Yihang Chen
Publications
When Should Active RAG Retrieve? A Budget-Aware Evaluation of Utility, Calibration, and Cost
Active RAG systems decide when to retrieve external knowledge during generation, making them a budget-sensitive case of agentic RAG and self-adaptive retrieval. Yet evaluations often leave the operating point underspecified: two systems may both claim a 50% evidence-usage budget while realizing different held-out usage rates, so higher accuracy can reflect a looser budget rather than a better retrieval policy. We study budget-aware evaluation for Active RAG by recasting active retrieval as utility estimation, where retrieval is valuable only through its marginal correctness change over a no-retrieval answer. This view separates three questions that single-point evaluations conflate: whether trigger scores rank useful retrieval decisions, whether thresholds calibrated on past data meet future budgets, and how trigger-side computation changes deployment cost. We operationalize these questions with exact top-k utility frontiers, deployable threshold frontiers, conservative budget frontiers, harm audits, and cost decompositions. Across knowledge-intensive multi-hop QA datasets and open instruction models, retrieval harm is non-negligible, router rankings change across datasets and budgets, nominal thresholds can miss target usage, and simple uncertainty or retrieval-score baselines often rival learned utility routers. Budget-aware Active RAG evaluations should therefore report frontiers, realized usage, threshold-transfer error, harm rates, and cost decompositions alongside accuracy.
The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy
The growing ability of large language models and vision-language models to jointly interpret and reason over images and text is reshaping medical imaging AI, moving it from task-specific predictors toward autonomous agents that perceive, reason, plan, remember, and act in clinical environments. This survey departs from the capability-first perspective of existing literature and instead begins from clinical deployment, asking what tasks, contamination-resistant benchmarks, and interactive training environments are required before medical agents can be trusted in practice. Medical agents are formalized as sequential decision-making systems under partial observability, together with a three-level autonomy taxonomy spanning assisted, cooperative, and fully autonomous operation. The field is organized along a unified scaling spine consisting of framework scaling, capability scaling, and environment scaling. Within this framework, clinical environment scaling, the integration of tools, data, and clinical gyms, is identified as the most actionable yet underexplored direction for agents operating in PACS, EHR, and FHIR ecosystems. Clinical self-evolution, where agents improve through interaction with their environments rather than parameter scaling alone, is further positioned as a key research frontier, drawing insights from self-improving agents, agent gyms, and test-time compute scaling. Applications across radiology, pathology, ophthalmology, and hospital workflows are examined together with deployment challenges including hallucination, cascading failures, and fairness. By consolidating more than 300 references, with particular emphasis on advances from 2025 to 2026, this survey provides a roadmap toward trustworthy, self-improving medical imaging systems for real clinical practice.
Operational Reframing and Approval-Framed Delegation in Multi-Agent LLM Safety
Safety evaluations of multi-agent LLM systems often compare a direct prompt with a planner-executor pipeline and report the difference as a single "pipeline effect." We argue that this aggregate is difficult to interpret because it conflates three mechanisms: harmful intent may be reframed as plausible operational work, the planner may refuse or transform the request, and the executor may act under delegation prompts implying prior approval. To separate these factors, we introduce a five-condition controlled contrast design, evaluated on 30 synthetic harmful scenarios and an exploratory external validation set from four agent-safety benchmarks using LLM-judged compliance. Our results show that aggregate pipeline safety is not a stable architectural property. Operational reframing is the most portable risk signal, increasing compliance for GPT, Gemini, and DeepSeek across both scenario sets, while Claude is comparatively resistant. Planner behavior can offset this risk mainly through refusal; however, when the planner produces executable steps, the executor may become more compliant than under the direct operational baseline. Approval-framed delegation is sensitive to prompt design, model pairing, and scenario source, and a skeptical executor prompt sharply reduces compliance. Raw-direct model rankings can also mispredict deployed planner-executor behavior. Gemini is safest under raw direct prompts in the primary set yet shows the largest amplification with a Claude planner, rising from 8.9 percent to 38.9 percent compliance. GPTs near-zero aggregate pipeline effect instead hides a reframing increase canceled by planner refusal. These findings suggest that multi-agent safety evaluations should report reframing, planner behavior, delegation framing, and model pairing separately before attributing failures to architecture itself.
Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG
Cited RAG evaluation often treats visible sources as a grounding signal, but a real, topically relevant citation can still under-warrant the attached wording. We study this diagnostic failure as citation laundering: a related source is presented as warrant for an over-strong claim. We introduce FORCEBENCH, a contrastive stress test for evidence-force calibration. Each item holds a cited passage fixed and pairs an evidence-calibrated claim with a localized force-raised variant across five operational axes: relation, modality, scope, temporal validity, and numeric specificity. A calibrated evaluator should score the evidence-calibrated claim higher. Headline experiments use a fixed, locality-filtered 198-pair evaluation set. A citation-presence sanity check is uninformative by design; token and entity overlap still violate monotonicity on 32.8--36.4% of pairs. Across four reported model judges, standard generic support prompting is insufficient for this force-calibration stress test (aggregate MVR 47.2%), while explicit warrant-strength prompting lowers MVR to 24.5% but remains imperfect. We release the benchmark, prompts, outputs, and plug-in pipeline so citation evaluators can report monotonicity violation rate and force sensitivity alongside conventional support metrics.
Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict
The Context-Compliance Regime in Retrieval-Augmented Generation (RAG) occurs when retrieved context dominates the final answer even when it conflicts with the model's parametric knowledge. Accuracy alone does not reveal how retrieved context causally shapes answers under such conflict. We introduce Context-Driven Decomposition (CDD), a belief-decomposition probe that operates at inference time and serves as an intervention mechanism for controlled retrieval conflict. Across Epi-Scale stress tests, TruthfulQA misconception injection, and cross- model reruns, CDD exposes three patterns. P1: context compliance is measurable in an upper-bound adversarial setting, where Standard RAG reaches 15.0% accuracy on TruthfulQA misconception injection (N=500). P2: adversarial accuracy gains transfer across model families: CDD improves accuracy on Gemini-2.5-Flash and on Claude Haiku/Sonnet/Opus, but rationale-answer causal coupling does not transfer. CDD reaches 64.1% mistake- injection causal sensitivity on Gemini-2.5-Flash, while sensitivities for all three Claude variants fall in the [-3%, +7%] range, suggesting that the Claude-side accuracy gains operate through a mechanism distinct from the explicit conflict-resolution trace. P3: explicit conflict decomposition improves robustness under temporal drift and noisy distractors, with CDD reaching 71.3% on temporal shifts and 69.9% on distractor evidence on the full Epi-Scale adversarial benchmark. These three patterns identify context-compliance as a structural axis along which standard RAG can be probed and intervened on, distinct from retrieval-quality or single-method robustness questions, and motivate releasing Epi-Scale for systematic study across model families and retrieval pipelines.
Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction
Agentic web search increasingly faces two distinct demands: deep reasoning over a single target, and structured aggregation across many entities and heterogeneous sources. Current systems struggle on both fronts. Breadth-oriented tasks demand schema-aligned outputs with wide coverage and cross-entity consistency, while depth-oriented tasks require coherent reasoning over long, branching search trajectories. We introduce \textbf{Web2BigTable}, a multi-agent framework for web-to-table search that supports both regimes. Web2BigTable adopts a bi-level architecture in which an upper-level orchestrator decomposes the task into sub-problems and lower-level worker agents solve them in parallel. Through a closed-loop run--verify--reflect process, the framework jointly improves decomposition and execution over time via persistent, human-readable external memory, with self-evolving updates to each single-agent. During execution, workers coordinate through a shared workspace that makes partial findings visible, allowing them to reduce redundant exploration, reconcile conflicting evidence, and adapt to emerging coverage gaps. Web2BigTable sets a new state of the art on WideSearch, reaching an Avg@4 Success Rate of \textbf{38.50} ($7.5\times$ the second best at 5.10), Row F1 of \textbf{63.53} (+25.03 over the second best), and Item F1 of \textbf{80.12} (+14.42 over the second best). It also generalises to depth-oriented search on XBench-DeepSearch, achieving 73.0 accuracy. Code is available at https://github.com/web2bigtable/web2bigtable.
EE-MCP: Self-Evolving MCP-GUI Agents via Automated Environment Generation and Experience Learning
Computer-use agents that combine GUI interaction with structured API calls via the Model Context Protocol (MCP) show promise for automating software tasks. However, existing approaches lack a principled understanding of how agents should balance these two modalities and how to enable iterative self-improvement across diverse applications. We formulate MCP-GUI interplay as a unified hybrid policy learning problem where the agent learns when each modality provides complementary advantages, and show that distillation and experience augmentation target fundamentally different failure modes - requiring application-aware mechanism selection. Built on this formulation, we propose a self-evolving framework with a fully automatic pipeline that orchestrates automatic environment generation and validation, trajectory collection, gap-driven task synthesis, and quality-filtered training - all without manual intervention. A key innovation is our experience bank, which accumulates LLM-learned rules from trajectory comparison, enabling inference-time improvement without fine-tuning. Systematic \textbf{cross-application analysis} across three desktop applications reveals that the optimal strategy depends on MCP-GUI composition: distillation achieves 77.8\% pass rate on MCP-dominant tasks (+17.8pp), while the experience bank excels on GUI-intensive tasks (+10.0pp).
Memento-Skills: Let Agents Design Agents
We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing agent}: it autonomously constructs, adapts, and improves task-specific agents through experience. The system is built on a memory-based reinforcement learning framework with \emph{stateful prompts}, where reusable skills (stored as structured markdown files) serve as persistent, evolving memory. These skills encode both behaviour and context, enabling the agent to carry forward knowledge across interactions. Starting from simple elementary skills (like Web search and terminal operations), the agent continually improves via the \emph{Read--Write Reflective Learning} mechanism introduced in \emph{Memento~2}~\cite{wang2025memento2}. In the \emph{read} phase, a behaviour-trainable skill router selects the most relevant skill conditioned on the current stateful prompt; in the \emph{write} phase, the agent updates and expands its skill library based on new experience. This closed-loop design enables \emph{continual learning without updating LLM parameters}, as all adaptation is realised through the evolution of externalised skills and prompts. Unlike prior approaches that rely on human-designed agents, Memento-Skills enables a generalist agent to \emph{design agents end-to-end} for new tasks. Through iterative skill generation and refinement, the system progressively improves its own capabilities. Experiments on the \emph{General AI Assistants} benchmark and \emph{Humanity's Last Exam} demonstrate sustained gains, achieving 26.2\% and 116.2\% relative improvements in overall accuracy, respectively. Code is available at https://github.com/Memento-Teams/Memento-Skills.
TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking
Test-time evolution of agent memory serves as a pivotal paradigm for achieving AGI by bolstering complex reasoning through experience accumulation. However, even during benign task evolution, agent safety alignment remains vulnerable-a phenomenon known as Agent Memory Misevolution. To evaluate this phenomenon, we construct the Trust-Memevo benchmark to assess multi-dimensional trustworthiness during benign task evolution, revealing an overall decline in trustworthiness across various task domains and evaluation settings. To address this issue, we propose TAME, a dual-memory evolutionary framework that separately evolves executor memory to improve task performance by distilling generalizable methodologies, and evaluator memory to refine assessments of both safety and task utility based on historical feedback. Through a closed loop of memory filtering, draft generation, trustworthy refinement, execution, and dual-track memory updating, TAME preserves trustworthiness without sacrificing utility. Experiments demonstrate that TAME mitigates misevolution, achieving a joint improvement in both trustworthiness and task performance.