimizing a reward function that integrates correctness and performance speedup. Starting from Qwen2.5-Coder-7B-Instruct (61.4% correctness, 1.10x speedup), the fine-tuned model SuperCoder attains 95.0% correctness and 1.46x average speedup, with additional improvement enabled by Best-of-N sampling and iterative refinement. Our results demonstrate, for the first time, that LLMs can be applied as superoptimizers for assembly programs, establishing a foundation for future research in program performance optimization beyond compiler heuristics.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.