Agents' Last Exam

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long-horizon, economically valuable, real-world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 subfields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is 2.6%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP-relevant impact.

When Does Model Collapse Occur in Structured Interactive Learning?

The proliferation of generative artificial intelligence has given rise to an interactive learning environment, where model parameters are continuously updated using not only data generated by natural processes, but also synthetic outputs produced by other models. This paradigm introduces two major challenges: (1) training data are no longer drawn exclusively from the target population, undermining a core assumption of classical statistical learning, and (2) model training processes become inherently correlated, as models interact with one another through repeated exposure to each other's synthetic outputs in a potentially complex manner. Establishing reliable statistical inference in such structured interactive learning environments therefore remains an important open problem. In particular, there is growing concern about model collapse, a phenomenon in which the performance of generative models progressively degrades as they are trained on synthetic data produced by earlier model generations. Prior work on model collapse primarily focuses on a single model trained on its own output, failing to capture model performance in multi-model interactive settings. In this work, we fill this gap by investigating the performance of generative models in an interactive learning environment with general interaction patterns. In particular, we formalize model interactions using directed graphs and show that the occurrence of model collapse depends critically on the topology of the interaction graph. We further derive an explicit necessary and sufficient condition characterizing when model collapse occurs, and establish finite-sample results for linear regression and asymptotic guarantees for general M-estimators. We support our theoretical findings through extensive numerical experiments.

PanDA: Unsupervised Domain Adaptation for Multimodal 3D Panoptic Segmentation in Autonomous Driving

This paper presents the first study on Unsupervised Domain Adaptation (UDA) for multimodal 3D panoptic segmentation (mm-3DPS), aiming to improve generalization under domain shifts commonly encountered in real-world autonomous driving. A straightforward solution is to employ a pseudo-labeling strategy, which is widely used in UDA to generate supervision for unlabeled target data, combined with an mm-3DPS backbone. However, existing supervised mm-3DPS methods rely heavily on strong cross-modal complementarity between LiDAR and RGB inputs, making them fragile under domain shifts where one modality degrades (e.g., poor lighting or adverse weather). Moreover, conventional pseudo-labeling typically retains only high-confidence regions, leading to fragmented masks and incomplete object supervision, which are issues particularly detrimental to panoptic segmentation. To address these challenges, we propose PanDA, the first UDA framework specifically designed for multimodal 3D panoptic segmentation. To improve robustness against single-sensor degradation, we introduce an asymmetric multimodal augmentation that selectively drops regions to simulate domain shifts and improve robust representation learning. To enhance pseudo-label completeness and reliability, we further develop a dual-expert pseudo-label refinement module that extracts domain-invariant priors from both 2D and 3D modalities. Extensive experiments across diverse domain shifts, spanning time, weather, location, and sensor variations, significantly surpass state-of-the-art UDA baselines for 3D semantic segmentation.

Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning

Large Language Models (LLMs) have shown remarkable performance in completing various tasks. However, solving complex problems often requires the coordination of multiple agents, raising a fundamental question: how to effectively select and interconnect these agents. In this paper, we propose \textbf{Agent Q-Mix}, a reinforcement learning framework that reformulates topology selection as a cooperative Multi-Agent Reinforcement Learning (MARL) problem. Our method learns decentralized communication decisions using QMIX value factorization, where each agent selects from a set of communication actions that jointly induce a round-wise communication graph. At its core, Agent Q-Mix combines a topology-aware GNN encoder, GRU memory, and per-agent Q-heads under a Centralized Training with Decentralized Execution (CTDE) paradigm. The framework optimizes a reward function that balances task accuracy with token cost. 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. Notably, on the challenging Humanity's Last Exam (HLE) using Gemini-3.1-Flash-Lite as a backbone, Agent Q-Mix achieves 20.8\% accuracy, outperforming Microsoft Agent Framework (19.2\%) and LangGraph (19.2\%), followed by AutoGen and Lobster by OpenClaw. These results underscore the effectiveness of learned, decentralized topology optimization in pushing the boundaries of multi-agent reasoning.

Composer 2 Technical Report

Composer 2 is a specialized model designed for agentic software engineering. The model demonstrates strong long-term planning and coding intelligence while maintaining the ability to efficiently solve problems for interactive use. The model is trained in two phases: first, continued pretraining to improve the model's knowledge and latent coding ability, followed by large-scale reinforcement learning to improve end-to-end coding performance through stronger reasoning, accurate multi-step execution, and coherence on long-horizon realistic coding problems. We develop infrastructure to support training in the same Cursor harness that is used by the deployed model, with equivalent tools and structure, and use environments that match real problems closely. To measure the ability of the model on increasingly difficult tasks, we introduce a benchmark derived from real software engineering problems in large codebases including our own. Composer 2 is a frontier-level coding model and demonstrates a process for training strong domain-specialized models. On our CursorBench evaluations the model achieves a major improvement in accuracy compared to previous Composer models (61.3). On public benchmarks the model scores 61.7 on Terminal-Bench and 73.7 on SWE-bench Multilingual in our harness, comparable to state-of-the-art systems.

CCF: Complementary Collaborative Fusion for Domain Generalized Multi-Modal 3D Object Detection

Multi-modal fusion has emerged as a promising paradigm for accurate 3D object detection. However, performance degrades substantially when deployed in target domains different from training. In this work, focusing on dual-branch proposal-level detectors, we identify two factors that limit robust cross-domain generalization: 1) in challenging domains such as rain or nighttime, one modality may undergo severe degradation; 2) the LiDAR branch often dominates the detection process, leading to systematic underutilization of visual cues and vulnerability when point clouds are compromised. To address these challenges, we propose three components. First, Query-Decoupled Loss provides independent supervision for 2D-only, 3D-only, and fused queries, rebalancing gradient flow across modalities. Second, LiDAR-Guided Depth Prior augments 2D queries with instance-aware geometric priors through probabilistic fusion of image-predicted and LiDAR-derived depth distributions, improving their spatial initialization. Third, Complementary Cross-Modal Masking applies complementary spatial masks to the image and point cloud, encouraging queries from both modalities to compete within the fused decoder and thereby promoting adaptive fusion. Extensive experiments demonstrate substantial gains over state-of-the-art baselines while preserving source-domain performance. Code and models are publicly available at https://github.com/IMPL-Lab/CCF.

Reduced-Overhead Channel Estimation and Iterative Detection of FTN Signaling Based on Pilot Superimposition and Spectral Interference Alignment

This paper proposes low-overhead and low-complexity channel estimation (CE) of frequency-domain equalization aided faster-than-Nyquist (FTN) signaling. In the proposed CE scheme, the concept of pilot superimposition is employed, where the FTN block is designed to superimpose pilot symbols with information symbols, and thus, no dedicated time and frequency resources nor guard bands are required, resulting in a 50% reduction of the overhead. Furthermore, interference induced by the pilot superimposition is eliminated by invoking a novel scheme, referred to as spectral interference alignment, where a data-dependent sequence is subtracted from transmitted information symbols. The theoretical mean-square error (MSE) of the proposed CE is derived, which verifies that the MSE is no longer affected by interference due to the pilot superimposition.

On the Robustness of Langevin Dynamics to Score Function Error

We consider the robustness of score-based generative modeling to errors in the estimate of the score function. In particular, we show that Langevin dynamics is not robust to the L^2 errors (more generally L^p errors) in the estimate of the score function. It is well-established that with small L^2 errors in the estimate of the score function, diffusion models can sample faithfully from the target distribution under fairly mild regularity assumptions in a polynomial time horizon. In contrast, our work shows that even for simple distributions in high dimensions, Langevin dynamics run for any polynomial time horizon will produce a distribution far from the target distribution in Total Variation (TV) distance, even when the L^2 error (more generally L^p) of the estimate of the score function is arbitrarily small. Considering such an error in the estimate of the score function is unavoidable in practice when learning the score function from data, our results provide further justification for diffusion models over Langevin dynamics and serve to caution against the use of Langevin dynamics with estimated scores.

How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning

Solving complex geometric problems inherently requires interleaved reasoning: a tight alternation between constructing diagrams and performing logical deductions. Although recent Multimodal Large Language Models (MLLMs) have demonstrated strong capabilities in visual generation and plotting, we identify a counter-intuitive and underexplored phenomenon. Naively applying Supervised Fine-Tuning (SFT) on interleaved plot-solution data leads to a substantial degradation in reasoning performance compared to text-only baselines. We argue that this failure stems from a fundamental limitation of SFT, which primarily induces distributional alignment: the model learns to reproduce the surface format of interleaved plotting but fails to internalize the causal dependency between the generated plot and reasoning steps. To overcome this limitation, we propose Faire (Functional alignment for interleaved reasoning), a reinforcement learning framework that enforces three casual constraints to move beyond superficial imitation toward functional alignment. Extensive experiments show that Faire induces a qualitative shift in model behavior in which the plotting is effectively internalized, yielding competitive performance on challenging geometric reasoning benchmarks.

Thinking with Drafting: Optical Decompression via Logical Reconstruction

Existing multimodal large language models have achieved high-fidelity visual perception and exploratory visual generation. However, a precision paradox persists in complex reasoning tasks: optical perception systems transcribe symbols without capturing logical topology, while pixel-based generative models produce visual artifacts lacking mathematical exactness. To bridge this gap, we propose that reasoning over visual inputs be reconceptualized as optical decompression-the process of reconstructing latent logical structures from compressed visual tokens. Guided by the axiom that Parsing is Reasoning, we introduce Thinking with Drafting (TwD), which utilizes a minimalist Domain-Specific Language (DSL) as a grounding intermediate representation. Unlike standard approaches that hallucinate answers directly, TwD forces the model to draft its mental model into executable code, rendering deterministic visual proofs for self-verification. To validate this, we present VisAlg, a visual algebra benchmark. Experiments demonstrate that TwD serve as a superior cognitive scaffold. Our work establishes a closed-loop system where visual generation acts not as a creative output but as a logical verifier, offering a generalizable path for visual reasoning.