Chat
-
RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement
2026-09-30 05:54:34Wenyi Wu, Minghao Fu, Jieyu You, Kun Zhou, Siqi Liu, Aayush Salvi, Yiheng Lin, Ce Zhang, Xiaohan Lan, Jiahui Zhu, Yujie Zhong, Qi She, Biwei HuangAbstract
Recent advances in large language models have made automatic game generation increasingly feasible, yet reliably improving generated games beyond a playable version remains challenging. Naive iterative refinement can easily overfit a small set of test cases, producing fragile games with unresolved bugs, missing behaviors, and poor generalization to broader player interactions. We introduce RSIGame, an autonomous agentic game development framework with recursive self-improvement. RSIGame organizes development into complementary local and global loops. Concretely, a local explore-diagnose-improve loop broadly explores the executable game, diagnoses and prioritizes discovered issues, and performs evidence-grounded revision, where an evolving checklist continually accumulates new testing and improvement guidance. A global loop tracks overall quality, preserves the best checkpoint, and detects saturation or regression over long-horizon development. Beyond test-time improvement, RSIGame further internalizes successful development experience into the generator through training. Across 140 GameCraft-Bench tasks, two game engines, and five generators, RSIGame consistently improves game quality under matched development budgets. Notably, experience internalization enables Qwen3.8-27B to reach 61.38 on Godot and 58.53 on Phaser, exceeding GPT-5.5 one-shot scores while reducing Qwen's generation tokens by 11 times.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39045
PDF
-
A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore Review
2026-09-30 05:32:26Chenguang Wang, Ming Li, Chengrui Fan, Jianpeng Chen, Han Chen, Tianyi Zhou, Dawei ZhouAbstract
AI reviewers can assign different judgments to manuscripts that report the same science in different wording, potentially rewarding rhetorical optimization over scientific improvement. We formulate Rhetorical Robustness as the joint requirement of stability across content-preserving rewrites and discrimination across papers. We introduce RobustReview, a controlled full-manuscript benchmark with 1,260 manuscript versions, and evaluate 30 reviewer configurations. The benchmark reveals false robustness, where low rewrite sensitivity coincides with score collapse across papers, and shows that human alignment and rhetorical robustness rank reviewers differently. Moreover, the evaluated content-focused prompting protocol does not consistently improve robustness across backbones. Motivated by these findings, we introduce SciCore, a dual-branch reviewer that averages a full-manuscript judgment with a judgment based on an extracted, structured science core. This design combines manuscript-level assessment with a content-normalized view intended to reduce rhetorical sensitivity. In our primary GPT-5.5 comparison, SciCore achieves a leading joint stability-discrimination profile among the benchmarked reviewers while maintaining competitive human alignment. These results identify rhetorical robustness as a distinct evaluation target and demonstrate the potential of science-core review to improve it.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39027
PDF
-
Real-time Chatbot Romance Scam Detection in Stage Classification
2026-09-30 04:19:18Yi-cheng Liu, Guan-ru Lai, Yi-cheng Lai, Lyn Chao-ling ChenAbstract
Romance scam has become a serious problem via social media, and the improvement of artificial intelligence enable to fake identify easily. In the study, a chatbot has developed to detect romance scam in real-time through Line Messaging API. Using the seven stage theories in the social science field, the stages of romance scam can be detected through large language model. In addition, once a romance scam is detected, the chatbot provides explanations of the stage and prevention advices through large language model. The contribution of the work provides a practical application, and can be used in real scenario for reducing the risk of romance scam.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20631
PDF
-
DrivingBench: Can Vision-Language Models Drive a Toyota Corolla?
2026-09-30 04:16:59Aditya Ramabadran, Simon Mahns, Tobias GesslerAbstract
Frontier models excel at many digital benchmarks, yet their ability to drive a real car, an everyday human skill, remains largely untested. We present DrivingBench, to our knowledge the first benchmark where general-purpose vision-language models must drive a real car. Through three tools, the models see camera frames from a Toyota Corolla and directly command its steering and velocity around a parking lot cone course at low speeds. The car may continue moving while the model thinks and new commands replace the currently running one, so inference latency is part of the task, testing the models' abilities to observe, act, monitor, recover, and complete a long-horizon objective under such constraints. We benchmark GPT-6 Astra, Claude Fable 5.1, GPT-5.6 Sol, and Grok 4.6 in vendor-native harnesses (Codex, Claude Code, Cursor) with up to three attempts each in one conversation; Astra is the only model to finish the course, on its second attempt, with no other attempt passing 50% of the course. Two of the four models improved materially across attempts with retained context. We also detail the design principles behind our action interface, and show how the tool output format and the framing of the task combined to determine whether models would drive at all or refuse. We release our harness, prompts, course map, and traces with video and telemetry for reproducibility.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38948
PDF
-
SceneJail: Exploiting Video Scenario Context to Jailbreak Multimodal LLMs
2026-09-30 03:47:17Wenyu Chen, Li Wang, Chuanchao Zang, Xiangtao Meng, Xinyu Gao, Jianing Wang, Zheng Li, Shanqing GuoAbstract
Video Multimodal Large Language Models (Video-MLLMs) support reasoning over video inputs, yet remain vulnerable to jailbreak attacks that elicit policy-violating responses. Existing video jailbreaks primarily manipulate how harmful queries are visually presented, thereby treating video merely as a carrier. Consequently, the surrounding video scenario remains unexplored as a contextual attack surface. In this paper, we show that the same harmful query can elicit different safety responses when placed in different video scenarios. To systematically exploit this vulnerability, we propose SceneJail, an adaptive black-box jailbreak framework with two coordinated components. Adaptive Scenario Construction dynamically searches for a surrounding scenario that is contextually compatible with the harmful query. Scenario-aware Prompt Search uses black-box response feedback to search for textual guidance tailored to the selected scenario. Extensive evaluations on the HADES and SafeBench datasets across eight Video-MLLMs, including two proprietary models, GPT-4.1 and Gemini3.5-Flash, demonstrate the effectiveness of SceneJail. SceneJail-F, which presents the complete query persistently, achieves average attack success rates (ASR) up to 91.5%, outperforming the strongest baselines by 29.1 percentage points. Furthermore, SceneJail-S, which distributes the query across successive frames, remains highly robust against current defenses, retaining a 72.3% ASR even under strict image filtering.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38899
PDF
-
Consistent Plan-Act for Long-Horizon Agentic Tasks
2026-09-30 03:38:49Heng-Zhuang Li, Yi-Kai Zhang, Yu Wang, Yueqing Sun, Jiayuan Zhang, Qi Gu, Han-Jia YeAbstract
Long-horizon agentic tasks demand strong reasoning and efficient execution across successive interactions with dynamic environments. A common approach decouples high-level planning from low-level execution through separate planner and actor roles. To investigate coordination failures in these tasks, we prompt both agents for structured state assertions and compare their reports programmatically to detect explicit contradictions. Our analyses reveal systematic disagreement about the same task-relevant state facts, a phenomenon we term planner-actor state mismatch. We further find that providing agents with task-relevant state information reduces mismatch and improves coordination and task performance. Based on the systematic analysis of the state mismatch, we propose Consistent Plan-Act (ConPAct), which feeds detected contradictions back to both agents to form consistent state interpretations and fine-tunes them on curated consistent interactions for better coordination. ConPAct improves performance across various environments and model configurations, e.g., increasing MiniGrid success rate from 38.6% to 54.4% with GPT-5.6-sol/terra as planner and actor respectively, demonstrating that state consistency can guide both inference-time correction and coordination training.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38891
PDF
-
Optimal Design for Active Preference Learning with Biased LLM Judges
2026-09-30 03:17:21Zhongman Du, Huiming Zhang, Haodong Zhu, Baochang ZhangAbstract
Learning from human preferences is central to large language model (LLM) alignment, but human preference annotation is costly. Active preference learning reduces this cost by selecting informative comparisons, and LLM judges can provide additional scalable feedback. However, the preferences of the judges may deviate from those of the target human population. Even after calibration on trusted reference data, active acquisition can shift the comparison distribution and expose residual judge bias. We therefore incorporate judge deviations into the acquisition design rather than relying on a separate calibration stage. Under joint estimation, comparisons that appear highly informative about the reward may also reflect judge bias and therefore provide less information about human preferences. To address this issue, we propose Nuisance-Adjusted Optimal Design (NAOD), a comparison-selection strategy that prioritizes policy-relevant target information after nuisance adjustment and uses the Frank-Wolfe algorithm for optimization. Theoretically, we establish a sharp conditional local asymptotic minimax lower bound on policy risk and construct an estimator that attains it. We further characterize the finite-sample cost of learning the nuisance representation and show that representation error can reverse an oracle design advantage. Finally, we validate these predictions experimentally and evaluate NAOD on Chatbot Arena data across 17 judges, 15 budget configurations, and 15 random cluster-level splits. NAOD reduces the mean regret of proxy policy by 29.1% relative to a matched target-information design, outperforms existing methods, and improves human-preference prediction on held-out data.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38860
PDF
-
BARRAC: Adaptation of an English Aspect-based Sentiment Analysis Approach for Classification Tasks in Arabic Dialects
2026-09-30 02:46:08Ali Almutairi, Gelareh Mohammadi, Imran Razzak, Aditya JoshiAbstract
With the rapid growth of Arabic NLP, several models, datasets and benchmarks have been reported. This paper asks whether approaches developed for majority languages like English can be adapted to Arabic tasks. We adapt an English aspect-based sentiment analysis framework to Arabic classification tasks and present the adaptation as BARRAC: Brainstorming Alignment and Replaced Representation learning for ArabiC tasks. BARRAC replaces consumer-review attribute pools with Arabic linguistic devices and markers for dialectal sentiment, sarcasm, and dialect identification, and replaces noisy self-training with two-stage training. Evaluated on five Arabic dialect datasets, BARRAC achieves a mean macro-F1 of 63.93\%, outperforming the best few-label SOTA by 3\%, and outperforming GPT-4o on four out of five tasks. Error analysis provides insights into remaining challenges. These results demonstrate that adapting task-specific approaches is a promising direction for Arabic NLP alongside adapting models, datasets and benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38820
PDF
-
StateTree: Enhancing Long-Term Dialogue Reasoning via Reinforcement Learning
2026-09-30 02:38:52Naen Xu, Wanqing Cui, Yibo Hu, Shixin Hong, Hengyu An, Meiguang Jin, Junfeng Ma, Tianyu DuAbstract
Large language models deployed as personalized assistants must reason over long, evolving interaction histories. However, in long-term dialogue reasoning, relevant evidence is scattered across sessions, preferences may be revised over time, and standard long-context training fails to address these challenges under data scarcity and prohibitive computational costs. We propose StateTree, a data-driven RL method that constructs a challenging auxiliary task from scarce dialogues with verifiable ground truth. StateTree augments multi-session dialogues with a tree-structured path-tracing task: key-value records are embedded across sessions to form a binary tree. Solving the task requires the model to traverse from root to leaf by retrieving records across sessions and comparing timestamps to resolve branches, then recover the hidden target question among distractor leaves. We apply curriculum RL training progressively increasing tree depth and introduce a compositional variant whose edges carry step-level reasoning fragments, training the model to compose partial cues into coherent queries. Trained on 10K-token contexts, StateTree generalizes to 128K tokens without full-length RL costs and exhibits capabilities including cross-session retrieval, temporal reasoning, knowledge update, and compositional multi-hop reasoning. StateTree outperforms both SFT and RL-based baselines while preserving short-context general reasoning. StateTree-7B achieves gains up to +23.60% on LongMemEval (128k), and StateTree-14B reaches 59.00% accuracy on LongMemEval, surpassing QwenLong-L1-32B (45.20%).
Abstract (translated)
URL
https://arxiv.org/abs/2609.38809
PDF
-
Self-Evolving Algorithm-Design Agents: Escaping In-Context Evolutionary Stagnation via Population-Curated Policy Optimization
2026-09-30 01:43:45Chen Lu, Ke Xue, Siyuan Xu, Mingxuan Yuan, Chao QianAbstract
Large language models are increasingly participating in complex real-world tasks in the form of algorithm-design agents, designing and refining algorithms. Many successful algorithm-design agents adopt pure in-context evolutionary frameworks, but they may quickly plateau in domains that require specialized knowledge. Parametric adaptation offers a way to internalize specialized knowledge, but conventional training requires abundant domain-specific corpora while high-quality algorithms are scarce in complex algorithm-design scenarios. In this paper, we propose sample-efficient parametric self-evolution where agents can explore and learn from self-generated algorithms. First, we characterize in-context evolutionary stagnation and analytically propose the Improvement Chain proposition, showing how learning successive self-generated algorithms can locally increase the likelihood of neighboring algorithms. Motivated by this local-transfer perspective, we further propose Population-Curated Policy Optimization (PCPO) to utilize a global population and a hybrid policy update scheme for retaining and reusing high-quality, diverse self-generated algorithms, shifting the policy towards stronger algorithms. In the task of learning rate schedule design for global placement in electronic design automation, trained only on 4 chip cases, PCPO outperforms the state-of-the-art in-context evolutionary methods (e.g., OpenEvolve and ShinkaEvolve) on average across 16 chip cases. With an 8B-size base model, PCPO achieves competitive performance compared to frontier closed-source models such as GPT-5.5. PCPO also reduces inference-time token cost by internalizing grounded domain knowledge and prompt distillation. Moreover, PCPO achieves significant speedups on four GPU kernel designs, with an average of 8.27$\times$ speedup against the PyTorch Eager baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38757
PDF
-
AIfred: Augmented Learning through Functional Robotic Embodiment at the Desk
2026-09-30 01:20:13Gregorio Orlando, Milan Groshev, Eduardo Castell\'o FerrerAbstract
Desk-based learning and creative activities benefit from handwritten engagement. However, current generative AI tools deliver guidance through a separate screen, creating a gap between where users think and where assistance appears. To address this, in this work we design AIfred, a desk-based robotic arm with a projector mounted at the end-effector that places AI-generated guidance alongside handwritten work. AIfred combines workspace perception, context-aware content generation, and robot-mediated projection to support math assignments, image generation, and drawing tasks. In a user study (n = 36), we compared AIfred against ChatGPT (GPT-5.6 Luna) running on a laptop. Both tools performed comparably while assistance was available during the math assignment (6.7 vs. 7.3/10, p = .41), but AIfred improved short-term learning transfer by 60% once assistance was withdrawn (7.0 vs. 4.4/10, p = .003). In addition, independent art and design professors ranked drawings produced with AIfred better in 33 of 36 cases. Our findings indicate that spatially co-located AI assistance benefits tasks whose guidance shares a spatial frame with the work.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38737
PDF
-
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
2026-09-30 00:54:09Fang Wu, Da Xing, Yanjie Huang, Junxi Wang, Ji Wang, Hejia Geng, Guancheng Wan, Bowen Zuo, Xiaomin Li, Shixiang Tang, Xinyu Xiang, Zehong Wang, Shiyi Du, Peng Xia, Shuangjia Zheng, Yining Hong, Li Erran Li, Jure Leskovec, Yejin ChoiAbstract
Modern multimodal models bring generation and understanding into a single unified system, which enables them to provide and learn from their own feedback. Motivated by this unified capacity, we introduce UniEvo-VL, a self-evolving framework for multimodal models to learn from this constructive self-correction feedback during test-time compute. Instead of relying on a separate, often larger, teacher, we leverage their self-critiques as privileged information and ask a single multimodal model to act as both teacher and student with different contexts. The student only sees the vanilla question, while the teacher conditions on the privileged critique. Then training minimizes the per-state divergence between their denoising diffusion distributions over the student's own sampling trajectories. Experiments demonstrate that UniEvo-VL improves the image generation capabilities of multimodal models, while maintaining their sensitivity to additional reflection information. Specifically, we build on top of the open-source Qwen-image-2512 and observe a significant performance gain from 0.747 to 0.808 on GenEval and from 32.97 to 35.53 on GenEval2 Soft-TIFA. Moreover, attempts with more powerful external critics (e.g., GPT5.6-Luna) show that multimodal models with strong judge capabilities can anticipate a higher self-evolving ceiling. Last but not least, mixed text-rendering outcomes show that our self-improvements may not be uniform across different tasks. Our study aims to shed light on the current hot recursive self-improvement research line to enhance the user experience when using multimodal models without external supervision or guidance.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38721
PDF
-
When Scientific Contradictions Are Lost in Translation
2026-09-29 22:22:54Tal Zeevi, Trey W. Jensen, Maxwell StromeAbstract
Two scientific findings can disagree without contradicting each other. Determining whether they conflict requires knowing whether they describe comparable measurements. We study how language models behave at this decision point. In a controlled task, we generate an unsatisfiable XOR constraint system and translate its constraints into scientific reports from different laboratories. One assignment satisfies more constraints, while another satisfies fewer but better matches expected biology. This creates a simple dilemma: does the model choose the assignment that best fits the constraints, or the one that better matches biological expectations? When the constraints are stated directly, GPT-5.6 Sol and Claude Opus 5 recover the best-supported assignment in 90% and 96% of cases, respectively. In scientific prose, however, the models behave differently. Claude Opus 5 often prefers the biologically expected assignment. Removing that biological preference increases recovery of the better-supported assignment from 27% to 79% (p<.001); recovery reaches 92% when the same Biology-favored record is accompanied by a formalization request and an explicit paired-design cue (p<.001). GPT-5.6 Sol is less sensitive, with neither corresponding change reaching statistical significance. These results suggest that reliable scientific verification depends not only on formal reasoning, but also on how models decide which findings should be compared and what relations they imply.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38621
PDF
-
StreamDecisionBench: Evaluating Decisions in Force on Evolving Language Streams
2026-09-29 22:15:49Jhen-Ke Lin, Chung Chun WangAbstract
As natural language drives more applications, language models increasingly run inside programs as decision components: the program sends them the current state and acts on the returned decision until a newer one arrives. When evidence changes during inference, a decision correct for its own state can stay in force after that state has passed, as when a call recorder keeps running after a customer starts reading out a card number; untimed (offline) accuracy counts such an error as correct. We introduce StreamDecisionBench (SDB), which evaluates the decision in force at every instant and attributes every erroneous instant to judgment, latency or both. Its scenarios stream evidence in four application families, with reference decisions computed from public rules by executable code. We summarize in-force accuracy across update intervals of 1-5 s by its normalized area under the curve on a logarithmic time axis, giving equal weight to equal multiplicative ranges. Across six settings of four hosted models, this score stays within 2.9 points of the scenario-wise product of untimed accuracy and an oracle's integrated timing score. Reasoning improves judgment, but at low effort latency costs Luna and Terra, two GPT models we also evaluate without reasoning, 38.8 and 42.8 points relative to untimed accuracy; a faster component with weaker judgment attains a similar integrated score to Terra without reasoning. The aggregate and family curves show where these tradeoffs change, making the evaluation's time-scale dependence visible.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38612
PDF
-
Systematically Exploring the Capabilities of GPT-6 Astra as Embodied Policies
2026-09-29 20:54:47Galbot Team, Xuchuan Chen, Xiaoqian Cheng, Yu Deng, Lihe Ding, Shaocong Dong, Xiangjun Gao, Haozhe Jia, Zekai Li, Zhoujian Li, Yunrui Lian, Sikai Liang, Chenghuai Lin, Dairu Liu, Jiahang Liu, Qingtao Liu, Yuxuan Ma, Zekun Qi, Jiayi Su, He Wang, Ruochen Xu, Tianyu Xu, Xudong Xu, Zhe Xu, Mi Yan, Siming Yan, Li Yi, Ruixi Yu, Jinlu Zhang, Yintianrun Zhang, Zhikai Zhang, Zhizheng Zhang, Yixin Zheng, Weiyi ZhuAbstract
GPT-6 Astra exhibits a remarkable ability to generate numerical robot actions, extending its role beyond high-level planning. To assess Astra's capabilities as general-purpose embodied policies, we conduct comprehensive evaluations across six domains, examining direct control, cooperation with learned policies, and feedback-driven adaptation. In gripper manipulation, Astra can correct task targets and prepare contact conditions for subsequent policy execution; hybrid control with {\pi}0.5 achieves 48% success on the evaluated RoboDojo subset. In dexterous manipulation, hybrid control achieves 50% success in ten experience-guided DexJoCo trials, while direct in-hand control struggles to coordinate finger contacts. In mobile manipulation, hybrid control reaches 38.7% success on the evaluated RoboCasa365. In navigation, Astra leads our local comparisons, reaching 92% success on RxR instruction following and 82% on HM3D object search, although search incurs substantial detours. In locomotion, dense motion-reference generation remains unreliable: none of five sequential attempts on a single obstacle course reaches the goal, despite improvements in stability and forward progress. In humanoid loco-manipulation, Astra exceeds baseline methods on 13 of 30 HumanoidBench tasks with pretrained whole-body controllers. These findings reveal a gap between useful task decisions and reliable physical control. Inference latency further constrains practical control: across 50 RoboDojo instances per condition, policy-assisted and direct control consume 624.8 million and 1.132 billion tokens. A 30-second locomotion run requires 250 model calls averaging 39.86 seconds each, with physics paused during inference.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38537
PDF
-
VAmoS Part Deux: Harder, More Realistic Voice-Agent Simulation
2026-09-29 20:33:57Joshua Meyer, Sahar Shayegan, Ritiz Tambi, Ali Khan, Sun Kim, Victor Shih, Mehdi Jamei, Andi PartoviAbstract
Voice agents in production must handle several requests, background speech, and customers who lose patience. We introduce VAmoS Energy, a benchmark that combines these challenges in 100 calls about utility billing and payment assistance. Each caller makes two to four requests. The agent has sixteen tools backed by a stateful Stripe billing twin and the Apache Fineract loan engine, with account access blocked until caller verification succeeds. The tasks use public household electricity data and a policy based on Pennsylvania's residential billing rules. An LLM-as-a-verifier checks the agent's actions and spoken figures against explicit requirements. On a calibration run, it agrees with a code verifier on 99.1% of checks. Across fourteen voice stacks and three repeats per task, completion ranges from 17.3% to 44.7%. Grok Voice leads, and Gemini 3.8 Live and GPT-Live follow at about the same cost per call. Background television reduces pooled completion from 38.7% to 8.6%. The simulated caller often accepts an incorrect result because it hears the agent's words but cannot inspect its actions. These findings show why voice agents need evaluation across the whole call, including what they say, what they change, and how they handle competing speech.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38512
PDF
-
Voices as Handles: Reasoning about Speaker Identity with Frozen Text LLMs
2026-09-29 20:25:40Runqiu Xu, Zhisheng Zheng, David HarwathAbstract
Multi-user voice agents must track who said what across dialogue sessions. Text LLMs are attractive backbones for such agents, but transcripts alone do not expose acoustic speaker identity, leaving the model without a persistent reference for linking information to speakers across sessions. We address this gap by introducing Speaker Handles, soft-token representations that expose acoustic speaker identity to a frozen text LLM for cross-session speaker-dependent reasoning. A three-stage curriculum trains a lightweight projector, with fewer than 0.1% of the backbone's parameters, to map speaker embeddings into these handles. Establishing whether the resulting handles truly support cross-session speaker-dependent reasoning is challenging with existing benchmarks because textual cues can partially reveal fact ownership. We therefore present SpeakerBind, a controlled shared-agent benchmark in which overlapping facts across users require correct cross-session speaker attribution. Speaker Handles achieve 97.40-98.36% accuracy on VoxCeleb1 and 70.40% on SpeakerBind, close to the 71.88% topline. These results show that the proposed Speaker Handles provide an efficient way to integrate acoustic speaker identity into frozen text LLMs for speaker-content reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38501
PDF
-
Role-guided Speaker Deletion Verification in Clinical Psychiatry Speech Recordings with Audio Language Models
2026-09-29 20:20:24Joseph T Colonel, Daniel Katzman, Kelsey Kirker, Adam N Davidson, Shalaila S Haas, Cheryl Corcoran, Ren\'{e} S Kahn, Guillermo Checci, Baihan LinAbstract
Clinical research in psychiatry increasingly relies on large scale collection of spoken language data to identify acoustic and linguistic biomarkers. Yet evolving consent and protocol requirements can oblige investigators to remove a designated speaker from multi-speaker recordings and to verify said removal at a scale infeasible for manual review of entire corpora. We study this verification problem for role-driven dyadic clinical dialogue in psychiatry and investigate it with two parallel, symmetric pipelines: confirming that clinician speech has been removed from psychiatric interview recordings, and confirming that patient speech has been removed from the same recordings. Each pipeline redacts the raw audio for its target role and then scans the surviving output with audio-language and large-language models to identify missed deletions. We evaluate this approach on a corpus of 48 dyadic recordings drawn from psychiatry settings, testing four open-weight models in an inference-only setting: Gemma-4-12B, Gemma-4-31B, Nemotron-3-Nano, and Nemotron-3-Nano-Omni. A disjunctive OR ensemble over fourteen model-view configurations had a combined F1 of 0.478 (precision 0.330, recall 0.870), an improvement over individual model estimates driven by recall gains that point to substantial complementarity across models and context views.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38491
PDF
-
KlinikeBench: Evaluating Language Models Beyond Diagnostic Accuracy
2026-09-29 20:08:21Xueting Fang, Zehui Li, Yang Yang, Camilla Giovino, Shubh K. Patel, Shailly Prajapati, Vallijah Subasri, Caihua ShanAbstract
Most clinical benchmarks evaluate language models (LMs) on diagnosis using complete case descriptions. In clinical practice, however, patients present information in different ways, and clinicians must obtain relevant history and determine which examinations are needed before reaching a diagnosis. Diagnostic accuracy alone therefore cannot establish whether an agent gathered essential information or conducted an appropriate clinical assessment. Furthermore, existing benchmarks lack professional clinicians' verification. To address this gap, we introduce KlinikeBench, a benchmark of 333 clinician-authored tasks, each providing an isolated sandbox environment with a virtual patient, clinical tools, and task-specific success criteria. More than 35 clinicians contributed to case authoring and benchmark evaluation. In an empirical study, clinicians gave simulated dialogues higher mean quality ratings than reference conversations, which is adapted from real conversation. In each task, an LM has a fixed budget of turns to communicate with the patient, ask about relevant history, request examinations, follow action constraints, and record a final diagnosis. We score these steps separately as well as together. Across 31 models and seven model families, the best-performing models (e.g., GPT-6-astra and Claude Opus 5) succeed on less than 30% of tasks, even though their diagnosis accuracy reaches 90.7%. Some models benefit from talking with the patient; others diagnose well from a complete chart but perform much worse in conversation. Overall, KlinikeBench provides a testbed for evaluating the full clinical encounter and reveals a substantial gap between diagnostic accuracy and performance in interactive clinical assessment.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38480
PDF
-
Reach Into The CHOIR: Free-List Elicitation Uncovers Distinct Model Voices in LLM Ensembles
Abstract
Open-ended LLM homogeneity can create false plurality when several systems appear to offer independent perspectives while returning the same familiar default. Single-pass answers obscure the distinction between agreement produced by a tightly constrained answer space, prompt-vocabulary echo, and broader answer spaces with stable alternatives beneath the surface. We introduce CHOIR (Collective Hierarchically-Ordered Inquiry Responses), a framework that adapts free-list elicitation from cognitive anthropology to LLM ensembles. CHOIR repeatedly elicits ranked lists, clusters items into prompt-level concepts, and measures concept salience across models, prompt variants, and persona conditions. We evaluate CHOIR on Infinity-Chat 100, an external prompt bank from recent work on open-ended model homogeneity, and on a 27-question targeted diagnostic bank designed to isolate mechanism-level contrasts. On Infinity-Chat 100, CHOIR reproduces high surface agreement (93/100 prompts above chance) while separating narrow prompts from broad prompts with recoverable depth. Across targeted probes and the external prompt bank, base-model identity remains the strongest recoverable signature, and persona prompts shift surfaced concepts within base-model signatures. A source-blind ranking module prioritises rare-but-stable candidates for later inspection. CHOIR turns open-ended homogeneity into a diagnostic measurement problem by asking where models converge, why they converge, and what remains reachable under structured depth probing.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38448
PDF
