Search arXiv⌕ Search

arXiv subjects

Kangwook Lee

Publications and source records attributed to Kangwook Lee.

At least 19 recordsLinked to original sources

Where Should Learning Live? Regret Analysis for Text, Parameter, and Joint Adaptation

Language-model systems can select prompts and parameter adapters repeatedly during deployment, using feedback to guide later choices. Earlier choices may change the context or environment inherited by later configurations. We study selection among preconstructed candidates and compare cumulative loss with the best fixed prompt--parameter pair used from the beginning. This excess loss separates into three terms: selection regret within the available family, the gap from restricting that family, and the benefit or harm of the actual deployment history. Selection is evaluated using the history each candidate would have produced if used throughout, which separates candidate quality from the effects of switching. When loss functions are fixed independently of selector randomness, past choices affect loss for only a bounded number of rounds, and every candidate's own-history loss is revealed, limiting switches yields sublinear expected regret within the selected family. We also quantify the costs and additional assumptions of independent probing and deployment-only feedback. Controlled experiments show that fewer switches can either lower or raise deployed loss, depending on whether inherited histories are harmful or helpful. With Qwen3.5-9B on Spider, text-only selection has lower within-family regret than joint selection, yet produces more failures because its candidate family excludes stronger configurations.

stat.ML↗

Exploration and Exploitation Errors Are Measurable for Language Model Agents

Language Model (LM) agents are increasingly used in complex decision-making tasks, from AI coding to physical AI, where they must both explore a search space and exploit acquired knowledge effectively. Although exploration and exploitation play different roles in decision-making, it remains challenging to systematically distinguish exploration and exploitation without access to the agent's internal policy, and to determine when either constitutes an error. To address this, we design partially observable 2D grid maps paired with an unknown symbolic task directed acyclic graph (DAG), abstracting practical agentic AI scenarios. We then propose a policy-agnostic metric that detects unproductive traversals, while permitting necessary backtracking. We attribute each error to exploration or exploitation based on whether the current state admits productive exploration, exploitation, or both. Using generated maps and task DAGs with controllable difficulty, we evaluate 35 frontier LM agents and find that even state-of-the-art models struggle to reach the goal within the step budget. $\log$ exploration and exploitation errors exhibit strong relationships with task success ($R^2 = 0.885$ and $0.875$, respectively), providing empirical evidence that the metric captures behavior relevant to task success. Beyond success rate, the metric reveals distinct exploration and exploitation behaviors among models with similar success rates. We further find that a compact memory harness achieves higher task success than a reasoning baseline that retains its own reasoning traces. Finally, we extend our metric to an iconic video game, Minecraft Clone, beyond our synthetic environment. We release our code at https://github.com/jjj-madison/measurable-explore-exploit.

cs.AI↗

PUBG Ally: A Conversational Embodied Agent as an AI Teammate

We introduce PUBG Ally, an embodied agent for PUBG: BATTLEGROUNDS that can reason, act autonomously, and play alongside players as a voice-enabled teammate. Building such a teammate requires combining two difficult capabilities: it must perceive and respond to a constantly changing game world under strict latency constraints while interacting naturally with players, keeping its speech synchronized with its actions. Ally therefore combines agentic tool use with real-time game control. A language-model agent uses a controlled interface to inspect game information, interpret player speech, maintain context, decide what to say, and issue high-level action choices that steer a faster control layer for movement, combat, and recovery. Because the player's and Ally's speech and actions continually shape each other and the course of the match, training requires data from actual gameplay. We therefore collect data across nearly 39k sessions in which real players play alongside Ally, recording gameplay, player speech, agent decisions, tool use, actions, and player feedback, and use these records for iterative training. To evaluate teammate quality, we use player feedback and preference comparisons to identify gaps between offline evaluations and player preferences, and iteratively refine the evaluation criteria. Deploying Ally in live service further requires low-latency on-device execution and safeguards for player-facing communication, which we address through model compression, context compaction, targeted safety training, runtime guardrails, and memory redaction. During the live service, we surveyed players in 141 countries. Among respondents whose play with Ally was confirmed in game records, positive responses exceeded negative responses by 25.1 percentage points when asked whether they would recommend Ally, with players describing Ally not only as a tool but also as a teammate or companion.

cs.AI↗

AgentVidBench: A Multi-Hop Video Question Answering Benchmark for Evaluating MLLM Agents

Comprehensive video understanding is crucial for advancing artificial intelligence toward the intricate dynamics of the physical world. While recent advances in Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in video understanding, existing benchmarks remain confined to simple scene-level queries or global summaries that require only single-step inference. Real-world video understanding involves more challenging tasks that require multi-hop multimodal reasoning, and there is a critical absence of video benchmarks equipped to rigorously evaluate these agentic capabilities. To bridge this gap, we introduce AgentVidBench, a multi-hop video question answering benchmark focused on evaluating the spatial, temporal, and causal reasoning capabilities of MLLM agents. Beyond standard question-answer pairs, AgentVidBench provides step-by-step solution traces to support trajectory evaluation that assesses whether agents explicitly acquire the evidence needed to justify their answers. Experiments with 12 proprietary and open-source MLLMs show that single-turn performance remains limited on AgentVidBench, while integrating these models into state-of-the-art agentic workflows generally improves performance with respect to both accuracy and trajectory scores. We further present a simple yet effective agentic strategy that serves as a competitive baseline on AgentVidBench, establishing our benchmark as a holistic testbed for future research on agentic video understanding. Code and datasets are available at https://github.com/krafton-ai/agentvidbench and https://huggingface.co/datasets/agentvidbench/agentvidbench.

cs.CV↗

WHALE: A Simple Recipe for Joint Harness-Weight Optimization

Agent performance depends jointly on the model parameters and the executable harness code that manages context and control flow. Optimizing either component in isolation can leave the system bottlenecked by its frozen counterpart: weight updates can change which harness is effective, while harness updates can change which model capabilities are exposed. Existing joint-adaptation methods optimize weights and textual prompts but leave the broader harness fixed. We propose Weight-Harness Alternating LEarning (WHALE), a simple recipe that alternates two phases: updating the model under the current harness, then searching for a better harness under the updated model. We instantiate these two phases with online rejection-sampling fine-tuning and Meta-Harness, respectively. When to switch is a key design choice: to separate real improvements from noise without over-optimizing against a changing counterpart, WHALE uses either fixed phase durations or an adaptive patience rule over training signals. Using Qwen3.5-2B/4B agents across three domains (search question answering, mathematical reasoning, and chess puzzles), WHALE outperforms weight-only, harness-only, and Fast-Slow Training by 4.15-24.38 percentage points in best mean@8 accuracy. Either component can be the bottleneck: harness search matches peak weight-only accuracy with far fewer rollouts in SearchQA, but improves math accuracy only after a weight update. Small interleaved updates also outperform stagewise weight-then-harness optimization in accuracy and rollout cost. The code is available at https://github.com/krafton-ai/WHALE.

cs.LG↗

Ludi${}_{\scriptscriptstyle 0.1}$: An Agentic System for Socially Intelligent Robots

Robot foundation models have substantially advanced perception and control, but natural human-robot collaboration requires more than executing isolated commands. A robot must recognize ambiguity, maintain context across turns, communicate its intentions, and revise ongoing behavior as the user's intent changes. We present $\scriptstyle\mathsf{Ludi}_{\scriptscriptstyle 0.1}$, an agentic system for socially intelligent robots that integrates interactive speech, multimodal reasoning, memory, navigation, and learned manipulation. Its decision-making core is a fine-tuned vision-language model trained on multi-turn interaction traces spanning ambiguous requests, clarifications, corrections, interruptions, mixed social and task dialogue, and multi-step tasks. A purpose-built harness manages the model-tool interaction loop, while specialized navigation and manipulation policies execute physical skills. Ludi${}_{\scriptscriptstyle 0.1}$ demonstrates a practical path toward fluid human-robot collaboration today while producing the multimodal interaction traces needed to develop a more deeply integrated foundation model for robots and people.

cs.RO↗

Multi-Bin Batching for Increasing LLM Inference Throughput

As large language models (LLMs) grow in popularity for their diverse capabilities, improving the efficiency of their inference systems has become increasingly critical. Batching LLM requests is a critical step in scheduling the inference jobs on servers (e.g. GPUs), enabling the system to maximize throughput by allowing multiple requests to be processed in parallel. However, requests often have varying generation lengths, causing resource underutilization, as hardware must wait for the longest-running request in the batch to complete before moving to the next batch. We formalize this problem from a queueing-theoretic perspective, and aim to design a control policy which is throughput-optimal under a static-batching framework. We propose Multi-Bin Batching, a simple yet effective method that can provably improve LLM inference throughput under this framework by grouping requests with similar (predicted) execution times into predetermined bins. Through a combination of theoretical analysis and experiments, including real-world LLM inference scenarios with static and continuous-batching baselines, we demonstrate that multi-bin batching substantially improves throughput over static batching and quantify the remaining gap to native continuous batching under both oracle and estimated length information.

cs.CL↗

Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers

Language models typically reason via explicit chain-of-thought (CoT), generating intermediate steps token-by-token. Latent CoT offers an alternative: it performs multi-step reasoning in the model's hidden states, replacing decoded tokens with continuous representations for greater efficiency. However, existing latent CoT methods underperform explicit CoT beyond 1B parameters, and the gap widens with scale. Looped, or recurrent-depth, Transformers, which reuse their weights to increase computation depth without adding parameters, are a natural fit for latent reasoning. We therefore ask whether looped Transformers can bridge this gap. We answer affirmatively with a simple recipe: a looped padded Transformer that processes K latent blocks in parallel for R iterations, with a cross-entropy loss on each latent position's gold CoT-step token, similar to explicit CoT supervision. We instantiate it as LOTUS (Looped Transformers with parallel supervision on latents). LOTUS is, to our knowledge, the first latent-CoT method to bridge the gap to explicit CoT at the 3B scale, while cutting thought-phase latency by 2.5x-6.9x from compact math expressions to natural language. Projecting LOTUS's post-loop latents through the base LM head recovers the gold reasoning steps and even surfaces alternative valid intermediate steps, evidence that its latent space is interpretable and CoT-aligned. Ablations confirm that both the looped backbone and the parallel supervision on gold CoT tokens are essential. Code is available at https://github.com/yingfan-bot/lotus.

cs.LG↗

ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs

While most autoregressive LLMs are constrained to one-by-one decoding, diffusion LLMs (dLLMs) have attracted growing interest for their potential to dramatically accelerate inference through parallel decoding. Despite this promise, the conditional independence assumption in dLLMs causes parallel decoding to ignore token dependencies, inevitably degrading generation quality when these dependencies are strong. However, existing works largely overlook these inherent challenges, and evaluations on standard benchmarks (e.g., math and coding) are not sufficient to capture the quality degradation caused by parallel decoding. To address this gap, we first provide an information-theoretic analysis of parallel decoding. We then conduct case studies on analytically tractable synthetic list operations from both data distribution and decoding strategy perspectives, offering quantitative insights that highlight the fundamental limitations of parallel decoding. Building on these insights, we propose ParallelBench, the first benchmark specifically designed for dLLMs, featuring realistic tasks that are trivial for humans and autoregressive LLMs yet exceptionally challenging for dLLMs under parallel decoding. Using ParallelBench, we systematically analyze both dLLMs and autoregressive LLMs, revealing that: (i) dLLMs under parallel decoding can suffer dramatic quality degradation in real-world scenarios, and (ii) current parallel decoding strategies struggle to adapt their degree of parallelism based on task difficulty, thus failing to achieve meaningful speedup without compromising quality. Our findings underscore the pressing need for innovative decoding methods that can overcome the current speed-quality trade-off. We release our benchmark to help accelerate the development of truly efficient dLLMs.

cs.LG↗

AsyncOPD: How Stale Can On-Policy Distillation Be?

On-policy distillation (OPD) trains a student on its own rollouts guided by teacher feedback and is becoming increasingly important for large language model (LLM) post-training. Like reinforcement learning (RL), however, OPD faces an on-policy systems bottleneck, as rollouts can dominate training time for reasoning workloads. Asynchronous training pipelines can alleviate this bottleneck by decoupling rollout generation from learner updates, but doing so introduces stale-policy data. While prior work has studied stale data in asynchronous RL, its effects in OPD remain underexplored. We present the first systematic study of staleness in asynchronous OPD, focusing on a practical setting where teacher feedback is implemented through local KL losses and full-vocabulary teacher logits are too expensive to store or transfer, necessitating finite teacher-score caches. We first show that KL direction changes the stale-data problem: teacher-weighted forward KL is more robust to stale rollouts, whereas student-weighted reverse KL is vulnerable. Second, for this vulnerable reverse-KL case, we study whether methods designed to stabilize asynchronous RL can mitigate OPD staleness. In our experiments, they do not improve over a simpler OPD-specific surrogate: recomputing the reverse-KL signal under the current student at learner time. Third, we analyze how finite teacher-score caches create a bias-variance tradeoff for sparse and sampled reverse-KL OPD estimators. This motivates multi-sample Monte Carlo (MC), which preserves MC correctability while reducing one-sample variance. Finally, we present and open-source AsyncOPD, a fully asynchronous OPD training pipeline built from these estimator choices. Experiments show that AsyncOPD improves training throughput by $1.6\times$ to $3.8\times$ over strict synchronous training while reaching comparable accuracy.

cs.LG↗

Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech

Recent advances in text-to-speech (TTS) models show impressive speech naturalness and quality, yet the role of large-scale open data in driving this progress remains underexplored. In this work, we introduce Raon-OpenTTS, an open TTS model that performs competitively with state-of-the-art closed-data TTS models, and Raon-OpenTTS-Pool, a large-scale open dataset for reproducible TTS training. Raon-OpenTTS-Pool consists of 615K hours of 240M speech segments aggregated from publicly available English speech corpora and web-sourced recordings. With a model-based filtering pipeline applied to Raon-OpenTTS-Pool, we derive Raon-OpenTTS-Core, a curated, high-quality subset of 510K hours and 194M speech segments. Using Raon-OpenTTS-Core, we train Raon-OpenTTS, a series of diffusion transformer (DiT)-based TTS models from 0.3B to 1B parameters. On multiple benchmarks, Raon-OpenTTS-1B shows comparable performance to state-of-the-art models such as Qwen3-TTS and CosyVoice 3, which are trained on several million hours of proprietary speech data. Notably, on Seed-TTS-Eval, Raon-OpenTTS-1B achieves a word error rate (WER) of 1.78% and a speaker similarity (SIM) of 0.749, ranking second on WER and first on SIM among recent open-weight TTS baselines. On CV3-Hard-EN, Raon-OpenTTS-1B achieves a WER of 6.15% and a SIM of 0.775, ranking first on both metrics. Furthermore, to support robust evaluation, we introduce Raon-OpenTTS-Eval, a structured benchmark for assessing TTS robustness across diverse acoustic conditions including clean, noisy, in-the-wild, and expressive speech. On Raon-OpenTTS-Eval, Raon-OpenTTS-1B achieves the best average WER and SIM among all evaluated models, and the second-best human preference, as measured by comparative mean opinion score (CMOS). Our data pool, filtering pipeline, training code, and checkpoints are publicly available at https://github.com/krafton-ai/RAON-OpenTTS.

eess.AS↗

How to Correctly Report LLM-as-a-Judge Evaluations

Large language models (LLMs) are widely used as scalable evaluators of model responses in lieu of human annotators. However, imperfect sensitivity and specificity of the LLM judges induce bias in naive evaluation scores. We propose a simple plug-in framework that corrects this bias and enables statistically principled uncertainty quantification. Our framework constructs confidence intervals that account for uncertainty from both the test dataset and a human-labeled calibration dataset. Additionally, it uses an adaptive strategy to allocate calibration samples for tighter intervals. Importantly, we characterize parameter regimes defined by the true evaluation score and the LLM judge's sensitivity and specificity in which our LLM-based evaluation yields more reliable estimates than human-only evaluation. Moreover, we show that our framework remains unbiased under distribution shift between the test and calibration datasets, in contrast to existing approaches.

cs.LG↗

Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models

Transformer-based large language models exhibit in-context learning, enabling adaptation to downstream tasks via few-shot prompting with demonstrations. In practice, such models are often fine-tuned to improve zero-shot performance on downstream tasks, allowing them to solve tasks without examples and thereby reducing inference costs. However, fine-tuning can degrade in-context learning, limiting the performance of fine-tuned models on tasks not seen during fine-tuning. Using linear attention models, we provide a theoretical analysis that characterizes how fine-tuning objectives modify attention parameters and identifies conditions under which this leads to degraded few-shot performance. We show that fine-tuning all attention parameters can harm in-context learning, whereas restricting updates to the value matrix improves zero-shot performance while preserving in-context learning. We further show that incorporating an auxiliary few-shot loss enhances in-context learning primarily on the target task, at the expense of degraded in-context learning ability on tasks not seen during fine-tuning. We provide empirical evidence from synthetic and real-world datasets consistent with the qualitative predictions of our theory.

cs.CL↗

Fine-tuning a vision-language model for fracture-surface morphology recognition

Vision-language models (VLMs) have shown strong potential for scientific image understanding, but general-purpose models often lack the domain-specific visual knowledge required for reliable materials characterization. In this work, we fine-tuned an open-source VLM (Qwen3-VL-32B-Instruct) for fracture-surface image analysis using a curated dataset of 13,168 open-source, literature-mined fracture-surface images. Morphology annotations were generated by GPT-5.2-Reasoning (high) from both the images and relevant excerpts of their source papers, and the dataset was further enriched with targeted manual collection and rotation-based augmentation. The resulting specialist model outperforms flagship proprietary multimodal models on a benchmark of 100 manually annotated images. It achieves a precision of 0.92, compared to 0.35 for the base Qwen3-VL-32B-Instruct, 0.58 for GPT-5.5-Reasoning (high), and 0.78 for Gemini 3.1 Pro-Reasoning (high). Dataset ablations show that manual collection of rare-feature images and augmentation via image rotation are both beneficial to improve recognition of less common fracture morphology features. We further discuss integrated use of the fine-tuned model with proprietary models to combine fracture-specific visual accuracy with broader multimodal reasoning for autonomous fractography. Although focused on fracture-surface images, this work demonstrates how VLMs can be adapted through targeted collection and fine-tuning on novel feature images to recognize those features and support downstream decision-making in autonomous microscopy workflows.

cond-mat.mtrl-sci↗

RLDX-1 Technical Report

While Vision-Language-Action models (VLAs) have shown remarkable progress toward human-like generalist robotic policies through the versatile intelligence (i.e. broad scene understanding and language-conditioned generalization) inherited from pre-trained Vision-Language Models, they still struggle with complex real-world tasks requiring broader functional capabilities (e.g. motion awareness, long-term memory, and physical sensing). To address this, we introduce RLDX-1, a general-purpose robotic policy for dexterous manipulation built on the Multi-Stream Action Transformer (MSAT), an architecture that unifies these capabilities by integrating heterogeneous modalities through modality-specific streams with cross-modal joint self-attention. RLDX-1 further combines this architecture with system-level design choices, including data synthesis for rare manipulation scenarios, learning procedures specialized for human-like manipulation, and inference optimizations for real-time deployment. Through empirical evaluation, we show that RLDX-1 consistently outperforms recent frontier VLAs (e.g. $π_{0.5}$ and GR00T N1.6) across both simulation benchmarks and real-world tasks that require broad functional capabilities beyond general versatility. In particular, RLDX-1 shows superiority in ALLEX humanoid tasks by achieving success rates of 86.8% while $π_{0.5}$ and GR00T N1.6 achieve around 40%, highlighting the ability of RLDX-1 to control a high-DoF humanoid robot under diverse functional demands. Together, these results position RLDX-1 as a promising step toward reliable VLAs for complex, contact-rich, and dynamic real-world dexterous manipulation.

cs.RO↗

Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games

Large Language Model (LLM) agents are reshaping the game industry, by enabling more intelligent and human-preferable characters. Yet, current game benchmarks fall short of practical needs: they lack evaluations of diverse LLM capabilities across various game genres, studies of agentic modules crucial for complex gameplay, and fine-tuning datasets to adapt pre-trained LLMs into gaming agents. To fill these gaps, we present Orak, a benchmark for training and evaluating LLM agents across 12 popular video games spanning all major genres. Using a plug-and-play interface built on Model Context Protocol (MCP), Orak supports systematic and reproducible studies of agentic modules in varied game scenarios. We further release a fine-tuning dataset of expert LLM gameplay trajectories covering multiple genres, turning general LLMs into effective game agents. Orak offers a united evaluation framework, including game leaderboards, LLM battle arenas, and \fix{ablation studies} of input modality, agentic strategies, and fine-tuning effects, establishing a foundation towards versatile gaming agents. Code and datasets are available at https://github.com/krafton-ai/Orak and https://huggingface.co/datasets/KRAFTON/Orak.

cs.AI↗

Raon-Speech Technical Report

We present Raon-Speech, a top-performing 9B-parameter speech language model (SpeechLM) for English and Korean speech understanding, answering, and generation, and Raon-SpeechChat, a high-performing full-duplex extension for natural real-time conversation. Raon-Speech successfully transforms a pre-trained LLM into a SpeechLM that both understands and generates speech while preserving strong text capabilities. It trains on 1.38M hours of highly curated English and Korean speech and text datasets with the following training stages: (1) speech modules alignment, (2) end-to-end SpeechLM pre-training with knowledge distillation, and (3) multi-task preference optimization-based post-training. Across 42 English and Korean speech and text benchmarks, Raon-Speech establishes the strongest overall profile on speech-centric tasks in our comparison against eight similarly sized recent audio foundation models, including Qwen2.5-Omni and Fun-Audio-Chat, while preserving strong text question answering performance. Building upon it, Raon-SpeechChat enables natural full-duplex conversation by continual training on 119K hours of time-aligned real and synthetic dialogue data. It proceeds through three complementary training stages: (1) causal encoder adaptation, (2) full-duplex pre-training, (3) full-duplex fine-tuning for voice and role-control. On multiple full-duplex benchmarks, Raon-SpeechChat shows its clearest strengths on the turn-taking and interruption-sensitive behaviors covered by FDB v1.0, and remains competitive across the broader full-duplex evaluation suite. We open-source all model checkpoints, the training and inference pipeline, and an interactive demo.

cs.CL↗

Meta-Harness: End-to-End Optimization of Model Harnesses

The performance of large language model (LLM) systems depends not only on model weights, but also on their harness: the code that determines what information to store, retrieve, and present to the model. Yet harnesses are still designed largely by hand, and existing text optimizers are poorly matched to this setting because they compress feedback too aggressively. We introduce Meta-Harness, an outer-loop system that searches over harness code for LLM applications. It uses an agentic proposer that accesses the source code, scores, and execution traces of all prior candidates through a filesystem. On online text classification, Meta-Harness improves over a state-of-the-art context management system by 7.7 points while using 4x fewer context tokens. On retrieval-augmented math reasoning, a single discovered harness improves accuracy on 200 IMO-level problems by 4.7 points on average across five held-out models. On agentic coding, discovered harnesses surpass the best hand-engineered baselines on TerminalBench-2. Together, these results show that richer access to prior experience can enable automated harness engineering.

cs.AI↗