arXiv subjects

Yuanzhe Shen

Publications and source records attributed to Yuanzhe Shen.

10 recordsLinked to original sources

arXiv2026

GUI Agents for Continual Game Generation

Generating a game is not the same as making one playable. Existing code-generation approaches often translate a prompt directly into an artifact, leaving interaction-level failures undetected. We argue that game generation requires a player and study two roles for graphical user interface (GUI) agents. First, we introduce \textbf{PlaytestArena}, an evaluation environment containing 200 browser-based game-generation tasks across eight genres, each paired with rubrics of expected in-play behaviors. An independent GUI judge loads and plays each build to adjudicate these rubrics. Second, we propose \textbf{Play2Code}, in which a game agent and a rubric-blind GUI playtester iteratively generate, play, and refine games through shared memory. The playtester provides gameplay traces and actionable feedback, while a separate GPT-5.5 judge assigns final benchmark scores. Across three frontier backbones, Play2Code achieves a 66.8\% rubric pass rate, outperforming single-pass and agentic-coding baselines by 37.1 and 14.6 points, respectively. Its scores also improve monotonically across refinement rounds. Further analysis shows that GUI-agent feedback is fully logged and traceable, while its priorities vary substantially across model backbones. These results establish GUI playtesting as an evaluation and refinement signal for interactive code generation. Our project website is available at https://continual-game-generation.vercel.app/

cs.SE↗

arXiv2026

RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data

Large language models (LLMs) are increasingly expected to tackle complex tasks, driven by their expanding applications and users' growing proficiency in crafting sophisticated prompts. However, as the number of explicitly stated requirements increases (particularly more than 10 constraints), LLMs often struggle to accurately follow such complex instructions, which limits their applicability in complex real-world scenarios. To the best of our knowledge, existing datasets do not exceed 10 constraints per instance. To address this challenge, we propose RECAST, an efficient and scalable framework for synthesizing datasets where each example incorporates far more constraints than those in existing benchmarks, aiming to challenge and extend the boundaries of models' ability to follow complex instructions. These constraints are extracted from real-world prompt-response pairs to ensure practical relevance. Using this framework, we construct RECAST-30K, a large-scale, high-quality dataset comprising 30k instances spanning 19 constraint types. Experimental results demonstrate that models finetuned on RECAST-30K substantially improve in following complex instructions while maintaining their general capabilities without degradation. Moreover, RECAST enables automatic verification of constraint satisfaction via rule-based validators for quantitative constraints and LLM-based validators for qualitative ones; the verifiability provided by RECAST enables the design of reward functions for reinforcement learning, which further boosts model performance on complex and challenging tasks.

cs.AI↗

arXiv2026

Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction

As LLM-based agents are increasingly used in long-term interactions, cumulative memory is critical for enabling personalization and maintaining stylistic consistency. However, most existing systems adopt an ``all-or-nothing'' approach to memory usage: incorporating all relevant past information can lead to \textit{Memory Anchoring}, where the agent is trapped by past interactions, while excluding memory entirely results in under-utilization and the loss of important interaction history. We show that an agent's reliance on memory can be modeled as an explicit and user-controllable dimension. We first introduce a behavioral metric of memory dependence to quantify the influence of past interactions on current outputs. We then propose \textbf{Stee}rable \textbf{M}emory Agent, \texttt{SteeM}, a framework that allows users to dynamically regulate memory reliance, ranging from a fresh-start mode that promotes innovation to a high-fidelity mode that closely follows interaction history. Experiments across different scenarios demonstrate that our approach consistently outperforms conventional prompting and rigid memory masking strategies, yielding a more nuanced and effective control for personalized human-agent collaboration.

cs.AI↗

arXiv2026

ClawBench: Can AI Agents Complete Everyday Online Tasks?

AI agents may be able to assist with emails and documents, but can they reliably complete everyday online workflows on real websites? Everyday online tasks offer a realistic yet unsolved testbed for evaluating the next generation of AI agents. To this end, we introduce ClawBench, an evaluation framework comprising 153 everyday online tasks that people need to accomplish regularly in their lives and work, spanning 144 platforms across 15 categories, from completing purchases and booking appointments to submitting job applications. These tasks require capabilities beyond existing benchmarks, such as obtaining relevant information from user-provided documents, navigating multi-step workflows across diverse platforms, and write-heavy operations like filling in many detailed forms correctly. Unlike existing benchmarks that evaluate agents in offline sandboxes with static pages, ClawBench operates on production websites, preserving the full complexity, dynamic nature, and interaction challenges of real-world web environments. An interception layer captures and blocks the final submission request, ensuring safe evaluation without real-world side effects. Our evaluations of 8 frontier models show that both proprietary and open-source models complete only a small portion of these tasks. For example, Claude Sonnet 4.6 achieves only 33.3%, which exposes gaps in current AI agents. Progress on ClawBench brings us closer to AI agents that can function as general-purpose assistants.

cs.CL↗

arXiv2026

ToolVerse: Unlocking Massive Environments and Long-Horizon Tasks for Agentic Reinforcement Learning

While LLM agents demonstrate strong reasoning abilities in compact and well-defined scenarios, they struggle to maintain robustness and effectiveness when faced with large-scale, diverse, and dynamic real-world environments that demand seamless tool integration. To address this gap, we introduce ToolVerse, a comprehensive framework that scales up agentic RL environments and enables agents to perform complex long-horizon reasoning in Tool-Integrated Reasoning (TIR) tasks. First, ToolVerse automatically builds the massive executable agent training environments from nearly 400 real-world Model Context Protocols (MCPs) that contain about 4500 tools. Second, we propose a task design strategy based on a tool dependency graph, utilizing Dynamic Unlocking Sampling Algorithm to generate long-horizon tasks, and produce GUST (Graph Unlocking Sampling Tasks) dataset. Third, to alleviate the credit assigment problem in long-horizon agentic RL, we propose a fine-grained Turn-Aware Relative Advantage algorithm. We conduct extensive Agentic RL training using ToolVerse and evaluate our framework on serveral agentic benchmarks. Experimental results demonstrate that our framework significantly strengthens LLMs' capabilities in long-horizon tool use, achieving a marked performance boost and showcasing robust reasoning within dynamic environments.

cs.AI↗

arXiv2026

TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios

As LLM-based agents are deployed in increasingly complex real-world settings, existing benchmarks underrepresent key challenges such as enforcing global constraints, coordinating multi-tool reasoning, and adapting to evolving user behavior over long, multi-turn interactions. To bridge this gap, we introduce \textbf{TRIP-Bench}, a long-horizon benchmark grounded in realistic travel-planning scenarios. TRIP-Bench leverages real-world data, offers 18 curated tools and 40+ travel requirements, and supports automated evaluation. It includes splits of varying difficulty; the hard split emphasizes long and ambiguous interactions, style shifts, feasibility changes, and iterative version revision. Dialogues span up to 15 user turns, can involve 150+ tool calls, and may exceed 200k tokens of context. Experiments show that even advanced models achieve at most 50\% success on the easy split, with performance dropping below 10\% on hard subsets. We further propose \textbf{GTPO}, an online multi-turn reinforcement learning method with specialized reward normalization and reward differencing. Applied to Qwen2.5-32B-Instruct, GTPO improves constraint satisfaction and interaction robustness, outperforming Gemini-3-Pro in our evaluation. We expect TRIP-Bench to advance practical long-horizon interactive agents, and GTPO to provide an effective online RL recipe for robust long-horizon training.

cs.AI↗

arXiv2025

SATER: A Self-Aware and Token-Efficient Approach to Routing and Cascading

Large language models (LLMs) demonstrate remarkable performance across diverse tasks, yet their effectiveness frequently depends on costly commercial APIs or cloud services. Model selection thus entails a critical trade-off between performance and cost: high-performing LLMs typically incur substantial expenses, whereas budget-friendly small language models (SLMs) are constrained by limited capabilities. Current research primarily proposes two routing strategies: pre-generation routing and cascade routing. Both approaches have distinct characteristics, with cascade routing typically offering superior cost-effectiveness and accuracy despite its higher latency. To further address the limitations of both approaches, we introduce SATER, a dual-mode compatible approach that fine-tunes models through shortest-response preference optimization and a confidence-aware rejection mechanism. SATER significantly reduces redundant outputs and response times, while improving both the performance of pre-generation routing and the efficiency of cascade routing. Experiments across three SLMs and six datasets, varying in type and complexity, demonstrate that SATER achieves comparable performance while consistently reducing computational costs by over 50\% and cascade latency by over 80\%.

cs.DC↗

arXiv2025

IntentionReasoner: Facilitating Adaptive LLM Safeguards through Intent Reasoning and Selective Query Refinement

The rapid advancement of large language models (LLMs) has driven their adoption across diverse domains, yet their ability to generate harmful content poses significant safety challenges. While extensive research has focused on mitigating harmful outputs, such efforts often come at the cost of excessively rejecting harmless prompts. Striking a balance among safety, over-refusal, and utility remains a critical challenge. In this work, we introduce IntentionReasoner, a novel safeguard mechanism that leverages a dedicated guard model to perform intent reasoning, multi-level safety classification, and query rewriting to neutralize potentially harmful intent in edge-case queries. Specifically, we first construct a comprehensive dataset comprising approximately 163,000 queries, each annotated with intent reasoning, safety labels, and rewritten versions. Supervised fine-tuning is then applied to equip the guard model with foundational capabilities in format adherence, intent analysis, and safe rewriting. Finally, we apply a tailored multi-reward optimization strategy that integrates rule-based heuristics and reward model signals within a reinforcement learning framework to further enhance performance. Extensive experiments show that IntentionReasoner excels in multiple safeguard benchmarks, generation quality evaluations, and jailbreak attack scenarios, significantly enhancing safety while effectively reducing over-refusal rates and improving the quality of responses.

cs.AI↗

arXiv2025

TripTailor: A Real-World Benchmark for Personalized Travel Planning

The continuous evolution and enhanced reasoning capabilities of large language models (LLMs) have elevated their role in complex tasks, notably in travel planning, where demand for personalized, high-quality itineraries is rising. However, current benchmarks often rely on unrealistic simulated data, failing to reflect the differences between LLM-generated and real-world itineraries. Existing evaluation metrics, which primarily emphasize constraints, fall short of providing a comprehensive assessment of the overall quality of travel plans. To address these limitations, we introduce TripTailor, a benchmark designed specifically for personalized travel planning in real-world scenarios. This dataset features an extensive collection of over 500,000 real-world points of interest (POIs) and nearly 4,000 diverse travel itineraries, complete with detailed information, providing a more authentic evaluation framework. Experiments show that fewer than 10\% of the itineraries generated by the latest state-of-the-art LLMs achieve human-level performance. Moreover, we identify several critical challenges in travel planning, including the feasibility, rationality, and personalized customization of the proposed solutions. We hope that TripTailor will drive the development of travel planning agents capable of understanding and meeting user needs while generating practical itineraries. Our code and dataset are available at https://github.com/swxkfm/TripTailor

cs.AI↗

arXiv2024

Generating 6-D Trajectories for Omnidirectional Multirotor Aerial Vehicles in Cluttered Environments

As fully-actuated systems, omnidirectional multirotor aerial vehicles (OMAVs) have more flexible maneuverability and advantages in aggressive flight in cluttered environments than traditional underactuated MAVs. %Due to the high dimensionality of configuration space, making the designed trajectory generation algorithm efficient is challenging. This paper aims to achieve safe flight of OMAVs in cluttered environments. Considering existing static obstacles, an efficient optimization-based framework is proposed to generate 6-D $SE(3)$ trajectories for OMAVs. Given the kinodynamic constraints and the 3D collision-free region represented by a series of intersecting convex polyhedra, the proposed method finally generates a safe and dynamically feasible 6-D trajectory. First, we parameterize the vehicle's attitude into a free 3D vector using stereographic projection to eliminate the constraints inherent in the $SO(3)$ manifold, while the complete $SE(3)$ trajectory is represented as a 6-D polynomial in time without inherent constraints. The vehicle's shape is modeled as a cuboid attached to the body frame to achieve whole-body collision evaluation. Then, we formulate the origin trajectory generation problem as a constrained optimization problem. The original constrained problem is finally transformed into an unconstrained one that can be solved efficiently. To verify the proposed framework's performance, simulations and real-world experiments based on a tilt-rotor hexarotor aerial vehicle are carried out.

cs.RO↗