RLPF: Reinforcement Learning from Performance Feedback for Code Generation

Code models are increasingly trained with execution feedback, but most training signals still stop at correctness. This leaves an important gap for systems code: two programs can pass the same tests while differing greatly in runtime. We study how to train code agents to prefer faster correct implementations, rather than treating efficiency only as an evaluation metric. The key difficulty is that runtime is a fragile reward. It is meaningful only after a program is correct, varies across tasks, and gives little guidance when most sampled programs fail to compile or run. We propose \textbf{RLPF}, reinforcement learning from performance feedback, which turns execution outcomes into a staged reward. Failed programs are ordered by execution progress, while correct programs are ranked by their relative improvement from the baseline toward the expert reference. This gives useful feedback before correctness and performance-sensitive feedback after correctness. Fine-tuning Qwen3-32B with RLPF on PerfCodeBench raises correct-and-runnable solutions from $11.1\%$ to $54.6\%$ and improves relative efficiency from $8.1\%$ to $38.6\%$. The trained model becomes competitive with stronger open-weight systems, and its optimization behavior transfers modestly to EffiBench-X. Additional studies show that model-generated references provide useful but weaker supervision, and that the full composite reward is more reliable than correctness-only or runtime-only baselines. These results suggest that code agents can be trained not only to pass tests, but also to optimize the programs they write.

MultivationBench: A Benchmark for Multimodal Sequential Motivation Reasoning

Multimodal Large Language Models have sparked significant interest due to their potential for social intelligence; however, their ability to perform sequential motivation reasoning remains insufficiently studied. Existing evaluations predominantly examine static text or isolated visual snapshots, which do not reflect the cumulative nature of real-world behavioral drivers. To address this gap, we introduce MultivationBench, a benchmark designed to rigorously evaluate multimodal motivation reasoning within story-driven visual narratives. The benchmark builds upon established psychological frameworks - Maslow's hierarchy and Reiss's basic desires - and requires models to integrate accumulated multimodal context to infer evolving motivations. Results indicate that MultivationBench presents a significant challenge: all tested models struggle to maintain consistent motivation reasoning across sequential contexts, revealing a critical disconnect between static recognition capabilities and the dynamic reasoning essential for human-like social understanding.

DishSeg24k: A Large-Scale Benchmark for Food Segmentation with Stochastic Expert Decoding

Food segmentation is essential for applications such as intelligent catering, dietary assessment, and recommendation. However, existing benchmarks fail to capture the complexity of real-world dining scenes. The challenges of dense inter-dish overlap, fine-grained class similarity, and extreme long-tail class distributions exceed the fidelity of current datasets. To fill this gap, we introduce \textbf{DishSeg24k}, a large-scale dish-level segmentation benchmark with 24,096 images, 112,281 instances, and 278 fine-grained categories in real-world dining environments. Based on DishSeg24k, we further propose \textbf{Food Expert-Adaptive Segmentation Transformers (FEAST)} to address these challenges. FEAST models query-based decoding as a Markov Decision Process (MDP), where each decoder layer update is treated as a sequential decision step that explores uncertainty along dish boundaries. We further redesign the decoder with a reinforcement learning (RL)-guided Mixture-of-Experts (MoE) module, in which a dual-critic decoupled optimization scheme separates task-oriented query refinement from structure-aware expert routing. This design promotes expert specialization and prevents expert collapse under long-tail category distributions. Finally, extensive experiments on DishSeg24k demonstrate the state-of-the-art performance of FEAST, which outperforms previous methods by {+3.21\%} mIoU, {+3.68\%} mDice, and {+4.00\%} mAcc, respectively. We further validate the effectiveness of FEAST on FoodSeg103. The dataset and code will be publicly released.

Handroid: Bridging Dexterous Hand and Humanoid

Dexterous hands and humanoid robots are typically developed as distinct embodiments: the former enable contact-rich manipulation at the object scale, whereas the latter provide mobility and whole-body interaction in human-centered environments. We introduce \textbf{Handroid}, a desktop-scale dual-embodiment robot that integrates both capabilities within a single reconfigurable platform. Handroid reuses one 27-DoF electromechanical body as either a dexterous hand or a desktop humanoid, measuring 0.33 m in height and 2.05 kg in weight. In the dexterous hand embodiment, 20 DoFs form an anthropomorphic hand closely matching the kinematic structure of the human hand. In the humanoid embodiment, the same articulated modules are reconfigured into a humanoid with a head, arms, and legs, including a 12-DoF lower-limb structure for locomotion and whole-body motion. Handroid further provides a unified control and learning framework supporting hand teleoperation, dexterous grasping, in-hand manipulation, humanoid locomotion, gait generation, and interactive motion authoring. We validate the platform through real-world dexterous manipulation, reinforcement-learning-based locomotion, keyframe motion deployment, and a long-horizon task involving embodiment reconfiguration, locomotion, docking, and dexterous pick-and-place. These results position Handroid as a compact and reproducible platform for advancing morphology-reconfigurable robotics and cross-embodiment robot learning.

Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions

The capability of LLM agents to function as the ``brain'' of a system fundamentally expands the scope of analysis beyond a standalone model. Consequently, safety is no longer only about input--output content alignment. It also concerns system behavior and real-world execution outcomes. However, the current literature is fragmented across attack types, applications, and benchmarks. This makes it hard to explain why failures such as prompt injection, tool misuse, and memory poisoning often share the same structural cause, and how they spread through an agent workflow. In this survey, we treat isolation as a first-class principle for LLM-agent system safety. By isolation, we refer to the separation of user inputs, tool access, execution channels, inter-agent communication, and environment-originated context. We organize the literature with a boundary-centric taxonomy of five boundaries: user-agent, agent-tool, agent-execution, agent-agent, and system-environment. This view helps identify where the loss of isolation first occurs, how compromise propagates across boundaries, and which defenses are most relevant at each interface. We also summarize cross-boundary failure paths, discuss open challenges, and outline a research agenda for isolation-by-construction in future agent systems.

SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents

Large language model (LLM) agents increasingly rely on agent harnesses that manage context, tools, and multi-turn execution, making tools a central interface for acting in realistic digital environments. As harness-connected tool ecosystems expand to hundreds or thousands of APIs, services, and task-specific skills, exhaustive tool schema injection becomes costly and imposes a closed-world assumption that limits agents to a predefined static inventory. Retrieval-augmented tool selection offers a natural alternative, but existing one-shot retrieval methods often fail to align isolated tool descriptions with the agent's true task intention, especially in long-horizon tasks where required capabilities emerge through decomposition, observations, and newly induced subgoals. We propose SING, an intention-aware active tool discovery framework that builds an intention-tool graph linking user intentions, tool capabilities, and tool collaboration patterns, and dynamically retrieves tools according to evolving task states. Using a unified corpus of 7,471 tools, we evaluate SING on three real-world tool-use benchmarks. SING improves Global Recall@5 by up to 59.8% and downstream success rate by up to 28.9% over baselines, while reducing full-corpus tool-schema exposure by 99.8%, demonstrating that intention-aware graph structure enables more accurate and context-efficient tool discovery in large-scale agentic ecosystems.

OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset

Ensuring the safety and compliance of large language models (LLMs) is of paramount importance. However, existing LLM safety datasets often rely on ad-hoc taxonomies for data generation and suffer from a significant shortage of rule-grounded, real-world cases that are essential for robustly protecting LLMs. In this work, we address this critical gap by constructing a comprehensive safety dataset from a compliance perspective. Using a powerful web-searching agent, we collect a rule-grounded, real-world case dataset OmniCompliance-100K, sourced from multi-domain authoritative references. The dataset spans 74 regulations and policies across a wide range of domains, including security and privacy regulations, content safety and user data privacy policies from leading AI companies and social media platforms, financial security requirements, medical device risk management standards, educational integrity guidelines, and protections of fundamental human rights. In total, our dataset contains 12,985 distinct rules and 106,009 associated real-world compliance cases. Our analysis confirms a strong alignment between the rules and their corresponding cases. We further conduct extensive benchmarking experiments to evaluate the safety and compliance capabilities of advanced LLMs across different model scales. Our experiments reveal several interesting findings that have great potential to offer valuable insights for future LLM safety research.

TRACE: Temporal Rule-Anchored Chain-of-Evidence on Knowledge Graphs for Interpretable Stock Movement Prediction

We present a Temporal Rule-Anchored Chain-of-Evidence (TRACE) on knowledge graphs for interpretable stock movement prediction that unifies symbolic relational priors, dynamic graph exploration, and LLM-guided decision making in a single end-to-end pipeline. The approach performs rule-guided multi-hop exploration restricted to admissible relation sequences, grounds candidate reasoning chains in contemporaneous news, and aggregates fully grounded evidence into auditable \texttt{UP}/\texttt{DOWN} verdicts with human-readable paths connecting text and structure. On an S\&P~500 benchmark, the method achieves 55.1\% accuracy, 55.7\% precision, 71.5\% recall, and 60.8\% F1, surpassing strong baselines and improving recall and F1 over the best graph baseline under identical evaluation. The gains stem from (i) rule-guided exploration that focuses search on economically meaningful motifs rather than arbitrary walks, and (ii) text-grounded consolidation that selectively aggregates high-confidence, fully grounded hypotheses instead of uniformly pooling weak signals. Together, these choices yield higher sensitivity without sacrificing selectivity, delivering predictive lift with faithful, auditably interpretable explanations.

Minimalist Compliance Control

Compliance control is essential for safe physical interaction, yet its adoption is limited by hardware requirements such as force torque sensors. While recent reinforcement learning approaches aim to bypass these constraints, they often suffer from sim-to-real gaps, lack safety guarantees, and add system complexity. We propose Minimalist Compliance Control, which enables compliant behavior using only motor current or voltage signals readily available in modern servos and quasi-direct-drive motors, without force sensors, current control, or learning. External wrenches are estimated from actuator signals and Jacobians and incorporated into a task-space admittance controller, preserving sufficient force measurement accuracy for stable and responsive compliance control. Our method is embodiment-agnostic and plug-and-play with diverse high-level planners. We validate our approach on a robot arm, a dexterous hand, and two humanoid robots across multiple contact-rich tasks, using vision-language models, imitation learning, and model-based planning. The results demonstrate robust, safe, and compliant interaction across embodiments and planning paradigms.

SurveyLens: A Research Discipline-Aware Benchmark for Automatic Survey Generation

The exponential growth of scientific literature has driven the evolution of Automatic Survey Generation (ASG) from simple pipelines to multi-agent frameworks and commercial Deep Research agents. However, current ASG evaluation methods rely on generic metrics and are heavily biased toward Computer Science (CS), failing to assess whether ASG methods adhere to the distinct standards of various academic disciplines. Consequently, researchers, especially those outside CS, lack clear guidance on using ASG systems to yield high-quality surveys compliant with specific discipline standards. To bridge this gap, we introduce SurveyLens, the first discipline-aware benchmark evaluating ASG methods across diverse research disciplines. We construct SurveyLens-1k, a curated dataset of 1,000 high-quality human-written surveys spanning 10 disciplines. Subsequently, we propose a dual-lens evaluation framework: (1) Discipline-Aware Rubric Evaluation, which utilizes LLMs with human preference-aligned weights to assess adherence to domain-specific writing standards; and (2) Canonical Alignment Evaluation to rigorously measure content coverage and synthesis quality against human-written survey papers. We conduct extensive experiments by evaluating 11 state-of-the-art ASG methods on SurveyLens, including Vanilla LLMs, ASG systems, and Deep Research agents. Our analysis reveals the distinct strengths and weaknesses of each paradigm across fields, providing essential guidance for selecting tools tailored to specific disciplinary requirements.