Chat
-
A GHOST in Long-Horizon Agents: Governance Hazard from Overlooked Safety Constraints across Turns
2026-10-02 01:33:04XinPeng Shen, Lan Zhang, Yixiao Huang, Haoran Cheng, Jiewei Lai, Leilei Chen, Haoxiang DengAbstract
Long-horizon agents are now playing an increasingly significant role in assisting humans with complex problem-solving. However, it is exactly their extended interaction history that introduces an underexplored execution-safety concern. Under benign interaction conditions, an agent may execute an action that violates a safety constraint specified many turns earlier. We term this failure mode Governance Hazard from Overlooked Safety Constraints across Turns (GHOST), which may cause irreversible damage. Our experiments reveal that GHOST events are not isolated cases: this failure mode, occurring precisely under benign interaction conditions, yields an occurrence rate of 11.5% on GPT-5.5. Furthermore, we theoretically show that if the residual conditional violation hazard along each safe prefix is bounded below by a non-summable sequence, the execution enters the hazard region almost surely. Leveraging this theoretical insight, we further propose STAR-Guard, a two-layer defense coupling historical semantic safety constraint restoration with pre-execution audit. STAR-Guard restores applicable safety constraints to reduce unsafe proposals, while its deterministic audit layer prevents residual violations from reaching the environment. Consistent with this two-layer design, we observe no GHOST events in our experiments under the GPT-5.5 setup.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02664
PDF
-
On-Premises Multi-Course RAG Tutoring for Business Education: Hardware-Software Trade-offs in a Campus AI Tutor
2026-10-01 21:33:46Sidney Shapiro, Joshua LindemannAbstract
Campus AI tutors based on retrieval-augmented generation (RAG) must ground answers in assigned course materials while keeping textbooks and student dialogue on institutional infrastructure. We present CourseChat, an on-premises, multi-course RAG tutor for undergraduate business education, deployed behind a campus web gateway and intended for use embedded in Moodle. Six isolated course offerings, each keyed by its own course reference number (CRN), share twin-edge AI hosts running a FastAPI service, a local vector database, and a local large language model (LLM) served by Ollama. We report two generation-model bake-off rounds, a separate fixed-evidence source-fidelity comparison, and conversation and quiz audits. Several larger models failed the classroom speed gate, but a 12B model and a 7B alternative passed. A separate mixture-of-experts candidate improved some corrections while introducing new factual and continuity errors. We therefore retain the 8B production model pending a demonstrated overall improvement, rather than claiming that 8B is universally optimal. Software changes improved follow-up topic resolution while preserving course scope; 435 prebuilt questions across 65 modules decouple practice from live generation. The results support treating model choice, evidence selection, serving compatibility, and product design as a joint engineering decision. They do not establish learning gains: faculty ratings, peak-load capacity, and complete public-gateway acceptance remain separate evaluation needs.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02510
PDF
-
Understanding Clinical Cognitive Dialogues Using Large Language Models
2026-10-01 21:18:18Vishalakshi Arumugam, Dan Schumacher, Veronica Rammouz, Erfan Nourbakhsh, Enrique Gonzalez Guerrero, Jeremy Davis, Anthony RiosAbstract
In-person cognitive assessment is both a test and an interaction. Clinicians explain tasks, repair misunderstandings, and adapt to patient responses, while patients may hesitate, seek clarification, or disengage. Yet clinical dialogue resources rarely label the interaction structure needed to study these behaviors at scale. We present an de-identified corpus of 33 cognitive assessment conversations with 8,250 utterances annotated for three speaker roles and 56 dialogue acts. We use this corpus to benchmark large language models on fine-grained dialogue-act classification and next-patient-utterance generation. We also test whether out-of-domain instruction data and explanation-augmented training transfer to this clinical setting. Instruction tuning produces the strongest patient-utterance reference matching and improves classification accuracy. Reasoning-aware fine-tuning produces the strongest classification results among the LLaMA-3.1-8B variants. However, even the best models struggle to separate closely related dialogue acts, showing that broad conversational intent is easier to recognize than fine-grained communicative function. The corpus and benchmark make interaction structure measurable in cognitive assessments and support follow-up work on conversational markers, clinician education, and carefully validated simulated patients. This work does not make diagnostic claims. Instead, it provides the data and evaluation framework needed to study these applications.
Abstract (translated)
URL
https://arxiv.org/abs/2609.34125
PDF
-
FinDialogLens: Event Extraction over Multi-Party Dialogue for Missed-Trade Identification in Financial Chatrooms
2026-10-01 20:29:40Chin-Lun Fu, Hong Ni, Behrouz MadahianAbstract
Multi-party financial chatrooms are vital for sales-and-trading professionals, but their complexity makes manual recovery of missed trades infeasible: each Request for Quote (RFQ) is an event whose final price and trade outcome appear many messages after the RFQ-trigger message (the inquiry message), interleaved with concurrent RFQs from other participants. We cast this as event extraction (EE) over multi-party dialogue and present FinDialogLens, a hybrid LLM pipeline in which compact fine-tuned classifiers act as inference-time scaffolds: they detect RFQ-triggers and price/trade outcome metadata, an RFQ-Level Module segments per-event RFQ windows, and a Trade Engine fills argument roles. With GPT-4o, FinDialogLens reaches 92.1% and 94.3% accuracy on final price and trade outcome, respectively, outperforming full-chatroom CoT prompting methods; fine-tuned open-source LLMs with as few as 3B parameters achieve comparable performance with modest in-domain data. To make the LLM-based solution practical at scale, a difficulty-aware router balances cost and accuracy by allocating RFQs between a low-cost rule-based engine and the higher-performing LLM-powered Trade Engine, cutting LLM calls by 85% on final price while recovering half of the accuracy gap to FinDialogLens (GPT-4o), saving over $300/day at our 70,000-RFQ/day scale.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02455
PDF
-
Trained Agentic Context Management
Abstract
We study long context language models. Instead of training long context natively, or designing a long context harness, we train a model over the simplest possible harness: a tool to call itself with any specified prompt and a tool to read tokens in a range from the input context. We finetune Qwen3.6-35B-A3B on a diverse synthetic dataset using this harness. With only 8,000 tokens of context, our small model is as strong as GPT-5.4 with 1M tokens of context on the OOLONG-synth benchmark when document length exceeds 40K tokens.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02404
PDF
-
Inherit-MAS: Test-Time Evolution of Multi-Agent Systems through Workflow and Execution Inheritance
2026-10-01 19:23:32Songtao Wei, Yi Li, Zhichun Guo, Bingzhe LiAbstract
Multi-agent systems (MAS) built from large language models coordinate specialized agents to tackle complex tasks, but effective workflows are difficult to design in advance. Test-time evolution refines workflows using execution feedback, yet broad revisions can disturb useful components, while re-executing unchanged requests can incur redundant computation. Inspired by the interplay of inheritance and selection in biological evolution, we introduce Inherit-MAS, which makes inheritance explicit at the workflow and execution levels. A meta-model first synthesizes a workflow of worker agents with declared roles, communication inputs, and tool permissions, and a separately prompted judge scores each executed candidate and diagnoses its deficiencies. In ordinary refinement rounds, \emph{workflow inheritance} starts from the latest completed candidate, may discard removable nodes judged unhelpful, and applies a validated edit to address the diagnosed deficiency. When the new candidate executes, \emph{execution inheritance} inherits eligible stored results only if the complete resolved request and execution context match, avoiding redundant model and tool calls. With GPT-4o-mini workers, Inherit-MAS achieves 55.4\% completion on WorkBench and 49.7\% joint F1 on HotpotQA FullWiki, outperforming EvoAgent, EvoMAS, and TacoMAS. With Qwen3-32B workers, it also exceeds these evolving-MAS baselines on both benchmarks. Compared with rerunning the same controller with execution inheritance disabled, execution inheritance reduces worker-token usage by 29.1\% on WorkBench and 34.6\% on HotpotQA, and total token usage by 5.3\% and 18.1\%.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02396
PDF
-
Social bot detection in the age of ChatGPT: Challenges and opportunities
2026-10-01 19:08:58Emilio FerraraAbstract
We present a comprehensive overview of the challenges and opportunities in social bot detection in the context of the rise of sophisticated AI-based chatbots. By examining the state of the art in social bot detection techniques and the more salient real-world application to date, we identify gaps and emerging trends in the field, with a focus on addressing the unique challenges posed by AI-generated conversations and behaviors. We suggest potentially promising opportunities and research directions in social bot detection, including (i) the use of generative agents for synthetic data generation, testing and evaluation; (ii) the need for multimodal and cross-platform detection based on network and behavioral signatures of coordination and influence; (iii) the opportunity to extend bot detection to non-English and low-resource language settings; and, (iv) the room for development of collaborative, federated learning detection models that can help facilitate cooperation between different organizations and platforms while preserving user privacy.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02386
PDF
-
Coco: An Agentic Copilot for the Hardware--Software Co-Design Lifecycle
2026-10-01 18:55:52Samuel Kushnir, Kavya Sreedhar, Yeshwanth Reddy Pogula, Amir Yazdanbakhsh, Narges Shahidi, Ming Liu, Varun Gohil, Ravi Iyer, Parthasarathy Ranganathan, Christina Delimitrou, Suvinay SubramanianAbstract
Co-designing ML models and the accelerators that run them is an unusual reasoning task: architects must draw confident, high-stakes conclusions about systems that do not yet exist, and the pace of both model evolution and hardware cadence means the analysis burden grows every quarter. The evidence behind each decision--hundreds of gigabytes of fresh simulation sweeps over novel design points--is by construction absent from any LLM's pretraining corpus, and there is no external literature to retrieve; naive "chat-with-your-data" approaches hallucinate exactly where correctness matters most. We present Coco (Copilot for Codesign), an agentic platform deployed with TPU architects that accelerates the co-design lifecycle of setting up experiments, sweeping simulators, and deriving insights. Coco is built as four layers: (i) a datastore that automatically registers every simulation sweep into a normalized relational schema, so agents ground every number in a SQL query rather than scraping heterogeneous files; (ii) a library of tools with typed APIs that agents compose without human orchestration; (iii) agents that encode recurring analysis workflows--most notably iso-execution analysis, which compares systems at matched execution configurations, including swept-but-dominated points off the Pareto frontier; and (iv) a platform UX whose navigation state doubles as agent context. We report early deployment experience toward a reduction in time-to-simulation and time-to-insight, and argue that co-design is a distinct agentic domain: its data must be retrieved rather than memorized, its workflows are recurring but context-dependent, and expert adoption hinges on UX that balances IDE-style control with interactive exploration.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02376
PDF
-
Automating the Application of HCI Principles: Skills for On-Demand UI Construction, the Human-AI Space to Think, and the Future of HCI
2026-10-01 18:45:43Nathan Conklin, Miranda Capra, Chris NorthAbstract
Human-computer interaction (HCI) is in the middle of a transition: large language models can now generate functional user interfaces (UIs) on demand from natural-language task descriptions. A user explains what they are trying to accomplish, and the system materializes a working interface to support it. This capability already exists in systems such as Claude and ChatGPT and continues to grow in fidelity as the underlying models improve. The next step along this trajectory is to move from interfaces that are merely generated to interfaces that are generated well. We propose a framework in which the dialogue between user and artificial intelligence (AI) becomes a Space to Think: a shared, structured cognitive workspace in which task decomposition produces an on-demand user interface as an extension of the user's thinking rather than as a separate artifact. Within this paradigm, classical HCI design knowledge (Nielsen's heuristics, Norman's affordance prescriptions, Web Content Accessibility Guidelines (WCAG) success criteria, cognitive-load constraints, and mixed-initiative principles) is encoded as skills: machine-readable this http URL files that the generating agent loads at runtime as software engineering tools. Skills turn HCI design knowledge into declarative, inspectable, version-controlled, and editable artifacts owned by the HCI community itself so that accessibility, learnability, and consistency become properties of a generative process rather than properties of a finished product. We outline a research agenda depicting a future where the HCI field transitions from today's design and knowledge heuristic checklist towards a future where the craft becomes machine-readable, executable, and open.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02369
PDF
-
MIRROR: Multipath Quorum Integrity for LLM Multi-Agent Communication
2026-10-01 18:22:22Ryuichi Yamafuji Lun, Jingzhen Wang, Shreyas Kolte, Ruiteng LiAbstract
Inter-agent communication is central to Large Language Model Multi-Agent Systems (LLM-MAS), but it introduces an underexplored vulnerability: Agent-in-the-Middle (AiTM) attacks that manipulate messages in transit without compromising the agents themselves. Prior work reports Attack Success Rates (ASR) approaching 100% on structured tasks. Existing defenses rely on semantic validation, which requires additional inference and can block benign outputs, or on transport-layer encryption, which does not help when an intermediary legitimately terminates TLS. We present MIRROR, a communication-layer integrity primitive that replicates a single canonicalized payload across k logical routes and accepts a message only when a strict majority of routes report the same digest. MIRROR uses unkeyed hashing and so authenticates nothing on its own, since an active on-path adversary can always recompute a digest over a payload it has modified. All integrity derives from the assumption that honest routes form a majority. The digest serves only to make witness routes constant-size and to bind the recovered payload to the quorum-agreed value under second-preimage resistance. We give the guarantee under a route-compromise bound alpha < 0.5, and extend it to correlated routes, where the quantity that matters is the size of the largest shared-failure group and not the route count. We further show that availability and integrity degrade at the same threshold: below alpha = 0.5, quorum-denial and message-dropping adversaries cannot block honest traffic. Across MMLU, HumanEval, and MBPP on two frameworks and four communication topologies, and in a MetaGPT deployment against a production API, MIRROR reduces ASR to 0% below the threshold at 1x LLM token cost. LLM-as-a-Judge costs 35x in the same deployment, and blocks up to 44.2% of benign outputs in the topology sweep.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02349
PDF
-
Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents
2026-10-01 17:59:50Yen-Jen Wang, Haozhe Jiang, Shuying Deng, Haoru Xue, Weirui Ye, Rocky Duan, Nika Haghtalab, S. Shankar Sastry, Pieter Abbeel, Haozhi QiAbstract
Building reliable robot capabilities across diverse tasks requires substantial human effort to develop and maintain skills, design rewards, and integrate perception with control. We present Reconstruct, Practice, Go Real (RPG), a framework for autonomous improvement of robot execution systems without updating model weights. RPG identifies manipulation capabilities in an offline dataset and constructs related practice tasks in simulation. During practice, RPG uses execution feedback, privileged simulator state, and available dataset videos to diagnose failures. It develops new reusable symbolic skills, refines existing skills, and revises the system prompt based on these diagnoses. Cross-task evaluation tests individual candidate changes and merged revisions before they are retained for reuse. At test time, a multimodal LLM uses the resulting system prompt and skill library to coordinate perception and robot control. On held-out initializations of 22 manipulation tasks, RPG improves task success from 28.6% after the first practice round to 95.0% after 15 rounds, outperforming all evaluated baselines, including ASPIRE (75.5%) and CaP-Agent0 powered by GPT-6 Astra Pro (60.0%). After a common calibration and hardware-adaptation procedure, the frozen system succeeds in all 30 physical trials, with ten trials on each of three tasks. Project Website: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.02204
PDF
-
Mem++: Non-Destructive Memory for Long-Term Organizational LLM Agents
2026-10-01 16:32:38Ahmad Yehia, Aly O. Abdelkareem, Islam Ahmed, Hesham Omran, Khaled Alashmouny, Christian Claudel, Abduallah MohamedAbstract
Large Language Model (LLM) agents now take part in organizational work, where many authors record decisions across documents over months. Because a revised decision arrives as a new document rather than an edit, answering a question requires knowing which version held at a given time. However, most memory systems compress the record at write time. By distilling each document into facts, notes or graph edges, these methods fix what can be answered before any question is asked. To address this, we propose Mem++, a non-destructive memory framework shifting from write-time distillation to read-time selection. Mem++ stores every document whole with its date and author, and it calls no generative model at write time. At read time, it retrieves only documents dated up to the time a question asks about and fuses lexical and semantic rankings. Unlike systems that overwrite older versions, Mem++ keeps them and leaves the choice to the answering model. Evaluations on the organizational benchmark OrgMemBench demonstrate that Mem++ surpasses the strongest memory system baseline by 8.0 to 13.1 points across two answering models. With gpt-4.1-mini, it also achieves the best overall score, 2.6 points above RAG. In addition, Mem++ achieves the best average LLM-judge score on LoCoMo and ranks second on LongMemEval-S, behind only its entity-graph variant. Code for benchmark evaluation is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02002
PDF
-
Counterfactual Auditing of Bias in Open-Source Large Language Models for Clinical Triage
2026-10-01 16:17:43Manar Aljohani, Brandon Ho, Kenneth McKinley, Dennis Ren, Xuan WangAbstract
Emergency department (ED) triage is a high-stakes prioritization task in which demographic, socioeconomic, and system-context information may improperly influence acuity assignment. Although open-source large language models (LLMs) are increasingly considered for local and privacy-preserving clinical decision support, it remains unclear how counterfactual bias varies across model families, sizes, medical-domain models, and domain-adapted models. We present a comparative counterfactual audit of ten open-source LLMs for pediatric Emergency Severity Index (ESI) prediction. Starting from real and handbook-style clinical vignettes, we construct paired counterfactual variants that change only one injected demographic, socioeconomic, healthcare-access, behavioral, social, or system-context variable while holding the clinical presentation fixed. Models include Qwen2.5-7B, Qwen2.5-14B-Instruct, a QLoRA fine-tuned Qwen2.5-7B, MedGemma variants, MedLLaMA2-7B, GPT-OSS-20B, and GPT-OSS-120B. We measure any counterfactual shift, undertriage, overtriage, shifts greater than one ESI level, mean shift, and mean absolute shift. Counterfactual sensitivity varied substantially and did not consistently decrease with larger model size or medical-domain pretraining. The fine-tuned Qwen2.5-7B showed the lowest overall sensitivity, with a 5.27% any-shift rate and mean absolute shift of 0.0534, versus 16.02% and 0.1706 for the base model. Several larger or medical-domain models showed more significant shifts. Stratified and correlation analyses further revealed clinically important directionality and shared failure patterns hidden by aggregate rates. These findings support counterfactual auditing as a lightweight, clinically interpretable framework for comparing fairness risks in open-source LLMs before clinical deployment.
Abstract (translated)
URL
https://arxiv.org/abs/2610.01963
PDF
-
Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens
2026-10-01 16:07:49Ruiyang Si, Jianxin Bi, Shunyu Yang, Rui Ni, Wenbo Huang, Qiang Wang, Shulong Jiang, Duomin Wang, Xiuyu Li, Haiwen Feng, Zhen Dong, Daquan ZhouAbstract
Vision language model (VLM) agents can control robots through visual feedback and action primitives, but repeated model invocations and redundant observations incur substantial token overhead. We introduce PyRUA-Lean, an interactive code-execution framework that couples feedback-driven primitive composition with selective observation: the agent composes classical robot primitives and learned vision-language-action (VLA) policies into Python cells that perform conditional checks and local retries, returning only explicitly requested images and state feedback for replanning. Across 700 simulated task instances from LIBERO-PRO, RoboTwin 2.0, and RoboCasa365, we compare PyRUA-Lean with a tool-calling baseline using the same GPT-6 Astra planner and underlying robot primitives. Under equal LLM-call budgets, PyRUA-Lean increases overall success from 63.1% to 71.7%. On instances solved by both agents, it uses 49% fewer LLM calls and 65% fewer input tokens.
Abstract (translated)
URL
https://arxiv.org/abs/2610.01939
PDF
-
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations
2026-10-01 14:31:34Arman Behnam, Sunglyoung Kim, Liangwei YangAbstract
A companion that talks with a person for months should come to understand them. It should remember what they said, infer who they are, and know when the past bears on the message in front of it. Testing this requires a real person's record, and such records are private, so benchmarks generate the person and the questions and settle in advance what matters. We release \bench, ten real relationships with an AI companion: 27,218 messages over up to 120 days, released as the conversation and four files derived from it, a profile, a persona, a chat ground truth and a question set, each citing the messages it rests on. Every chat label carries the reasoning trace that produced it, checked stage by stage against the conversation. Three findings follow. First, the past is rarely needed and far away. Pooled measures mislead: a recency window finds the required message for 95.9\% of probes and 2.2\% of those that need memory, and at the natural rate 96\% of the gain from supplying recorded evidence comes from messages that need none. Second, no detector we tried can tell when memory is needed on real messages, authored questions over the same histories leak the cue, and labeling the same messages as memories raises their use by ten to fourteen points. Third, three agent systems reconstruct the persona with the same F1 at a 31-fold difference in cost.
Abstract (translated)
URL
https://arxiv.org/abs/2610.01780
PDF
-
Chaining Skills to Hijack LLM Agents
2026-10-01 12:28:49Tian Dong, Zixuan Ma, Haodong Zhao, Huaien Zhang, Shaofeng Li, Hao ChenAbstract
LLM agents use skills to improve performance on specialized tasks. To complete a user request, an agent may invoke several skills in sequence, allowing information produced under one skill to guide the next. Because skills may come from open-source repositories, this handoff can also carry attacker-controlled claims into later decisions. In this paper, we introduce APEX, which constructs and refines adversarial skill chains tailored to a user task and an attacker-selected action. The key insight is that an agent-written record of genuine task progress can carry a false claim of user approval across skills: an upstream skill induces the agent to create the record, and a downstream skill uses it to direct the attacker-selected action. Across four targeted-action families and six models on SkillsBench, the chains induce the selected action in 512 of 690 attempts (74.2%). On GPT-5.4, the full chain succeeds in 84.3% of attempts, compared with 17.4% when the workflow is merged into one skill. We further evaluate a prompting defense that asks the agent to check skill-produced files against the original request. On GPT-5.4, it lowers targeted-action success from 84.3% to 59.1%, while the verifier test-pass rate across 72 benign native-skill tasks falls from 86.7% to 56.3%. These results highlight the need for defenses that prevent attacker-directed actions while preserving legitimate task performance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.01564
PDF
-
AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Models
2026-10-01 12:28:03Yuxiang Wang, Kunyu Feng, Yuancheng Wang, Zihang Liu, Shengbo Cai, Qinke Ni, Wan Lin, Tao Feng, Yingda shen, Ming-Hao Hsu, Zhixian Zhao, Liqiang Zhang, Teddy Sun, Steve Yves, Zhizheng WuAbstract
Model intelligence and fast response jointly shape the quality of interaction with speech language models, yet remain difficult to achieve together. Explicit chain-of-thought (CoT) improves reasoning and audio understanding, but generating intermediate reasoning tokens delays responses. Describing fine-grained acoustic cues further lengthens CoT and increases latency. Latent reasoning can reduce this overhead, yet existing methods often trail CoT and remain limited by single-path supervision and reasoning budgets that do not adapt to problem difficulty. We introduce AURAL, which models a distribution over multiple plausible reasoning continuations in latent space and jointly predicts chunks of future states to reduce sequential forward passes and reasoning latency. To provide initial supervision for latent reasoning, we construct AuralReason-683K: 683K bilingual speech utterances (about 1,000 hours) with concise CoT for emotion recognition, empathetic dialogue, and general reasoning. AURAL-RL then explores beyond these traces, rewarding concise reasoning that yields high-quality answers and adapting reasoning effort to each problem. Across two backbones, AURAL-RL achieves performance comparable to CoT-RL, with larger gains over the respective supervised checkpoints on most metrics. Analysis further shows that harder questions elicit more latent reasoning steps. On Qwen2.5-Omni, it reduces time to the first answer token by 11.8x, from 1.22 to 0.10 s, versus 0.05 s for direct answering.
Abstract (translated)
URL
https://arxiv.org/abs/2610.01560
PDF
-
False Floors: LLM Safety Routing Evaluations Break Under Distribution Shift
2026-10-01 12:09:28Amit Singh Bhatti, Vishal VaddinaAbstract
Safety routers send each request to one of several models and are judged against the best single model. A major routing benchmark picks that comparator on the evaluation data. In the benchmark's own setting this is harmless, but under distribution shift it is not. On HELM Safety the selection cost is 0.003-0.030 of harm under random splits and 0.045-0.113 under held-out categories, comparable to the whole deficit attributed to routing, with its direction holding under either published judge alone. It rises seven- to ninefold on AgentDojo when suites are held out. Across seven safety corpora chosen by rules fixed in advance, three meet a registered interval test and four beat a later permutation null, and three of the four interval misses are corpora where some models have zero observed harm. Prior work proves the direction of this bias. We size it on harm and accuracy, show that it is larger under the held-out splits we measure, and bound it by optimism plus a shift-dependent regret. Scored honestly under shift, routing buys little on these benchmarks. In most pool cells the nested router serves the honest baseline's model, and on the nearly saturated AgentDojo corpus a perfect pre-dispatch router is worth at most two points of harm. We also find a model's expressed recognition of a late injection steerable. On held-out reruns an attacker who knows which model it faces lowers GPT-5.4's judged recognition by 19.6 points, confirmed by an independent label. In an offline counterfactual composition into a controller, the same attack raises or lowers estimated harm depending on the fallback model. Safety routing should be evaluated under shift, against a baseline chosen without the test labels, and recognition-based defences should be scored on harm against an attacker who chooses what the model sees.
Abstract (translated)
URL
https://arxiv.org/abs/2610.01535
PDF
-
LLM-Assisted Discovery of Typed Semantic Links for Ontology Network Construction
2026-10-01 09:59:00Nouha Hayouni, Sheeba Samuel, Alsayed AlgergawyAbstract
Constructing typed, justified semantic links between ontologies is essential for enabling interoperability across heterogeneous and interdisciplinary knowledge domains. However, manually curating such links is difficult to scale. To address this challenge, we propose an end-to-end framework for ontology network construction that automates the discovery and generation of both intra-domain and inter-domain relationships. Our approach combines domain-adapted DistilBERT embeddings for dense contextual representation, clustering-based pre-filtering to reduce the candidate search space, and GPT-4o-driven relationship generation via iterative prompt engineering to produce semantically rich, interpretable links. Applied to ReproduceMeON - a network of 33 ontologies spanning machine learning, microscopy, computational science, and experimental workflow - the pipeline reduces approximately 800k raw concept pairs to 95k high-quality candidates. Human expert validation of 429 generated relationships by two independent annotators yields an overall precision of 80.19% (91.49% on high-certainty annotations) and an F1 of 0.890, with substantial inter-annotator agreement. Comparative experiments against five similarity-based baselines, including Sentence-BERT, show a substantial performance gap (best baseline F1 = 0.581), while an ablation study demonstrates that similarity-based methods alone fail to discriminate valid from invalid relationships (AUC approx 0.5) on the filtered candidate set. These findings highlight the necessity of LLM-based reasoning over concept roles and domain semantics for accurate relationship construction.
Abstract (translated)
URL
https://arxiv.org/abs/2610.01393
PDF
-
Gacha Decoding: Eliciting Diverse Generations Through Instruction Following
2026-10-01 09:48:48Scott Geng, Yufei Zhang, Joseph Lee, Jerry Li, Marjan Ghazvininejad, Pang Wei KohAbstract
We introduce Gacha Decoding, an inference-time method for eliciting diverse language model generations that scales with model capability. Across open-ended domains (in-the-wild chat, creative writing, planning for image generation, and protein design), Gacha Decoding significantly outperforms existing generation diversity approaches at equal quality (up to 2.4x Vendi over the next-best prior approach), reaching the same number of high-quality modes with over an order of magnitude fewer samples (11.0x) and discovering novel modes that no other approach surfaces. Our key insight is to treat diversity as an instruction-following problem: rather than relying on the LM's token entropy, we combine its instruction-following capability with randomness from an external RNG tool to scalably identify and realize distinct modes of the response space. This approach of "planning with dice" enables Gacha to invert the long-observed tension between diversity and model capability. As the underlying LM becomes a better instruction follower, diversity under Gacha Decoding consistently improves--even as its token entropy and diversity under prior approaches decline. Together, our results highlight that instruction following, rather than token entropy alone, can drive generation diversity.
Abstract (translated)
URL
https://arxiv.org/abs/2610.01382
PDF
