ReflectCAP: Detailed Image Captioning with Reflective Memory

Detailed image captioning demands both factual grounding and fine-grained coverage, yet existing methods have struggled to achieve them simultaneously. We address this tension with Reflective Note-Guided Captioning (ReflectCAP), where a multi-agent pipeline analyzes what the target large vision-language model (LVLM) consistently hallucinates and what it systematically overlooks, distilling these patterns into reusable guidelines called Structured Reflection Notes. At inference time, these notes steer the captioning model along both axes -- what to avoid and what to attend to -- yielding detailed captions that jointly improve factuality and coverage. Applying this method to 8 LVLMs spanning the GPT-4.1 family, Qwen series, and InternVL variants, ReflectCAP reaches the Pareto frontier of the trade-off between factuality and coverage, and delivers substantial gains on CapArena-Auto, where generated captions are judged head-to-head against strong reference models. Moreover, ReflectCAP offers a more favorable trade-off between caption quality and compute cost than model scaling or existing multi-agent pipelines, which incur 21--36\% greater overhead. This makes high-quality detailed captioning viable under real-world cost and latency constraints.

How You Ask Matters! Adaptive RAG Robustness to Query Variations

Adaptive Retrieval-Augmented Generation (RAG) promises accuracy and efficiency by dynamically triggering retrieval only when needed and is widely used in practice. However, real-world queries vary in surface form even with the same intent, and their impact on Adaptive RAG remains under-explored. We introduce the first large-scale benchmark of diverse yet semantically identical query variations, combining human-written and model-generated rewrites. Our benchmark facilitates a systematic evaluation of Adaptive RAG robustness by examining its key components across three dimensions: answer quality, computational cost, and retrieval decisions. We discover a critical robustness gap, where small surface-level changes in queries dramatically alter retrieval behavior and accuracy. Although larger models show better performance, robustness does not improve accordingly. These findings reveal that Adaptive RAG methods are highly vulnerable to query variations that preserve identical semantics, exposing a critical robustness challenge.

Beyond Normalization: Rethinking the Partition Function as a Difficulty Scheduler for RLVR

Reward-maximizing RL methods enhance the reasoning performance of LLMs, but often reduce the diversity among outputs. Recent works address this issue by adopting GFlowNets, training LLMs to match a target distribution while jointly learning its partition function. In contrast to prior works that treat this partition function solely as a normalizer, we reinterpret it as a per-prompt expected-reward (i.e., online accuracy) signal, leveraging this unused information to improve sample efficiency. Specifically, we first establish a theoretical relationship between the partition function and per-prompt accuracy estimates. Building on this key insight, we propose Partition Function-Guided RL (PACED-RL), a post-training framework that leverages accuracy estimates to prioritize informative question prompts during training, and further improves sample efficiency through an accuracy estimate error-prioritized replay. Crucially, both components reuse information already produced during GFlowNet training, effectively amortizing the compute overhead into the existing optimization process. Extensive experiments across diverse benchmarks demonstrate strong performance improvements over GRPO and prior GFlowNet approaches, highlighting PACED-RL as a promising direction for a more sample efficient distribution-matching training for LLMs.

CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution

AI agents equipped with tool-calling capabilities are susceptible to Indirect Prompt Injection (IPI) attacks. In this attack scenario, malicious commands hidden within untrusted content trick the agent into performing unauthorized actions. Existing defenses can reduce attack success but often suffer from the over-defense dilemma: they deploy expensive, always-on sanitization regardless of actual threat, thereby degrading utility and latency even in benign scenarios. We revisit IPI through a causal ablation perspective: a successful injection manifests as a dominance shift where the user request no longer provides decisive support for the agent's privileged action, while a particular untrusted segment, such as a retrieved document or tool output, provides disproportionate attributable influence. Based on this signature, we propose CausalArmor, a selective defense framework that (i) computes lightweight, leave-one-out ablation-based attributions at privileged decision points, and (ii) triggers targeted sanitization only when an untrusted segment dominates the user intent. Additionally, CausalArmor employs retroactive Chain-of-Thought masking to prevent the agent from acting on ``poisoned'' reasoning traces. We present a theoretical analysis showing that sanitization based on attribution margins conditionally yields an exponentially small upper bound on the probability of selecting malicious actions. Experiments on AgentDojo and DoomArena demonstrate that CausalArmor matches the security of aggressive defenses while improving explainability and preserving utility and latency of AI agents.

Persona Switch: Mixing Distinct Perspectives in Decoding Time

Role-play prompting is known to steer the behavior of language models by injecting a persona into the prompt, improving their zero-shot reasoning capabilities. However, such improvements are inconsistent across different tasks or instances. This inconsistency suggests that zero-shot and role-play prompting may offer complementary strengths rather than one being universally superior. Building on this insight, we propose Persona Switch, a novel decoding method that dynamically combines the benefits of both prompting strategies. Our method proceeds step-by-step, selecting the better output between zero-shot and role-play prompting at each step by comparing their output confidence, as measured by the logit gap. Experiments with widely-used LLMs demonstrate that Persona Switch consistently outperforms competitive baselines, achieving up to 5.13% accuracy improvement. Furthermore, we show that output confidence serves as an informative measure for selecting the more reliable output.

When Wording Steers the Evaluation: Framing Bias in LLM judges

Large language models (LLMs) are known to produce varying responses depending on prompt phrasing, indicating that subtle guidance in phrasing can steer their answers. However, the impact of this framing bias on LLM-based evaluation, where models are expected to make stable and impartial judgments, remains largely underexplored. Drawing inspiration from the framing effect in psychology, we systematically investigate how deliberate prompt framing skews model judgments across four high-stakes evaluation tasks. We design symmetric prompts using predicate-positive and predicate-negative constructions and demonstrate that such framing induces significant discrepancies in model outputs. Across 14 LLM judges, we observe clear susceptibility to framing, with model families showing distinct tendencies toward agreement or rejection. These findings suggest that framing bias is a structural property of current LLM-based evaluation systems, underscoring the need for framing-aware protocols.

Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluation

While large language models (LLMs) are increasingly used as automatic judges for question answering (QA) and other reference-conditioned evaluation tasks, little is known about their ability to adhere to a provided reference. We identify a critical failure mode of such reference-based LLM QA evaluation: when the provided reference conflicts with the judge model's parametric knowledge, the resulting scores become unreliable, substantially degrading evaluation fidelity. To study this phenomenon systematically, we introduce a controlled swapped-reference QA framework that induces reference-belief conflicts. Specifically, we replace the reference answer with an incorrect entity and construct diverse pairings of original and swapped references with correspondingly aligned candidate answers. Surprisingly, grading reliability drops sharply under swapped references across a broad set of judge models. We empirically show that this vulnerability is driven by judges' over-reliance on parametric knowledge, leading judges to disregard the given reference under conflict. Finally, we find that this failure persists under common prompt-based mitigation strategies, highlighting a fundamental limitation of LLM-as-a-judge evaluation and motivating reference-based protocols that enforce stronger adherence to the provided reference.

Reliability-Aware Adaptive Self-Consistency for Efficient Sampling in LLM Reasoning

Self-Consistency improves reasoning reliability through multi-sample aggregation, but incurs substantial inference cost. Adaptive self-consistency methods mitigate this issue by adjusting the sampling budget; however, they rely on count-based stopping rules that treat all responses equally, often leading to unnecessary sampling. We propose Reliability-Aware Adaptive Self-Consistency (ReASC), which addresses this limitation by reframing adaptive sampling from response counting to evidence sufficiency, leveraging response-level confidence for principled information aggregation. ReASC operates in two stages: a single-sample decision stage that resolves instances confidently answerable from a single response, and a reliability-aware accumulation stage that aggregates responses by jointly leveraging their frequency and confidence. Across five models and four datasets, ReASC consistently achieves the best accuracy-cost trade-off compared to existing baselines, yielding improved inference efficiency across model scales from 3B to 27B parameters. As a concrete example, ReASC reduces inference cost by up to 70\% relative to self-consistency while preserving accuracy on GSM8K using Gemma-3-4B-it.

Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning

Recent advances in Large Language Models (LLMs) - particularly model scaling and test-time techniques - have greatly enhanced the reasoning capabilities of language models at the expense of higher inference costs. To lower inference costs, prior works train router models or deferral mechanisms that allocate easy queries to a small, efficient model, while forwarding harder queries to larger, more expensive models. However, these trained router models often lack robustness under domain shifts and require expensive data synthesis techniques such as Monte Carlo rollouts to obtain sufficient ground-truth routing labels for training. In this work, we propose Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning (STEER), a domain-agnostic framework that performs fine-grained, step-level routing between smaller and larger LLMs without utilizing external models. STEER leverages confidence scores from the smaller model's logits prior to generating a reasoning step, so that the large model is invoked only when necessary. Extensive evaluations using different LLMs on a diverse set of challenging benchmarks across multiple domains such as Mathematical Reasoning, Multi-Hop QA, and Planning tasks indicate that STEER achieves competitive or enhanced accuracy while reducing inference costs (up to +20% accuracy with 48% less FLOPs compared to solely using the larger model on AIME), outperforming baselines that rely on trained external modules. Our results establish model-internal confidence as a robust, domain-agnostic signal for model routing, offering a scalable pathway for efficient LLM deployment.

Black-Box Hallucination Detection via Consistency Under the Uncertain Expression

Despite the great advancement of Language modeling in recent days, Large Language Models (LLMs) such as GPT3 are notorious for generating non-factual responses, so-called "hallucination" problems. Existing methods for detecting and alleviating this hallucination problem require external resources or the internal state of LLMs, such as the output probability of each token. Given the LLM's restricted external API availability and the limited scope of external resources, there is an urgent demand to establish the Black-Box approach as the cornerstone for effective hallucination detection. In this work, we propose a simple black-box hallucination detection metric after the investigation of the behavior of LLMs under expression of uncertainty. Our comprehensive analysis reveals that LLMs generate consistent responses when they present factual responses while non-consistent responses vice versa. Based on the analysis, we propose an efficient black-box hallucination detection metric with the expression of uncertainty. The experiment demonstrates that our metric is more predictive of the factuality in model responses than baselines that use internal knowledge of LLMs.