paperlist.ai

AI 顶会论文

AI 顶会论文库

检索 30+ 个顶会的论文，包括 NeurIPS、ICLR、ICML、CVPR、ACL、AAAI 等。输入关键词筛选，打开任意一篇查看摘要、作者和链接。

arXiv

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Ziyu Ma, Shidong Yang, Yuxiang Ji, Xucong Wang, Yong Wang, Yiming Hu, Tongwen Huang, Xiangxiang Chu

Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after deployment. As a result, similar workflows, tool usage patterns, and failure modes are repeatedly rediscovered across users, preventing the system from improving with experience. While interactions from different users provide complementary signals about when a skill works or fails, existing systems lack a mechanism to convert such heterogeneous experiences into reliable skill updates. To address these issues, we present SkillClaw, a framework for collective skill evolution in multi-user agent ecosystems, which treats cross-user and over-time interactions as the primary signal for improving skills. SkillClaw continuously aggregates trajectories generated during use and processes them with an autonomous evolver, which identifies recurring behavioral patterns and translates them into updates to the skill set by refining existing skills or extending them with new capabilities. The resulting skills are maintained in a shared repository and synchronized across users, allowing improvements discovered in one context to propagate system-wide while requiring no additional effort from users. By integrating multi-user experience into ongoing skill updates, SkillClaw enables cross-user knowledge transfer and cumulative capability improvement, and experiments on WildClawBench show that limited interaction and feedback, it significantly improves the performance of Qwen3-Max in real-world agent scenarios.

arXiv

Is CLIP Cross-Eyed? Revealing and Mitigating Center Bias in the CLIP Family

Oscar Chew, Hsiao-Ying Huang, Kunal Jain, Tai-I Chen, Khoa D Doan, Kuan-Hao Huang

Recent research has shown that contrastive vision-language models such as CLIP often lack fine-grained understanding of visual content. While a growing body of work has sought to address this limitation, we identify a distinct failure mode in the CLIP family, which we term center bias, that persists even in recent model variants. Specifically, CLIP tends to disproportionately focus on the central region of an image, overlooking important objects located near the boundaries. This limitation is fundamental as failure to recognize relevant objects makes it difficult to perform any sophisticated tasks that depend on those objects. To understand the underlying causes of the limitation, we conduct analyses from both representation and attention perspectives. Using interpretability methods, i.e., embedding decomposition and attention map analysis, we find that relevant concepts especially those associated with off-center objects vanish from the model's embedding in the final representation due to information loss during the aggregation of visual embeddings, particularly the reliance on pooling mechanisms. Finally, we show that this bias can be alleviated with training-free strategies such as visual prompting and attention redistribution by redirecting models' attention to off-center regions.

arXiv

StoryScope: Investigating idiosyncrasies in AI fiction

Jenna Russell, Rishanth Rajendhran, Chau Minh Pham, Mohit Iyyer, John Wieting

As AI-generated fiction becomes increasingly prevalent, questions of authorship and originality are becoming central to how written work is evaluated. While most existing work in this space focuses on identifying surface-level signatures of AI writing, we ask instead whether AI-generated stories can be distinguished from human ones without relying on stylistic signals, focusing on discourse-level narrative choices such as character agency and chronological discontinuity. We propose StoryScope, a pipeline that automatically induces a fine-grained, interpretable feature space of discourse-level narrative features across 10 dimensions. We apply StoryScope to a parallel corpus of 10,272 writing prompts, each written by a human author and five LLMs, yielding 61,608 stories, each ~5,000 words, and 304 extracted features per story. Narrative features alone achieve 93.2% macro-F1 for human vs. AI detection and 68.4% macro-F1 for six-way authorship attribution, retaining over 97% of the performance of models that include stylistic cues. A compact set of 30 core narrative features captures much of this signal: AI stories over-explain themes and favor tidy, single-track plots while human stories frame protagonist' choices as more morally ambiguous and have increased temporal complexity. Per-model fingerprint features enable six-way attribution: for example, Claude produces notably flat event escalation, GPT over-indexes on dream sequences, and Gemini defaults to external character description. We find that AI-generated stories cluster in a shared region of narrative space, while human-authored stories exhibit greater diversity. More broadly, these results suggest that differences in underlying narrative construction, not just writing style, can be used to separate human-written original works from AI-generated fiction.

arXiv

Goose: Anisotropic Speculation Trees for Training-Free Speculative Decoding

Tao Jin, Phuong Minh Nguyen, Naoya Inoue

Speculative decoding accelerates large language model inference by drafting multiple candidate tokens and verifying them in a single forward pass. Candidates are organized as a tree: deeper trees accept more tokens per step, but adding depth requires sacrificing breadth (fallback options) under a fixed verification budget. Existing training-free methods draft from a single token source and shape their trees without distinguishing candidate quality across origins. We observe that two common training-free token sources -- n-gram matches copied from the input context, and statistical predictions from prior forward passes -- differ sharply in acceptance rate (~6x median gap, range 2-18x across five models and five benchmarks). We prove that when such a quality gap exists, the optimal tree is anisotropic (asymmetric): reliable tokens should form a deep chain while unreliable tokens spread as wide branches, raising the depth ceiling of balanced trees. We realize this structure in GOOSE, a training-free framework that builds an adaptive spine tree: a deep chain of high-acceptance context-matched tokens with wide branches of low-acceptance alternatives at each node. The resulting tree provably accepts at least as many tokens per step as either source alone. On five LLMs (7B-33B) and five benchmarks, GOOSE achieves 1.9-4.3x lossless speedup, outperforming balanced-tree baselines by 12-33% under the same budget.

arXiv

ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention

Xinyan Wang, Xiaogeng Liu, Ming Pei, Chaowei Xiao

Large Reasoning Models (LRMs) often reach a correct solution before their long Chain-of-Thought trace ends, yet continue with redundant verification, repeated attempts, or unnecessary exploration that wastes computation and can even overturn the correct answer. We frame this behavior as a latent productive-to-redundant transition and show it is directly reflected in hidden states: around first-correct-solution (FCS) boundaries, late-layer representations separate efficient from overthinking tokens, while boundary-permutation and position controls collapse. We propose ROM, a streaming intervention framework that monitors a frozen LRM with a lightweight hidden-state detector ($\sim$0.1\% of backbone parameters) and intervenes at well-formed reasoning boundaries; Counterfactual Self-Correction (CSC) balances supervision with wrong$\rightarrow$correct trajectories, preserving useful pre-FCS self-correction. Unlike prior adaptive early-exit methods, ROM extracts no intermediate answers, launches no probe decoding, and updates no backbone weights. Across five backbones from three model families and five reasoning benchmarks, against ten recent baselines under a shared protocol, ROM$_{\text{CSC}}$ attains the highest accuracy in 19 of 25 model--benchmark settings, cuts response length by 28--77\% (mean 45\%) versus vanilla decoding, and is the only method on the accuracy--length Pareto front in every setting. The same MATH500-trained supervision transfers zero-shot across scales, families, and task domains, and end-to-end wall-clock latency drops by 46.5\% with $\sim$5\% per-token overhead. Code is available at https://github.com/SaFo-Lab/ROM.

arXiv

Human-Level Text-to-SQL via Reinforcement Learning on Verified Data, Without Pipeline Engineering

Yuxuan Zhu, Tengjun Jin, Yoojin Choi, Daniel Kang

Translating natural language questions to SQL queries (Text-to-SQL) is a long-standing problem in database research. Recent efforts have focused on improving accuracy by building increasingly complex multi-stage large LLM pipelines, layering task decomposition, schema linking, and model-based query selection on top of an LLM. Despite this growing complexity, a substantial gap (>10%) between such systems and human experts persists on benchmarks, suggesting that pipeline engineering alone has hit a ceiling. We show that human-level Text-to-SQL performance is achievable by fine-tuning an LLM using RLVR on clean data, without pipeline components. In this paper, we identified the dominant bottleneck for RLVR on Text-to-SQL: existing training data contains pervasive annotation errors that mislead optimization. To address this, we developed a multi-round, expert-driven verification pipeline and used it to curate BIRD-Platinum, a dataset of 2.5k verified instances sampled from BIRD Train, with errors corrected in 61% of instances. We show that fine-tuning Qwen3-235B on BIRD-Platinum yields consistent improvements (11-16%) over BIRD Train on Arcwise-Plat (an expert-verified version of BIRD) and Spider2, outperforming SOTA open-source systems by 0.6-16%. Furthermore, we diagnosed two failure modes of standard RLVR on Text-to-SQL. We find that (1) result-based rewards have non-trivial false positive rates, and (2) models systematically ignore the external knowledge in BIRD-style problems. To address them, we propose ReViSQL-BIRD, a specialized reward shaping method that combines result-based rewards with SQL equivalence verification and leverages process rewards for incentivizing external-knowledge use. We fine-tuned Kimi-K2.6 with ReViSQL-BIRD. On Arcwise-Plat, ReViSQL-BIRD-K2.6 is the first method to achieve human-level accuracy (92.96%), outperforming top five open-source systems by 10-22%.

arXiv

LLMs Remember First, Forget Last: Dual-Process Interference in Large Language Models

Sourav Chattaraj, Kanak Raj

Large language models can process millions of tokens, yet how they handle conflicting information within context remains poorly understood. From patient health logs tracking evolving vital signs to legal documents with superseding clauses, real-world applications routinely require models to retrieve specific values from streams of semantically similar, competing updates. We adapt classical interference paradigms from cognitive psychology to compare retroactive interference (RI; recalling initial values after updates) and proactive interference (PI; recalling recent values despite competing prior encodings) across 39 LLMs spanning 1B to 2.5T parameters. Every model exhibits the same pattern: PI causes substantially greater degradation than RI (d = 1.73), the opposite of the typical human finding where new information more readily disrupts old. Four lines of evidence indicate that RI and PI engage distinct mechanisms: model size predicts RI resistance but not PI; the two scores correlate only weakly; error analysis reveals qualitatively different failure profiles, with RI failures reflecting passive retrieval failure and PI failures reflecting active primacy intrusion; and hallucination rates remain below 1% in both conditions. An adaptive bootstrap design further shows that RI decays smoothly while PI collapses bimodally at high interference, consistent with gradual dilution versus winner-take-all attention dynamics. These findings characterize a systematic primacy bias in transformer attention, with implications for reliable deployment in settings where in-context information evolves over time.

arXiv

From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves

Haritz Puerto, Haonan Li, Xudong Han, Timothy Baldwin, Iryna Gurevych

Large reasoning models (LRMs) produce reasoning traces (RTs) that often contain sensitive information. These leaky thoughts are difficult to control and frequently violate explicit privacy directives. Because RTs can be exposed through prompt injection attacks, this becomes a direct privacy risk to the user. We approach this as a controllability problem: since privacy directives are themselves instructions, improving instruction-following (IF) within the RT provides a direct path to reducing privacy leaks. To this end, we introduce an SFT dataset that teaches models to follow general instructions throughout their reasoning process, and propose Staged Decoding, a simple decoding strategy that decouples RT and answer generation using separate LoRA adapters to maximize IF of each component. We evaluate our approach on six models from two families (1.7B-14B parameters), across two IF benchmarks and two privacy benchmarks. Our method yields substantial improvements, with gains of up to 20.9 points in IF and 51.9 percentage points on privacy benchmarks, though these can come at the cost of task utility due to the trade-off between reasoning performance and IF. Our results show that improving IF in LRMs can significantly enhance privacy, suggesting a promising direction for future privacy-aware LRMs. Our code is available at https://github.com/UKPLab/arxiv2026-controllable-reasoning-models.

arXiv

R3S: Refining and Recovering Reinforcement Signals for Multilingual Understanding and Reasoning

Junxiao Liu, Zhijun Wang, Yixiao Li, Zhejian Lai, Liqian Huang, Xin Huang, Xue Han, Junlan Feng, Shujian Huang

Large reasoning models often default to English reasoning when processing non-English questions, yet their performance drops substantially when reasoning in the question language. Even with the same reasoning language, semantically equivalent English and non-English questions still exhibit a clear performance gap. Together, these phenomena reveal two distinct bottlenecks: target-language question understanding and target-language reasoning. Existing methods typically optimize only one of these capabilities. However, simply combining them may not be sufficient to optimize both effectively, as answer correctness alone cannot distinguish failures in question understanding from those in reasoning. We propose R3S, a reinforcement learning framework that disentangles the optimization of the two capabilities. R3S refines translation rewards derived from downstream reasoning accuracy through English-solvability filtering and recovers target-language RLVR signals using self-generated English hints. Together, these designs require neither external model feedback nor external multilingual training data. Experiments across three backbone models and five languages show that R3S improves language-consistent accuracy over the target-language RLVR baseline on MMATH by an average of 10.3 percentage points, while maintaining near-perfect language consistency. Consistent gains on MMLU-ProX further demonstrate its generalization beyond math problems.

arXiv

SPRInG: Continual LLM Personalization via Selective Parametric Adaptation and Retrieval-Interpolated Generation

Seoyeon Kim, Jaehyung Kim

Personalizing Large Language Models typically relies on static retrieval or one-time adaptation, assuming user preferences remain invariant over time. However, real-world interactions are dynamic, where user interests continuously evolve, posing a challenge for models to adapt to preference drift without catastrophic forgetting. Standard continual learning approaches often struggle in this context, as they indiscriminately update on noisy interaction streams, failing to distinguish genuine preference shifts from transient contexts. To address this, we introduce SPRInG, a novel semi-parametric framework designed for effective continual personalization. During training, SPRInG employs drift-driven selective adaptation, which utilizes a likelihood-based scoring function to identify high-novelty interactions, selectively updating the user-specific adapter on drift signals while preserving hard-to-learn residuals in a replay buffer. During inference, we apply strict relevance gating and fuse parametric knowledge with retrieved history via probability interpolation. Experiments on the long-form personalized generation benchmark demonstrate that SPRInG significantly outperforms existing baselines, validating its robustness for real-world continual personalization.

arXiv

ReMIND: Orchestrating Modular Large Language Models for Controllable Serendipity A REM-Inspired System Design for Emergent Creative Ideation

Makoto Sato

Large language models (LLMs) are increasingly used not only for problem solving but also for creative ideation; however, generating ideas that are both novel and coherent remains challenging. While high-temperature sampling can promote originality, it often compromises consistency and usefulness. Here, we propose ReMIND, a four-stage framework comprising wake, which establishes a stable semantic baseline through low-temperature generation; dream, which performs high-temperature exploratory generation; judge, which evaluates candidate outputs for consistency and extracts salient novel ideas; and rewake, which consolidates selected ideas into coherent final outputs. By assigning these functions to independent LLM modules, ReMIND explicitly separates exploration from stabilization. We systematically evaluated diverse model configurations using multiple creative ideation tasks. External evaluations showed that novelty enhancement could emerge through two separable stages: first from the wake to the dream phase through high-temperature exploration, and subsequently from the dream to the rewake phase through judge-mediated selection and consolidation. Notably, different LLM families exhibited distinct functional tendencies. These findings suggest that serendipitous ideation in LLMs is not solely a property of individual models but emerges from interactions among models assigned to specialized cognitive roles. ReMIND provides a general framework for investigating computational creativity and demonstrates how modular LLM orchestration can bridge exploratory generation and coherent idea formation.

arXiv

HFS: Holistic Query-Aware Frame Selection for Efficient Video Understanding

Yiqing Yang, Yun Li, Daiqing Qi, Lehan Yang, Tianlong Wang, Wenhao Zhang, Sheng Li, Kin-man Lam

Key frame selection is essentially a set-level optimization problem: the quality of the selected subset depends on the interactions among frames, rather than the score of any single frame. Existing methods generally exhibit three major limitations. Point-wise methods score each frame independently and ignore inter-frame dependencies. Although the training-free set-level methods explicitly model the inter-frame relationships, their selection criteria are fixed and cannot be adapted through downstream task feedback. Learnable methods can leverage data-driven training; however, they lack an explicit, differentiable set-quality objective and rely on offline-generated supervision signals. To address these limitations, we propose an end-to-end trainable and task-adaptive framework for frame selection. A Chain-of-Thought prompt conditions a Small Language Model (SLM) to extract task-specific latent query vectors, which are combined with multimodal features to enable dynamic, query-aware frame scoring. We further formulate a continuous set-level objective function that jointly accounts for relevance, coverage, and redundancy, enabling differentiable set-level optimization via Gumbel-TopK for selecting optimal frame combinations. Finally, we employ a student-teacher mutual learning strategy, in which the student selector (SLM) and teacher reasoner (MLLM) are trained to align their frame-importance distributions via KL divergence. Combined with cross-entropy loss, this design enables fully end-to-end optimization, eliminating reliance on static pseudo-labels. Experiments across multiple benchmarks, including Video-MME, LongVideoBench, MLVU, and NExT-QA, demonstrate that our method significantly outperforms existing frame-selection approaches.

arXiv

Multilingual Agent-Based World Modeling for Social Science

Xuan Zhang, Wenxuan Zhang, Anxu Wang, See-Kiong Ng, Yang Deng

Multi-agent role-playing has recently shown promise for studying social behavior with language agents, but existing simulations are mostly monolingual without cross-lingual interaction, an essential property of real societies. We introduce MAWM, the first Multilingual Agent-based World Modeling framework that supports multi-turn multilingual interactions among generative agents with diverse sociolinguistic profiles. MAWM enables two modes of analysis: (i) global public opinion modeling, which tracks how attitudes toward open-domain survey questions evolve across languages and cultures, and (ii) media influence and information diffusion, via autonomous news agents that dynamically generate content and shape user behavior. To ground the simulation in realistic population distributions, we construct the MAPS benchmark, which combines survey questions and demographic personas drawn from global population distributions. Experiments on simulation alignment, along with social science case studies on cultural assimilation and normative diffusion, show that native-language simulation better reflects real survey data than English-only simulation, and that the agent society in MAWM reproduces established sociocultural phenomena and highlights the value of multilingual simulation as an alternative interpretable tool for computational social science.

arXiv

MoE-Prism: Disentangling Monolithic Experts for Elastic MoE Services via Model-System Co-Designs

Xinfeng Xia, Xiaofeng Hou, Jiacheng Liu, Wenfeng Wang, Mingxuan Zhang, Peng Tang, Chao Li, Minyi Guo

Mixture-of-Experts (MoE) scales model capacity through sparse activation, and is becoming an important architecture for large language models (LLMs). However, existing MoE serving systems typically execute all requests under a fixed routing configuration, limiting their ability to exploit heterogeneous computation requirements across requests. Routing top-$k$, which determines the number of routed experts activated per token, directly controls routed-expert computation and provides a natural mechanism for request-level compute elasticity. Realizing this capability, however, requires finer-grained routing units and efficient runtime execution for heterogeneous routing budgets. We present \textsc{MoE-Prism}, a model and system support framework for request-level compute elasticity in MoE serving. \textsc{MoE-Prism}decomposes monolithic experts into fine-grained sub-experts to expose denser routing operating points and provides a $k$-aware serving runtime that effectively serves heterogeneous routing budgets under both throughput-oriented and latency-sensitive workloads. We implement \textsc{MoE-Prism} on top of vLLM and evaluate it on three representative MoE models. \textsc{MoE-Prism} expands the number of available routing operating points by $4\times$, improves offline inference throughput by up to 33.9\%, and reduces online serving TTFT under heterogeneous workloads. These results demonstrate practical elastic MoE serving with request-level routing targets.

arXiv

NeuroAda: Activating Each Neuron's Potential for Parameter-Efficient Fine-Tuning

Zhi Zhang, Yixian Shen, Congfeng Cao, Ekaterina Shutova

Existing parameter-efficient fine-tuning (PEFT) methods primarily fall into two categories: addition-based and selective in-situ adaptation. The former, such as LoRA, introduce additional modules to adapt the model to downstream tasks, offering strong memory efficiency. However, their representational capacity is often limited, making them less suitable for fine-grained adaptation. In contrast, the latter directly fine-tunes a carefully chosen subset of the original model parameters, allowing for more precise and effective adaptation, but at the cost of significantly increased memory consumption. To reconcile this trade-off, we propose NeuroAda, a novel PEFT method that enables fine-grained model finetuning while maintaining high memory efficiency. Our approach first identifies important parameters (i.e., connections within the network) as in selective adaptation, and then introduces bypass connections for these selected parameters. During finetuning, only the bypass connections are updated, leaving the original model parameters frozen. Empirical results on 23+ tasks spanning both natural language generation and understanding demonstrate that NeuroAda achieves state-of-the-art performance with as little as $\leq \textbf{0.02}\%$ trainable parameters, while reducing CUDA memory usage by up to 60%. We release our code here: https://github.com/FightingFighting/NeuroAda.git.

arXiv

Beyond Pixels: Exploring DOM Downsampling for LLM-Based Web Agents

Thassilo M. Schiepanski, Nicholas Piël

The advent of large language models (LLMs) has sparked an evolution of autonomous web browsing agents: given a web browsing task and serialised user interface (UI) state, an LLM is expected to suggest input actions that incrementally solve the given task. The central challenge lies in serialising UI state for LLMs. Web agents have increasingly relied on grounded graphical UI (GUI) snapshots - screenshots augmented with visual cues - favoured for their modest input token footprint. Document object model (DOM) snapshots, serialised as HTML, represent a compelling alternative that leverages previously demonstrated HTML interpretation capabilities of LLMs. Their excessive token footprint, however, has precluded reliable deployment with web agents to date. We propose D2Snap, an algorithm to downsample the DOM, premised on preserving actionability and actionability-discriminating features. We evaluate D2Snap-downsampled DOM snapshots using a snapshot-variant web agent (GPT-4o) on a dataset sampled from Online-Mind2Web. Whilst 42% of raw DOM snapshots exceed the model context window (128 x 10^3 tokens), all D2Snap-downsampled DOM snapshots of our reference configuration fit, at a mean context utilisation of 16.5%. Against the 67% success rate of a grounded GUI snapshot baseline, our configuration attains 73% (+5.8%pt; 95% CI -13.6 to +26.0%pt; McNemar, p = 0.47), excluding a deficit (one-sided 95%) beyond 11%pt. Image input moreover appears to add little to snapshot utility; grounding text alone attains 62% (-5.8%pt; McNemar, p = 0.37).

arXiv

Testing Hypotheses from the Social Approval Theory of Online Hate: An Analysis of 110 Million Messages from Parler

David M. Markowitz, Samuel Hardman Taylor

We examined how social approval motivates online hate via the social approval theory, which argues social approval signals on hate messages predict more hate and toxicity. Using 110 million messages from Parler (2018-2021), we observed that upvotes on hate speech posts (e.g., messages broadcast on users' profiles to followers' feeds) predicted a lower probability of hate in the next immediate post but more in the following week's post. In other analyses, upvotes on comments (e.g., messages embedded within conversational threads) negatively predicted hate speech in the next comment but positively predicted toxicity during the next week and month. Between-person effects revealed a similar pattern of negative immediate short-term effects but positive longer-term effects for hate speech. For comments, social disapproval (downvotes) moderated these relationships, making them less positive at weekly through quarterly time-intervals and more strongly negative at six-months. Social approval predicts online hate in time- and message-dependent ways.

arXiv

REMAC: Self-Reflective and Self-Evolving Multi-Agent Collaboration for Long-Horizon Robot Manipulation

Puzhen Yuan, Angyuan Ma, Yunchao Yao, Huaxiu Yao, Masayoshi Tomizuka, Mingyu Ding

Vision-language models (VLMs) have demonstrated remarkable capabilities in robotic planning, particularly for long-horizon tasks that require a holistic understanding of the environment for task decomposition. Existing methods typically rely on prior environmental knowledge or carefully designed task-specific prompts, making them struggle with dynamic scene changes or unexpected task conditions, e.g., a robot attempting to put a carrot in the microwave but finds the door was closed. Such challenges underscore two critical issues: adaptability and efficiency. To address them, in this work, we propose an adaptive multi-agent planning framework, termed REMAC, that enables efficient, scene-agnostic multi-robot long-horizon task planning and execution through continuous reflection and self-evolution. REMAC incorporates two key modules: a self-reflection module performing pre-condition and post-condition checks in the loop to evaluate progress and refine plans, and a self-evolvement module dynamically adapting plans based on scene-specific reasoning. It offers several appealing benefits: 1) Robots can initially explore and reason about the environment without complex prompt design. 2) Robots can keep reflecting on potential planning errors and adapting the plan based on task-specific insights. 3) After iterations, a robot can call another one to coordinate tasks in parallel, maximizing the task execution efficiency. To validate REMAC's effectiveness, we build a multi-agent environment for long-horizon robot manipulation and navigation based on RoboCasa, featuring 4 task categories with 27 task styles and 50+ different objects. Based on it, we further benchmark state-of-the-art reasoning models, including DeepSeek-R1, o3-mini, QwQ, and Grok3, demonstrating REMAC's superiority by boosting average success rates by 40% and execution efficiency by 52.7% over the single robot baseline.

arXiv

Transformer Explainer: Learning LLM Transformers with Interactive Visual Explanation and Experimentation

Aeree Cho, Grace C. Kim, Alexander Karpekov, Seongmin Lee, Alec Helbling, Benjamin Hoover, Zijie J. Wang, Minsuk Kahng, Duen Horng Chau

The Transformer architecture underpins modern large language models powering state-of-the-art text generation and AI applications. However, its complexity makes it difficult for non-experts to learn. Existing resources often lack interactivity, rely on static descriptions of simplified architectures, or fail to reflect models' behavior with real data. To address this gap, we introduce Transformer Explainer, an interactive visualization tool for non-experts to learn Transformers. The tool integrates an overview illustrating the Transformer's data flow with on-demand explanations that gradually reveal mathematical details. Smooth transitions across abstraction levels highlight the interplay between high-level structures and low-level operations. Running a live GPT-2 instance directly in the browser, Transformer Explainer empowers learners to experiment with custom input and hyperparameters without setup, observing next-token predictions in real time. A 90-participant user study showed that our tool offered significant advantages in improving user understanding and engagement. Transformer Explainer has attracted over 490,000 users.

arXiv

Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theory

Gordon Dai, Weijia Zhang, Jinhan Li, Siqi Yang, Chidera Onochie lbe, Srihas Rao, Arthur Caetano, Misha Sra

The emergence of Large Language Models (LLMs) and advancements in Artificial Intelligence (AI) offer an opportunity for computational social science research at scale. Building upon prior explorations of LLM agent design, our work introduces a simulated agent society where complex social relationships dynamically form and evolve over time. Agents are imbued with psychological drives and placed in a sandbox survival environment. We conduct an evaluation of the agent society through the lens of Thomas Hobbes's seminal Social Contract Theory (SCT). We analyze whether, as the theory postulates, agents seek to escape a brutish "state of nature" by surrendering rights to an absolute sovereign in exchange for order and security. Our experiments unveil an alignment: Initially, agents engage in unrestrained conflict, mirroring Hobbes's depiction of the state of nature. However, as the simulation progresses, social contracts emerge, leading to the authorization of an absolute sovereign and the establishment of a peaceful commonwealth founded on mutual cooperation. This congruence between our LLM agent society's evolutionary trajectory and Hobbes's theoretical account indicates LLMs' capability to model intricate social dynamics and potentially replicate forces that shape human societies. By enabling such insights into group behavior and emergent societal phenomena, LLM-driven multi-agent simulations, while unable to simulate all the nuances of human behavior, may hold potential for advancing our understanding of social structures, group dynamics, and complex human systems.

继续浏览

更多 AI 顶会论文

30+ 个顶会，按会议、年份和主题浏览。

浏览全部会议

进入任一会议和年份，查看完整论文列表。

全部会议 →

搜索论文

按标题、作者或关键词，在 21 万+ 篇论文里搜索。

搜索论文 →