Agent 进展

Personal health management unfolds over repeated encounters, yet most health AI systems treat each request in isolation. We developed HealthClaw, an open-source agent architecture that updates support as a person's routines, preferences, measurements and risks change. It separates shared safety rules and medical knowledge from private longitudinal memory containing profile facts, reusable procedures and episodic traces. After each episode, induction determines what should update the profile, revise a procedure, remain episodic or be excluded. We evaluated HealthClaw with a synthetic year-long benchmark and nine 200-case biomedical tasks. Across 900 longitudinal support probes, answer accuracy increased from 0.2% with current-query prompting to 45.7% with HealthClaw, while prompt-side context exposure was 71.7% lower than with full-history prompting. In 100 privacy probes, HealthClaw produced higher privacy-aware answer quality and fewer unsafe disclosures than both baselines. Across the biomedical tasks, the mean absolute gain in the task-specific primary metric was 27.0 percentage points, and seven gains remained significant after false-discovery-rate correction. These offline benchmarks support governed, self-evolving memory for longitudinal personal health agents, although clinical effectiveness requires prospective evaluation. HealthClaw is publicly available at https://github.com/HC-Guo/HealthClaw.

Most daily activities are inherently procedural. However, existing evaluations for egocentric video understanding seldom address procedural understanding and largely overlook complex key-step-level reasoning under the widely used video question answering (VQA) paradigm for MLLMs. Such capabilities are crucial for building procedural AI assistants deployable on wearable devices. To bridge this gap, we introduce the Egocentric Procedural Understanding VQA task (EgoProceVQA), which systematically evaluates egocentric procedural reasoning abilities of current MLLMs and agents through six types of key-step-centric questions. Furthermore, we develop EgoProceGen, a data generation platform that efficiently constructs QA data tailored to different question types. Based on this platform, we build a benchmark with 3,600 questions, four common procedural scenarios, and 31 everyday procedural tasks. Evaluations on EgoProceVQA show that existing MLLMs and agents still have substantial room for improvement in procedural understanding. Therefore, we further propose EgoProceAgent, a self-skill-exploration agentic framework. We design a generic tool library for procedural understanding and a standardized sub-skill library shared across tools and models, enabling self-exploration without ground-truth supervision. By exploring how to compose and select sub-skills, the agent discovers effective skill strategies for diverse problems, and attains state-of-the-art performance among open-source models on multiple tasks. Together, our benchmark, generation platform, and agentic framework establish a unified foundation for EgoProceVQA. Project page: https://z1oong.github.io/EgoProceVQA/.

We present MyAG, a graph-based framework for designing and analyzing composable LLM agent systems. Our framework separates agent system construction into three graph abstractions: a component graph for agents, environments, and modules; a workflow graph for execution control; and a search graph for runtime execution. This separation allows users to flexibly reuse the same components with different strategies. We further support hierarchical composition through recursive system nodes and provide monitoring and visualization tools for inspecting agent execution. Experiments on representative agent applications show that our framework supports flexible agent system design and helps analyze performance-efficiency tradeoffs. Our framework is publicly available and fully open-source.

Explainable Reinforcement Learning (XRL) seeks to make Reinforcement Learning (RL) policies more transparent and interpretable, a key requirement in safety-critical and human-centric scenarios. However, it is mostly based on user studies, thus targeting the needs of a specific audience and lacking shared evaluation metrics. On the other hand, logic-based approaches within eXplainable Artificial Intelligence (XAI) provide compact, human-readable abstractions of decision-making. However, the systematic quantification of the explainability degree of logical representations remains an open problem. This work aims to advance the state of the art in XRL by introducing objective and planning-oriented metrics for policy explainability in RL settings. At the same time, it contributes to the field of logic for XAI by providing a principled way to quantify the explainability of logical rules, moving beyond common-sense assessments and simple propositional fragments. We employ Inductive Logic Programming (ILP) to extract symbolic representations of RL policies and define a novel set of explainability metrics, including activation rate, feature coverage, syntactic distance and semantic distance. These metrics quantify alignment between symbolic rules and agent behavior, the role of features in decision-making, and the evolution of policies during training and across agents in single and multi-agent RL. Experiments across different RL domains show that the proposed metrics highlight action-specific learning dynamics beyond global return, provide fine-grained insights into domain features beyond classical approaches for global feature importance estimation, and uncover coordination, specialization, and adaptation patterns in MARL. Moreover, they provide crucial insights for the transfer and generalization of action-specific policies.

Recent advances in generative and embodied AI have been driven by large-scale predictive learning over multimodal data. However, the resulting systems remain largely based on passive training regimes where linguistic regularities create the scaffold onto which information from other modalities is attached. Conversely, neuroscience and cognitive science suggest that biological intelligence is organized in the opposite way, where grounded world models acquired through interaction with the environment provide the semantic scaffold to which language is attached. Here, we illustrate five examples of neural circuits supporting grounded world modelling, which underlie navigation in physical and conceptual spaces, affordance-based perception and interaction with objects, active perception and exploratory learning, allostatic control and emotion, and the distinction between self- and world-generated outcomes. These examples highlight several features largely missing from current embodied AI, including the role of intrinsic dynamics as a foundation for learning, the centrality of action in aligning these dynamics with the external world, the prominence of autonomous experience and open-ended learning over passive assimilation of externally provided data, and the fact that early predictive and control mechanisms scaffold higher cognitive abilities such as reasoning, conceptual navigation, planning, imagination, understanding others' minds, and communication. Finally, we discuss whether and how principles derived from biological systems may inform future embodied AI, including training regimes based on social interaction to construct world models that are not only grounded but also socially shared and aligned with human norms and values.

Vision-Language Models (VLMs) have demonstrated remarkable potential for high-level reasoning in autonomous driving, yet they fundamentally struggle to generate precise, low-level control actions. This limitation is rooted in a semantic-physical gap caused by the inherent mismatch between discrete language tokens and continuous trajectory planning. While Vision-Language-Action (VLA) architectures attempt to bridge this gap by unifying perception and control into a single policy, this entanglement creates a new bottleneck. Standard VLAs experience a severe spatial representation collapse, which irreversibly degrades the fine-grained spatial and geometric priors essential for safe, boundary-aware navigation. To address this limitation, we propose the S-squared-VLA, which explicitly decouples the semantic and spatial streams in Vision-Language-Action models. The semantic stream leverages hierarchical bridging to extract multi-scale VLM features for robust intent reasoning. In parallel, an independent spatial stream bypasses the autoregressive language bottleneck, directly preserving uncompressed spatial features from the visual encoder. By integrating auxiliary perception supervision, this stream explicitly equips the model with rich spatial and geometric priors. Finally, a dual-stream planning adapter fuses high-level semantic intent with precise spatial constraints via cascaded attention mechanisms. Evaluations on the NAVSIM closed-loop benchmark show that S-squared-VLA achieves a Predictive Driver Model Score (PDMS) of 87.1, establishing a new state-of-the-art for VLA models under a purely supervised fine-tuning (SFT) setting. By mitigating the spatial representation collapse of traditional VLMs, our framework significantly outperforms baselines, achieving the highest No Collision (NC) rate of 98.4 among all evaluated methods.

LLM-based agents have rapidly improved at operating individual digital environments such as mobile applications, desktop systems, and smart homes. However, real-world user goals often span multiple devices: information may come from a phone, be processed on a desktop, and the result may need to appear on another device. Most existing benchmarks center on a single dominant execution environment, making it difficult to evaluate whether agents can acquire and integrate information across heterogeneous devices and complete end-to-end tasks with cross-device dependencies. We introduce DevicesWorld, a large-scale executable benchmark for cross-device collaborative operation. DevicesWorld contains 6,140 tasks and integrates three classes of device environments — mobile, desktop, and IoT — into a unified cross-device interaction and evaluation framework. Each task defines a natural-language user goal, participating devices and initial states, executable actions, rule-based verifiers, and a cleanup procedure. A multi-stage construction and quality-control pipeline keeps tasks close to realistic user needs while allowing final outcomes to be automatically verified from device states and generated files. We evaluate five frontier LLM-agent systems on a fixed evaluation set. All methods achieve low success rates, with the best reaching only 12.5%. Among failed runs, about 28.7% satisfy at least one scoring condition yet still fail the full task. Trajectories show that agents become stuck acquiring information or manipulating interfaces, confuse source and output devices, or terminate before all conditions are jointly satisfied. DevicesWorld turns cross-device collaborative operation into an executable, reproducible, and diagnostically useful evaluation problem for research on reliable cross-device agents.

Multi-turn agents solve complex tasks through extended sequences of tool interactions before producing a final answer, making credit assignment a fundamental challenge during post-training. Outcome rewards provide reliable supervision for short-horizon reasoning, but become sparse and high-variance as trajectories grow to tens or hundreds of tool calls. They can also be misleading: a failed rollout may contain many useful actions that move the agent closer to the goal, yet outcome-only training assigns them the same negative advantage as the eventual mistake. We propose TRACE (Turn-level Reward Assignment via Credit Estimation), a dense credit-assignment method for agentic reinforcement learning. TRACE represents rollouts as state transitions at tool-call boundaries, obtains gold-answer log-probabilities from a frozen reference model, transforms them into log-ratio state values, and derives per-action rewards as Temporal-Difference changes in those values. This requires no additional critic or process-label training, and its one-step log-ratio TD component telescopes across redundant tool calls. On long-horizon complex search, TRACE substantially improves base-model tool-use ability using pure RL, without a cold-start supervised fine-tuning stage, an agentic mid-training stage, or training on live-web data. On the closed-web BrowseComp-Plus benchmark, it raises Qwen3-4B from $7.2$ to $35.6$ and Qwen3-30B-A3B from $8.4$ to $42.6$. The learned search behavior also transfers to open-web benchmarks, and the learning curves show earlier improvement and faster convergence during RL training.

Automated Program Repair (APR) has witnessed significant progress with the advent of Large Language Models (LLMs). However, as modern software systems increasingly expose rich graphical user interfaces, effectively leveraging visual information from bug screenshots has become essential for understanding bugs and generating accurate fixes in multimodal scenarios. Real-world issue reports frequently contain heterogeneous visual attachments including UI screenshots, IDE snapshots, GIFs, and text-centric images, each with distinct visual patterns and domain-specific semantics that impose substantial perceptual demands on MLLMs. Furthermore, bug screenshots often contain large expanses of uninformative and bug-irrelevant regions, distracting the model's attention and limiting patch diversity. To address these challenges, we propose VisualRepair, an MLLM-based framework for visual software issue repair comprising two core modules: Image Type-aware Tool Calling (ITTC), which classifies input images and dynamically invokes a tailored tool-calling chain for robust visual interpretation, and Dynamic Test-time Region Focusing (DTRF), which grounds multiple bug-related region candidates and refines them via an adaptive zoom-in and zoom-out strategy to improve fault localization and promote diverse patch generation. Extensive experiments on the SWE-bench Multimodal benchmark demonstrate that VisualRepair consistently outperforms state-of-the-art approaches. VisualRepair resolves 196 and 25 instances on the test and dev sets, respectively, surpassing the best baseline by 10 and 11 instances. These results highlight the effectiveness of type-aware visual understanding and region-focused localization for automated visual software issue repair.

Active 3D reconstruction requires selecting informative viewpoints under limited sensing budgets. In multi-agent settings, coordination inefficiencies such as redundant observations and spatial clustering can significantly reduce reconstruction quality. We present COLMAR, a cooperative view policy learning framework for multi-agent active 3D reconstruction. COLMAR formulates viewpoint allocation as a shared policy optimization over map-centric observations and introduces a reconstruction-aware objective that promotes overlap-aware coverage, team-level discovery, and collision-safe exploration. Dense feedback derived from incremental reconstruction updates aligns exploration behavior with downstream geometric quality. The policy is trained using parameter-sharing Proximal Policy Optimization (PPO) with independent per-agent action selection at deployment, conditioned on a fused team map and without inter-agent message passing for decision making. Selected viewpoints are then reconstructed with 3D Gaussian Splatting (3DGS) for high-fidelity photometric evaluation. Experiments on GLEAM and Replica demonstrate consistent improvements over heuristic and non-cooperative baselines, achieving up to 54% higher reconstruction accuracy and 49% greater coverage under matched sensing budgets.

Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks. Yet nearly all existing approaches, from graph-structured memories to reflective insight stores, access memory through fixed, hand-designed heuristics. We argue that this static view of memory is a core bottleneck for agentic learning because optimal memory behavior is fundamentally context-dependent. The early stages of the tasks, benefit from minimal retrieval because memory is sparse; recurring goal types benefit from plan reuse rather than generic nearest-neighbor lookup; stuck agents benefit from re-retrieval with alternative queries; and across long task streams, the memory store itself must be consolidated and pruned to remain useful. We present Memory as a Controlled Process (MemCon), a framework that models memory operations as a Markov Decision Process and learns an online policy that adaptively decides when, what, and how much to retrieve, when to inject a distilled plan, and when to consolidate or forget. MemCon is backend-agnostic: it wraps any existing memory implementation, learns from task-by-task binary feedback with no pretraining and no additional LLM calls, and uses a lightweight tabular contextual bandit with UCB exploration that converges within tens of tasks. Across 6 benchmarks, 3 agent frameworks, and 3 LLM backbones, MemCon consistently outperforms multiple memory baselines by up to 15.2 points in task success while reducing token consumption by 5--20%.

Real-world deployment of embodied agents requires active exploration, visual grounding, and interactive intent disambiguation. However, existing frameworks often rely on privileged simulator states or assume complete instructions, bypassing realistic deployment challenges. To bridge this gap, we present REAL, an agentic framework for open-world mobile manipulation. REAL establishes sim-to-real-consistent environment APIs without oracle perception and integrates a simulated user to enable human-in-the-loop interaction. Within this environment, we design diverse task compositions to drive data collection, supervised fine-tuning, and online reinforcement learning, systematically optimizing agent performance. To comprehensively evaluate this approach, we introduce REAL-Bench, a benchmark spanning 241 tasks across active exploration, visual distraction, articulated manipulation, and interactive disambiguation. Experimental results demonstrate that our trained agent outperforms leading commercial closed-source VLMs on interactive tasks with a 56.9% success rate. Further empirical analysis reveals that our hierarchical training pipeline successfully aligns the model's tool-use capabilities while maintaining robust open-vocabulary reasoning under extended exploration horizons. Finally, we deploy and evaluate our framework on a physical dual-arm mobile robot, where it achieves a 78.3% end-to-end success rate over 60 real-world episodes. These physical trials demonstrate robust zero-shot transferability to unseen household scenarios, validating that our sim-to-real-consistent design successfully bridges the reality gap for long-horizon mobile manipulation. Code is available at https://github.com/InternRobotics/REAL.

Large Language Model (LLM) agents have shown remarkable capabilities in autonomous decision-making by generating sequential trajectories of states, actions, and observations. However, in complex, long-horizon tasks, these agents frequently suffer from compounding errors and struggle to recover from failures. Existing self-correction mechanisms rely on prompt-based reflection, which is inherently brittle, incurs heavy time and API costs due to iterative trial-and-error loops, and produces task-specific memory that may be hard to generalize to new scenarios. To address this, we propose Experience Memory Graph (EMG), a framework that reformulates agent failure recovery as a graph matching problem. At training time, we convert both failed exploration trajectories and successful expert trajectories into directed action decision graphs. By matching these graphs, we extract common subgraphs (successful workflows) and graph edit paths that explicitly indicate how to correct failures (e.g., which actions to add, delete, or relabel under a given observation), and store them in a memory graph with intra-task nodes and cross-task edges. At test time, EMG retrieves relevant insights and guides the agent in a single, loop-free execution. Experiments on ALFWorld and ScienceWorld show that EMG consistently outperforms state-of-the-art reflection baselines in success rate and average reward, while requiring no test-time trial-and-error.

What happens to an LLM agent's tool choice when the reliable tool silently changes within an ongoing session? We borrow set-shifting from cognitive psychology to study how well agents adapt to hidden reliability shifts. Our benchmark mounts tool-skill libraries with redundancies, where many tools solve the same task but differ in hidden reliability. In our evaluation framework, a branched schedule shifts the reliable tool group at hidden boundaries and pairs every shift with a no-shift control. We find that agents, by default, settle on a small recurring routine within a few turns of each boundary, with call shares concentrating on a few discrete values after each reliability shift. We score the set-shifting accuracy for each agent trajectory: the joint probability of routing to the target tool group in every post-shift window. We test open-weight LLMs in an open-source agentic harness and find qualitatively distinct failure modes across the same set of routines. We also find that set framing, how the toolset presents the alternatives as competing or complementary, shifts the routing dynamics.

Large language models (LLMs) are increasingly applied to vulnerability detection due to their strong code comprehension capabilities, but most existing approaches rely on isolated functions or context extracted by fixed program-analysis rules. These methods cannot adaptively explore repository-level dependencies to gather sufficient context when vulnerabilities span multiple functions or files, compromising detection reliability. We present DREA (Decoupled Reasoning and Exploration Agents), a hypothesis-driven framework for repository-level vulnerability detection. DREA decouples reasoning from exploration through two collaborating agents: a planning agent backed by an advanced LLM that forms vulnerability hypotheses and directs the investigation, and an explorer agent powered by a lightweight model that retrieves repository-level context on demand. Goal-directed context acquisition is the primary source of detection improvement in this design, while offloading token-heavy exploration to the local model keeps inference economically tractable. To support evaluation, we construct RepoPairBench, a repository-grounded benchmark of validated Python vulnerability-fix pairs from real-world projects. Beyond binary detection accuracy, we introduce a reasoning correctness evaluation to assess whether a model's rationale matches the documented vulnerability mechanism. Across three LLMs, DREA improves Pair-Correctness from 19-26% to 30-42% while offloading over 93% of tokens to the explorer, reducing estimated billable API cost by a factor of 16-48. Reasoning correctness analysis further reveals that 26-55% of true positives, for both DREA and the function-only baseline, are correct predictions supported by flawed rationales, identifying security reasoning quality as a shared bottleneck for current LLMs.

The rapid proliferation of Agentic Artificial Intelligence fundamentally disrupts traditional customer loyalty paradigms. As AI evolves from passive recommendation algorithms to autonomous, goal-directed agents capable of executing purchasing decisions, the conventional understanding of consumer-brand relationships requires a structural reevaluation. By synthesizing extant literature across human-machine teaming, consumer decision-making, and algorithmic trust dynamics, we demonstrate that traditional loyalty models fail to account for algorithmic bounded rationality and constructed autonomy. To address this, we introduce the Dynamic Verifiable Multi-Agent Human Agentic Loyalty Loop (DVM-HALL) model. We formalize brand choice via a softmax probability formulation where human emotional equity, agentic machine-experience utility, calibrated trust, delegated authority, and verifiable execution jointly determine selection. The model features recursive updating mechanisms to dynamically calibrate trust and delegation after each interaction. Crucially, the framework integrates a verifiable execution layer for Decentralized Finance (DeFi) and tokenized loyalty settings, incorporating execution risks — such as gas costs, slippage, MEV exposure, and smart-contract vulnerabilities — as core predictors of agentic brand preference. Furthermore, we introduce the Net Human-Agent Score (NHAS), an auditable, risk-weighted metric designed to measure human-agent alignment using human feedback, execution logs, benchmark comparisons, and verifiable receipts. Finally, we propose a comprehensive three-stage empirical validation plan spanning controlled shopping experiments, multi-agent market simulations, and DeFi testbeds. This framework provides the foundational theory required for brands to navigate the impending transition toward machine customers.

As Large Language Models (LLMs) evolve into autonomous agents, the need for unified evaluation infrastructure becomes critical. However, current evaluation pipelines remain highly fragmented and tightly coupled, hindering reproducibility and causing redundant engineering. To address this, we introduce AgentCompass, an open-source, lightweight, and extensible infrastructure for evaluating LLM-based agents. AgentCompass organizes the evaluation process around three independent components, namely Benchmark, Harness, and Environment, thereby enabling flexible configurations without requiring the reimplementation of complex execution logic. Furthermore, it features a fault-tolerant asynchronous runtime and comprehensive trajectory analysis tools to transparently diagnose nuanced failure modes like reward-hacking. Natively supporting over 20 benchmarks across five capability dimensions, AgentCompass provides the community with a scalable and reproducible infrastructure for advancing agent research.

Multimodal agents that think with images iteratively manipulate visual evidence and invoke tools across many steps. Existing reinforcement learning methods reduce trajectories to scalar rewards, forcing the policy to discover reusable tool-use patterns from scratch on every new task; memory-based alternatives retain past experience, yet they rely on test-time retrieval, without updating the policy to absorb reusable patterns from that experience. Our key insight is that multimodal reasoning trajectories should be distilled into reusable skills that co-evolve with the policy during training, rather than being consumed as rewards or retrieved from a static store. To this end, we propose SPyCE (Skill-Policy Co-evolution), a framework that distills trajectories into a hierarchical skill library and updates it throughout reinforcement learning. Execution skills capture local visual operations, while workflow skills encode high-level priors that orchestrate tool use. During training, the policy model conditions on retrieved skills to guide its rollouts, while the skill library evolves using valuable rollouts generated by the policy. This creates a closed loop in which improved policies yield better skills, and the evolving skill library, in turn, provides stronger priors for policy rollouts. Experiments across eight benchmarks demonstrate that SPyCE consistently outperforms both RL-based and memory-based baselines. Further analysis reveals that both the hierarchical skill design and the co-evolution mechanism are critical to our design. These results suggest joint skill-policy optimization as a promising paradigm for building capable multimodal agents.

Urban region profiling constitutes a core problem in urban computing, supporting applications such as population estimation, economic assessment, and environmental monitoring. Existing methods typically formulate this task as multimodal representation learning, fusing heterogeneous urban data, e.g., satellite imagery, points of interest, textual descriptions, and 3D building information, into latent embeddings for prediction. However, these approaches are largely correlation-driven, assume cross-modal consistency, and rely on static pipelines, which limit their robustness in heterogeneous or unseen urban regions. We propose UrbanAgent, an agentic framework that reframes urban region profiling as a reasoning-driven inference problem. UrbanAgent instantiates an independent agent for each data modality and performs structured multi-agent collaborative reasoning to explicitly address cross-modal inconsistencies rather than absorbing them into a single representation. In addition, UrbanAgent extends indicator prediction as a closed-loop process of active evidence acquisition and iterative reasoning, enabling agents to verify uncertain inferences through tool-augmented retrieval of external knowledge optimized via reinforcement learning. Extensive experiments on global urban datasets for Carbon emissions, GDP, and Population estimation show that UrbanAgent consistently outperforms existing baselines, achieving an average improvement of 8.1% in R2, and exhibiting strong generalization performance in unseen-city settings.

Automatic scientific discovery has long been a goal of computational scholars - a machine that can discover nature's secrets on its own, moving computational systems beyond data-fitting tools toward the generation and refinement of mechanistic models of the universe. Recent advances in symbolic regression (SR) and large-language-model (LLM)-based agents suggest that such systems can recover equations from data, incorporate domain priors, and automate parts of the research workflow. However, most existing approaches either focus on narrow equation-discovery benchmarks or broad end-to-end automation pipelines, while biological systems remain comparatively underexplored. Here, we introduce the MEDA system, an LLM- and SR-powered agentic framework for discovering ordinary-differential-equation (ODE) models of biological and biologically inspired dynamical systems. MEDA retrieves background knowledge, defines admissible variables, generates mechanistic constraints, proposes candidate ODEs, and fits and evaluates them. We evaluate it across canonical model retrieval, reasoning-based extrapolation to unseen variants, and open-ended discovery, with and without experimental data. Across these settings, MEDA recovered the correct state variables, achieved strong structural recovery in retrieval and extrapolation tasks, and produced biologically plausible discovery-oriented models. Ablation and robustness analyses show that knowledge-guided formalization and mechanistic constraints are load-bearing components, whereas numerical fitting alone can preserve trajectory-compatible but biologically incorrect equations.

Although large language models (LLMs) have set benchmarks for zero-shot reasoning, their deployment remains cost-prohibitive and environmentally taxing. Small Language Models (SLMs) offer a sustainable alternative, but prone to errors, on tasks requiring complex, multi-hop logical grounding. We investigate a neuro-symbolic agentic framework to enhance the reasoning capabilities of SLMs, specifically Gemma 3 (1B, 4B) and Llama 3.2 (3B), using the CLUTRR kinship benchmark. Our approach transforms the SLM into a minimalist agent utilizing two specialized tool calls: extract_facts for symbolic triplet extraction and get_hint for expert reasoning via a Relational Graph Convolutional Network (RGCN). We evaluate these models across two configurations, both in an Oracle scenario with ground-truth triplets and a Realistic scenario relying on self-extracted knowledge. Our results reveal that while RGCN-derived hints provide a 1.5 - 2x performance gain over story-only baselines, the system is constrained by the extraction bottleneck and sequential deductive fragility, where early extraction errors compound over multi-hop chains. Furthermore, we identify a "distraction effect" in specific architectures where noisy, self-generated facts degrade performance despite the presence of expert hints. This work characterizes the challenges of symbolic grounding in low-resource agentic systems and provides a roadmap for iterative verification in neuro-symbolic agentic pipelines.

Tool-augmented large language model agents excel at long-horizon tasks, yet they are typically post-trained on fixed toolsets. When tasks demand new tools, these agents struggle to incorporate them effectively, and retraining from scratch is often impractical. We identify the core obstacle in such toolset expansion problem as behavioral inertia: the tendency of agents to fall back on familiar tools and established reasoning patterns despite having access to new ones. We demonstrate that injecting counterfactual anchor contexts at critical decision points can break this inertia, recovering failed trajectories by eliciting suppressed agent capabilities. To scale this insight, we propose ToolAnchor, a framework that uses teacher models to hypothesize these counterfactual contexts, verifies them via student rollouts, and internalizes the successful interventions through agentic post-training. Extensive evaluations across general AI assistant (GAIA), textual search (BrowseComp), and visual search (VDR-Bench) tasks demonstrate that ToolAnchor consistently exhibits competitive performance under expanded toolsets. Our work bridges the gap between static post-training and dynamic adaptation, charting a new path for scalable agentic reinforcement learning.

An agent harness is the external control layer that turns a base LLM into an executable agent by managing context, tools, orchestration, memory, decoding, and output handling. While harness design strongly affects agent behavior, most automatic improvement methods optimize narrower artifacts such as prompts, pipelines, or workflows, and deployed agents usually reuse a single global harness for all cases. We introduce MemoHarness, an adaptive harness optimization framework that learns from its own executions. MemoHarness decomposes the harness into six editable control dimensions, stores per-case diagnoses and distilled global patterns in a dual-layer experience bank, and adapts the learned harness to each test case using retrieved experience without test-time labels, feedback, or additional search. In our evaluation across shell-agent, code-generation, and analytical-reasoning benchmarks, MemoHarness improves over the fixed harnesses we compare against and shows selective transfer to unseen suites and base models. Its additional context can also remain cost-competitive when much of the retrieved experience is cacheable. These results provide evidence that execution experience is a practical substrate for building agent harnesses that are more adaptive than a single static configuration, while leaving broader claims about statistical robustness and component attribution to future work.

We present RAGthoven, our system for SemEval-2026 Task 1 (MWAHAHA), Subtask A (multilingual constrained humor generation in English, Spanish, and Chinese). RAGthoven decomposes creative text generation into a multi-stage large language model (LLM) pipeline (Planner, Best-of-N Writer, Reflector for self-critique, LLM-as-a-judge Judge) grounded in computational humor theory (Benign Violation Theory, Script-based Semantic Theory of Humor) and refined across ten experiments. In our final configuration, we augment the Planner with retrieval-augmented generation (RAG) from a curated joke corpus, seeding generation with diverse joke mechanisms. We also evaluate two agentic variants — ReAct-style sequential tool-calling (Exp09) and autonomous multi-branch orchestration (Exp10) — that expose the same four stages with a deterministic ConstraintAudit checker. Across four frontier models on a held-out 12-instance English sample, neither agentic variant produced outputs we judged superior to the non-agentic pipeline despite substantially higher tool-call budgets. RAGthoven shares Rank 1 with the Gemini 2.5 Flash baseline in all three languages, with overlapping organizer-reported confidence intervals. In Spanish, it leads the baseline by 42 raw Elo points (1182 vs. 1140), while in English (1045 vs. 1081) and Chinese (1045 vs. 1053) the baseline holds the higher raw rating within the same statistical tie. Together, these results suggest language-dependent diminishing returns from elaborate multi-stage prompt engineering and agentic scaffolding once a strong frontier model is in the loop.

While 3D Scene Graphs (3DSGs) provide crucial structured representations for embodied agents, conventional Ahead-of-Time, build-everything-then-filter pipelines conflict with the real-time, low-latency demands of edge platforms, inducing a perceptual saturation effect via severe observation redundancy. To resolve this, we present JITOMA (Just-In-Time On-demand Memory Activation), a closed-loop framework that unifies task reasoning, perception, and memory into a just-in-time growth process. Instead of exhaustively mapping the entire environment, JITOMA leverages a top-down task heatmap at the frontend to filter continuous observations, routing minimal streams to maintain a global foundation of low-cost, dormant anchors. Upon a cognitive query, the backend Large Language Model (LLM) parses the robotic intent to dynamically awaken task-relevant anchors, triggering resource-intensive operations — such as dense node captioning and functional inference — exclusively within the activated local subgraph. To evaluate these dynamic capabilities and study perceptual saturation trade-offs, we introduce JITOMA-Bench, a comprehensive suite for long-horizon multi-tasking and complex multi-step reasoning. Extensive experiments demonstrate that JITOMA substantially reduces active graph size and captioning latency, while maintaining stable processing time under long-horizon task switching.

The capability of a modern AI agent depends not only on its foundation model but also on its harness, which constructs prompts, manages state, invokes tools, and coordinates execution. As models, APIs, environments, and requirements evolve, the harness must be continually modified. Before such a change can be made, a developer or coding agent must identify all code locations that implement the target behavior. This is difficult because production harnesses are large, tightly coupled, and behaviorally distributed, while modification requests describe what the system should do and repositories are organized by files and modules. Code search, repository indexing, and long-context processing ease inspection, but still leave this behavior-to-code mapping to be recovered by hand. Behavior localization is therefore a central bottleneck in harness evolution. We introduce the Harness Handbook, a behavior-centric representation synthesized automatically from a harness codebase via static analysis and LLM-assisted structuring, linking each behavior to its corresponding source. We also introduce Behavior-Guided Progressive Disclosure (BGPD), which guides agents from high-level behaviors to relevant implementation details and verifies candidate locations against the current source. On diverse modification requests from two open-source harnesses, Handbook-Assisted planning improves behavior localization and edit-plan quality while using fewer planner tokens, with the largest gains on scattered sites, rarely executed paths, and cross-module interactions. Evolving complex agentic systems thus depends not only on generating edits, but also on determining where those edits should be made.

Agent memory is a systems problem for long-horizon agents. Practical deployments require retention of task state across extended conversations, recovery of user-specific facts and preferences across sessions, and accumulation of procedural knowledge from prior outcomes. These requirements extend beyond document retrieval: a memory layer must determine which interactions become durable state, how that state is scoped, how it is retrieved under latency constraints, and how it is revised or removed over time. This report studies Oracle Agent Memory as a database-native memory substrate built on Oracle Database. Three themes organize the discussion: memory as a lifecycle spanning ingestion, extraction, consolidation, retrieval, summarization, and revision or removal; a layered architecture that separates an active memory core from a passive memory-store interface with explicit scope control across users, agents, and threads; and evaluation methodology in which downstream task accuracy is complemented by memory-centric measures such as evidence retrieval, recall, latency, and estimated token use. The report summarizes LongMemEval results, reaching 93.8% accuracy, compares Oracle Agent Memory against flat-history baselines, using about 10.7x fewer tokens, and published or reported external baselines where available, and closes with implementation-oriented appendix material covering setup, thread lifecycle, and search semantics.

OpenClaw has emerged as a leading agent framework for complex task automation, yet it faces insufficient cross-platform GUI interaction support and a well-built self-evolution mechanism. These flaws limit its adaptation to diverse device ecosystems and prevent performance improvements through continuous learning from execution experience. To resolve these issues, we propose the Know Deeply, Act Perfectly paradigm for personal assistants, which holds that accumulated user interaction and task-running experience directly improve execution accuracy and efficiency, unifying cognitive comprehension and operational execution. Based on this paradigm, we introduce KnowAct-GUIClaw, a novel Know-Route-Act-Reflect framework designed to address OpenClaw's GUI manipulation deficits and break through its cross-platform and recursive self-improvement constraints. First, the host agent leverages accumulated interaction experience and task-relevant knowledge for long-horizon task decomposition and allocation (Know). Second, a pluggable GUI subagent with an experience-attributable memory system (Know) and self-evolving skill library (Act), enabling seamless cross-platform migration and fast-path integration. Especially, this framework continuously stores user profiles and feedback to improve the accuracy of task decomposition and tool calls. Extensive experiments across Android, iOS, HarmonyOS and Windows show that KnowAct-GUIClaw achieves superior efficiency, accuracy and cross-platform adaptability. Especially, the GUIClaw with open-source Kimi-2.6 models achieves the best performance (64.1%) on the long-horizon MobileWorld benchmark, beating all agentical frameworks and closed-source agentical models, e.g., Seed-2.0-Pro and GPT-5.5. Additionally, the knowledgeable memory and execution skills supported by our framework are transferable across diverse base models, improving by 8.5% with Kimi-2.6.

Learning broad world knowledge directly from raw visual data is a fundamental capability of intelligence. We introduce UniVR, the first investigation into simultaneously learning complex reasoning, fine-grained physical dynamics, and long-term planning from pure visual demonstrations. At its core, UniVR features VR-GRPO, a reinforcement learning paradigm with complementary global and step-level rewards. This approach enforces logical coherence and physical consistency throughout the reasoning process without requiring task-specific heuristics or image-text pairs. To train and evaluate UniVR, we construct VR-X, a large-scale benchmark curated from 16 diverse sources spanning long-horizon manipulation, spatial puzzles, and physical reasoning. It is the first comprehensive suite to assess these heterogeneous capabilities under a purely visual protocol. Remarkably, UniVR achieves up to a 25% improvement on VR-X, and its superior visual reasoning also boosts performance on various multimodal understanding benchmarks. These findings underscore the vast potential of reasoning within visual spaces, with all code, data, and models are open-sourced for further research.

Musculoskeletal diseases are among the leading causes of disability worldwide and create the greatest global need for rehabilitation. Because recovery, remodelling and degeneration often unfold over months to years, musculoskeletal care requires longitudinal management that repeatedly integrates evolving patient evidence, external medical knowledge and stage-specific functional goals. In routine practice, this evidence is fragmented across visits, departments and hospital systems, limiting individualized, evidence-based care. Here we report OrthoPilot, a clinical artificial intelligence system powered by a large language model that integrates hospital data streams with authoritative external knowledge for continuous musculoskeletal management. OrthoPilot autonomously retrieves real-time imaging, laboratory, pathology and order data and converts evolving patient states into evidence-based decisions from admission diagnosis to rehabilitation planning. We established a specialist-validated benchmark from real-world electronic health records spanning 1,000 disease codes. In a reader study across the complete care pathway, OrthoPilot was compared with 81 orthopaedic physicians and surpassed experts with 25 years of experience in diagnostic reasoning, clinical decision-making and management planning. It also outperformed all evaluated intelligent systems across 60 external clinical centres. In a prospective study of 1,870 complex cases, OrthoPilot increased full-chain management success by 10.6%. During an 8-month randomised deployment involving 8,240 inpatients, it increased cumulative cases per bed by 9.7% and improved patient-reported access to health information. These results move clinical AI from predicting isolated events toward executing longitudinal management across complete musculoskeletal care pathways.