Tell an LLM negotiator to be "headstrong" and it should hold firm on price, but does that instruction retain the same behavior in every language? To test this, we use identical buyer and seller instances of Gemini 3.6 Flash to negotiate the same 12 CraigslistBargain scenarios in English and Korean. The pilot-scale 2 x 2 x 3 design crosses interaction language, seller urgency (none or strong), and buyer persona (cooperative, neutral, or headstrong), yielding 432 attempted negotiations. We call this property cross-lingual social-policy fidelity: whether a prompt-defined social policy produces the same behavioral effect regardless of interaction language. It often does not. Korean negotiations reached agreement far more often than English (77.3% vs. 52.5%, a 24.8-point gap, Holm-adjusted p = .0039), but only for neutral and headstrong buyers; cooperative buyers were already near-ceiling in both languages. Buyers' opening offers barely differed by language; the gap instead emerged later, through larger seller concessions and a smaller final gap in Korean, and agreed prices were also lower in Korean. Repeating the full design with Qwen3.7 Flash as both agents gives directional support: agreement was again higher in Korean (+13.9 points vs. Gemini's +24.8, with an interval whose lower bound is near zero), and sellers again conceded more. Pragmatic analysis reveals why: while both languages frequently featured face-threatening acts like rejections and counter-offers, Korean dialogue softened these threats with substantially more politeness mitigation, especially among sellers (11.7% vs. 3.6%). These results show that such a policy can produce different simulated negotiation behavior, not just different wording, when only the interaction language changes.
https://arxiv.org/abs/2611.00300
Collaborative robots (cobots) are designed to be safer and more interactive than traditional industrial robots, share the same workspace as humans, and assist them in a range of shop-floor tasks such as palletization, joint assembly, and part inspection. Many of these tasks involve repetitive workflows that may evolve with changes in production environments and task specifications. These requirements motivate the need for intuitive interfaces that allow workers to modify workflows on the shop floor and generalise these routines for future use. This work introduces the Teach-Abstract-Apply (TAA) framework, which enables human operators to (a) teach new workflows to cobots in natural language, (b) abstract the taught workflows into skills for later use, and (c) apply these skills in different settings. As a case study, we apply the TAA framework to a collaborative structure-building task and evaluate it with both open-weight (Qwen3-Coder) and closed (GPT5.2-Codex) models in self-play and cross-model configurations. Our results show that skill abstraction improves task success rates and reduces interaction cost. Beyond automated evaluation, a preliminary human-in-the-loop study suggests that the pipeline also works with human instructions.
https://arxiv.org/abs/2611.00297
LLM agents that operate over long inputs must perform context management: deciding what to retain in a fixed-size context window. A common approach is compaction, where the model replaces its history with a self-generated note. Yet off-the-shelf agentic models, including GPT-5.5 and GLM-5.3, often write ineffective notes, and reinforcement learning (RL) alone rarely discovers useful note-taking behavior. We present MEMENTO, a long-context agent built on Qwen3-8B and trained to manage its context through compaction. We first bootstrap note-taking by fine-tuning on synthetic trajectories annotated with notes generated in hindsight, then reinforce it with RL using a reward that combines answer correctness, note-quality heuristics, and confidence calibration. Although trained only to compact into a fresh window, MEMENTO extends at test time to strategies such as context folding and confidence-based backtracking. On book-level question answering across four benchmarks, with books of up to 2.5M tokens, MEMENTO raises Qwen3-8B's accuracy from 36.9% to 67.8% while never holding more than 20K tokens in context. It outperforms GPT-5.5 agent in the same harness (13.1%) and full book context (56.7%) at less than 1/50 the cost. It also nearly matches a ~100x larger GLM-5.3 agent (69.3%) at 1/9 the cost, and comes within 6.4 points of GLM-5.3 full context at 1/26 the cost.
https://arxiv.org/abs/2611.00244
Conversational assistants are expected to help people with diverse backgrounds, preferences, and communication styles. Yet evaluations centered on a single cooperative user provide limited insight into how reliably an assistant serves users with different personas. We introduce PersonaChatBench, a framework for evaluating task competence and responsiveness to diverse user needs. PersonaChatBench pairs the same underlying task with multiple simulated users, each guided by a private persona card that specifies distinct needs, preferences, and interaction behaviors. By holding the task fixed while varying the user, the framework examines how assistant performance changes across user conditions. We evaluate 20 language models across six domains, separately assessing native task outcomes, fulfillment of expressed persona needs, and simulator fidelity. Our results show that task performance and need fulfillment vary across personas and domains. Strong task performance does not necessarily translate into satisfying individual needs, and models' relative strengths in meeting those needs are not consistent across domains. PersonaChatBench makes these differences measurable, revealing gaps obscured by aggregate scores and helping identify which users an assistant serves well and where adaptation is needed. It provides a basis for evaluating consistency across users and guiding the development of assistants that better accommodate diverse needs in everyday applications.
https://arxiv.org/abs/2610.42060
Chatbots are increasingly consulted about public affairs, and their judgments of policies are useful only if they are robust. We measure this robustness in the setting of an ordinary user, through consumer chat interfaces. For 30 days, five chatbot configurations (Mistral, Gemini Flash, Claude Sonnet, and Claude Opus at two effort settings) were asked twice a day to score the long-term effect on the United States of 40 actions of the last four presidential administrations and of 15 hypothetical reforms, each with a confidence and a short comment. The judgments are robust: all configurations agree on the sign and the ranking of the administrations' mean scores, and two different configurations asked on the same day give opposite signs to the same action in about 4% of cases. Responses from different days differ more than same-day responses (which shared the order of the items); the difference grows slowly over the month, except where the service itself changed. We identify three such changes, which shifted the judgments while leaving little or no trace in the interface. Treating the comments as a retrieval task, we find them specific to each item and consistent across runs and chatbots, with lexical and embedding similarities agreeing. We release the dataset of 16,500 judgments.
https://arxiv.org/abs/2610.39398
Hundreds of millions of people now ask large language model (LLM) chatbots for health advice, which raises a question that is simple to pose and hard to answer: does everyone get the same advice? We audit six widely deployed LLMs from four providers on smoking cessation, a domain with codified clini- cal guidance and substantial public-health stakes, by putting the same four cessation questions to twelve user personas that differ in life stage, self-described expertise, and smoking history, for a total of 2,880 responses. What the models say depends on who appears to be asking. Every model named FDA-approved prescription cessation medications less often to teen personas than to adult personas, by 32 to 67 percentage points, and in five of six models a persona presenting health- care expertise received fewer facts than a persona presenting none. We then evaluate one deployable intervention: a short system prompt specifying a factual floor, the set of core med- ical facts every user should receive when they are relevant, while leaving tone, vocabulary, and framing free to adapt. The prompt narrows persona differences in every model, but its effect on overall fact coverage varies in both magnitude and direction across models, so a prompt validated on one system cannot be assumed to transfer to another. Two cautions frame these results. Equal mention rates are not always the correct clinical target, because prescription cessation pharmacother- apy is not recommended for minors, so a defensible factual floor must be age-aware rather than uniform. And because our personas vary on several attributes at once, we report scenario- level differences rather than isolated effects of age or expertise. We release all 2,880 responses and the analysis code.
https://arxiv.org/abs/2610.42039
This paper presents TurnTurk-GPT, a text-based turn-taking predictor for Turkish obtained by fine-tuning a Turkish GPT-2 model with the TurnGPT objective on synthetic and real dialogue, and evaluates it on real Turkish conversation against rule baselines, a zero-shot Turkish language model and a widely used multilingual end-of-turn detector. Evaluation uses word-level decision points on unpunctuated, lower-cased text approximating the output of streaming speech recognisers, recording-disjoint and speaker-disjoint folds, nested threshold selection and paired cluster bootstrap tests. TurnTurk-GPT outperforms the multilingual detector under both recording-disjoint and speaker-disjoint evaluation. It outperforms the zero-shot language model only when the test speakers occur in training; on unseen speakers the two are statistically indistinguishable. Removing the suffixes of the turn-final word reduces AP by up to 44%, against 2% for a sentence-internal word, locating the Turkish end-of-turn cue in verb-final morphology. Synthetic dialogue alone yields the weakest trained model, and when a speaker pauses the zero-shot and multilingual baselines remain close to chance. The model and the evaluation protocol are publicly released.
https://arxiv.org/abs/2610.42010
Multi-turn negotiation remains a challenging problem for large language model (LLM) agents. While LLMs can conduct natural-language dialogue, existing benchmarks predominantly assess only agreement rates, overlooking whether negotiated commitments actually create value once executed. To address this gap, we introduce TradeWar, a multi-country simulation benchmark that translates negotiation dialogues into concrete tariff and trade-share policies, enforces capacity and network constraints during settlement, and evaluates outcomes via an Economic Health Index (EHI). To solve this execution-grounded task, we propose TACTIC (Trade-aware Adaptive Consolidation and Theory-of-mind for International Commerce), an agent that iteratively refines its negotiation strategy across episodes-without updating base LLM weights-by leveraging prior experience, opponent behavior, and past settlement outcomes. Despite using zero-shot chain-of-thought (CoT) prompting, PromptLLM attains a 75% agreement rate but only 57.1 final EHI (*100), whereas TACTIC reaches 68.8. Across 20 sequential episodes and three seeds, TACTIC's final EHI improves from 58.2 to 73.2, compared with 65.2 for an ablation without cross-episode updates. Under technology-controls and energy-crisis shocks, TACTIC also exhibits smaller performance degradation than PromptLLM and MemoryLLM. These results indicate that CoT deliberation and interaction memory alone do not fully address delayed execution feedback, whereas settlement-grounded adaptation improves long-horizon negotiation in TradeWar.
https://arxiv.org/abs/2610.42004
Foundation models (FMs) learn reusable representations from large collections of unlabeled data. In chemistry the corresponding data mainly consists of molecular structures, which are abundant, whereas experimental measurements are scarce. Chemical FMs such as ChemBERTa and MoLFormer were therefore trained on diverse molecular structures to enable fine-tuning on small experimental datasets (less than 100 datapoints in most realistic scenarios) and subsequent property prediction. At the same time, general-purpose FMs such as GPT-6 Astra and Claude Opus 5.5 were trained on virtually all publicly available data, including knowledge of the humankind on molecular properties and laws governing them. Here we compare accuracies of chemical and general-purpose FMs on tasks from various areas of chemistry. Strikingly, general-purpose GPT-6 Astra outperforms the currently eligible chemical FMs on five physicochemical and quantum-chemical regression tasks when only 60 experimental datapoints are available. Only when provided 10x datapoints do the best chemical FMs reach performance of GPT-6 Astra: on 1,000 and 10,000 points they show performance on par with Astra on 60 and 1,000 points, respectively. Thus, counterintuitively, frontier general-purpose FMs are better suited for guiding chemical research in data-scarce areas than specialized chemical FMs, suggesting that learning relevant primitives (e.g. chemical structures) does not substitute training on relevant humankind knowledge.
https://arxiv.org/abs/2610.41899
Conversational explainable AI (ConvXAI) agents often use GUS-style architectures with separate modules for intent recognition, dialogue management, and template-based response generation. While faithful to the underlying XAI methods, these pipelines are hard to adapt and often struggle with context-dependent follow-up questions. We present SimXAI, a lightweight LLM-centric conversational layer that replaces these modules with a single tool-calling LLM that bridges access to existing XAI resources. Rather than a standalone agent, SimXAI serves as a modular interface that enables conversational access to external XAI resources. We further introduce an evaluation suite for single- and multi-turn parsing, faithfulness, and contextualization. Across existing and new datasets, SimXAI achieves strong function-selection accuracy and high faithfulness while better handling context-dependent requests. In a user study replacing only the conversational layer of TalkToModel, a representative GUS-based agent, users completed tasks more accurately and in fewer turn. Overall, SimXAI improves GUS-based design while preserving faithfulness and improving conversational quality.
https://arxiv.org/abs/2610.41856
Large closed-source reasoning models expose only their final answers. The intermediate reasoning that produces those answers is hidden behind API surfaces, tool-call policies, and safety filters. Existing chain-of-thought (CoT) extraction methods assume a side channel: a visible reasoning field, a scratchpad carried through tool calls, or a signed/encrypted reasoning block. We reproduce three representative state-of-the-art extraction methods and find that, on Claude-Sonnet-5.5 accessed through the standard chat-completions interface, all three return zero CoT tokens. The failure is structural rather than a bug: the reasoning field is absent, named tool selection is rejected, free-text scratchpad arguments are filtered, and no replayable reasoning block is exposed. We therefore take a different route. We present RECAST, a reconstruction-based framework that conditions a decoder on the question and the target model's final answer, reconstructs a first-person structured rationale, cleans it, and builds SFT-ready data. To the best of our knowledge, RECAST is the first system to reconstruct CoT from frontier closed models such as Claude-Sonnet-5.5, GPT-6.1, and Gemini 3 without using hidden reasoning channels. We instantiate RECAST on Claude-Sonnet-5.5 and additionally obtain successful qualitative reconstructions on GPT-6.1 and Gemini 3 with the same answer-only protocol. The system is open-source and packaged as an agent skill: one prompt deploys it and runs the complete pipeline to produce SFT-ready CoT data. This preprint describes the system, its threat model, and a controlled artifact validation; it does not claim large-scale benchmark improvements.
https://arxiv.org/abs/2610.41813
The needle-in-a-haystack (NIAH) benchmark was introduced as a test for measuring a model's ability to find small relevant facts within a very large body of input text. However, existing NIAH benchmarks each suffer from one or more of the following limitations: (1) reliance on synthetic data, so their evaluations may not generalize to real-world settings; (2) reuse of previously published datasets, leading to the risk of benchmark contamination; (3) dependence on manual annotation, which requires human effort to create and update data and is prone to future benchmark contamination; and (4) unrealistic simplification of long-context multi-hop reasoning where each next step is trivial given previous steps, while real-world reasoning often requires planning over multiple possible proof paths. To address these limitations, we introduce \Benchmark, a dynamic benchmark built from real citation relationships among scientific papers published after the evaluated models' knowledge cutoff date, which utilizes real-world information while ensuring no benchmark contamination. The fully automated benchmark construction pipeline samples representative subgraphs of the citation graph formed by these papers and converts each subgraph into a long-context QA example with a verifiable answer. We use GraphNIAH to evaluate eight LLMs from the GPT-5.6, Gemini-3, and Qwen3.5 families. We find that accuracy falls as questions require longer reasoning paths: at question depths of 16 and 32, the GPT-5.6 and Qwen3.5 models answer YES/NO questions no better than random guessing, mostly by answering NO; four of the eight models answer no counting example correctly, and the others model get worse as the subgraph size increases. These findings suggest that current LLMs often stop searching the citation relationships in their context before they reach the answer, even though every fact they need is in the context.
https://arxiv.org/abs/2610.41704
Language agents increasingly tackle long-horizon tasks in interactive environments, where actions often depend on latent preconditions. The core difficulty is not trajectory length but recovery: when a prerequisite is missing or an earlier decomposition fails, trying another plausible action rarely helps. ReAct and later reflection or adaptive-planning methods support local correction, but express recovery as free-form text, with no explicit control state linking the terminal goal, the active goal, and the failure source. We introduce the Verify--Backtrack Loop (VBL), a training-free extension of ReAct that turns precondition discovery and failure diagnosis into structured planning-state updates. VBL maintains the task decomposition as a bounded goal stack and, on goal activation, execution failure, or material state change, jointly verifies two horizons---whether the active goal contributes to the terminal goal and whether it is feasible in the current state. These dual-horizon judgments, combined with typed failure attribution, trigger explicit operations---Push, Pop, retry, or BacktrackTo the parent. We evaluate VBL with Qwen3.5-9B, GPT-4o, and DeepSeek-V3.2 on AppWorld, ALFWorld, and ScienceWorld. VBL improves over ReAct and reflection-based control on every backbone--benchmark pair. On the challenging AppWorld setting, it improves task success by up to 22.07 percentage points over ReAct. Ablations show that removing either verification or diagnosis degrades performance, in several settings below ReAct, confirming that the two mechanisms are complementary. These results show that reliable long-horizon interaction benefits from revising the planning state, not merely the next action.
https://arxiv.org/abs/2610.41564
Long-context diffusion repeatedly pays for both token interaction and feed-forward computation. We formulate these costs as two separate budgets: the edges available to an attention graph and the experts activated for each token. This view connects local, dilated, and global attention with conditional expert computation without assuming that sparsity alone preserves document-level information. We specify normalized masked attention, distinguish denoising depth from sampling iterations, and derive graph and compute bounds. A reported sparse-expert configuration, denoted DualBudget, is analyzed across scientific summarization, multi-hop question answering, dialogue, and sentence-pair prediction. All supplied table measurements are retained. The length study shows gains over the listed baselines through 16K, together with measurable degradation as length increases. Ablations reveal mixed changes across the three reported scores, while the cost record indicates a 20% reduction relative to DiffuSeq under an unspecified timing convention. The analysis separates these observations from unmeasured claims about training speed, absorbing states, global coherence, and deployment memory.
https://arxiv.org/abs/2610.41487
While prior work has highlighted that systematic nation-level bias in large language models (LLMs) can pose operational risks for international relations (IR) applications, many existing evaluations still lack a clearly specified unbiased reference (ground truth), limiting fully quantitative and cross-setting measurement. Using an expanded corpus of 722 official UN Security Council (UNSC) records, we measure nation-level bias with five complementary tests, thereby extending prior approaches to cover a broader set of bias expression channels: opinion ranking (WOW), association sorting (AK+-), vote simulation (PVS), opposition attribution (F-Oppose), and framing (Headliner). To enable grounded bias evaluation, we explicitly define an unbiased status for each test; in particular, for WOW and AK+- where ground truth is difficult to specify, we propose an action-based pseudo unbiased status derived from observable voting behavior to construct a quantifiable baseline. Benchmarking 4 LLMs (GPT-4o-mini, Llama 3.3-70B, Mistral-22B-Small, and Qwen3-30B) across the five permanent members of the UNSC, we find a test-agnostic macro-pattern: relative to the reference baselines defined for each test, model outputs lean toward the opposition (red) side for China and Russia and toward the supportive (blue) side for the U.K., the U.S., and France. These results underscore the need to audit IR-facing LLM deployments with grounded, multi-test benchmarks tied to explicit reference points.
https://arxiv.org/abs/2610.41486
Fine-tuning a language model changes how it responds, but where is this fine-tuned behavior instantiated? To better understand this, we evaluate whether the change in model behavior arises only during the generation of the answer tokens where the change manifests, or whether altered processing of previous tokens causes it via the attention mechanism. For this, we patch the KV cache from a LoRA fine-tuned model into the unmodified base model, and vice versa. Our results show that for some behaviors, like responding in German or emergent misalignment, patching the KV cache can indeed transfer them from the fine-tuned to the base model. Correspondingly, patching the KV cache from base to fine-tune can partially or fully remove fine-tuned behavior. Furthermore, we find that the effect of patching grows with how much of the KV cache is patched and concentrates at a few pivotal positions, with system-prompt and chat-template tokens having disproportionate influence.
https://arxiv.org/abs/2610.41480
Patients often arrive at brief, time-constrained clinical visits unsure of what to expect or ask, and millions of adults now turn to general-purpose AI chatbots to prepare beforehand. Yet whether conversational AI improves visit readiness remains unclear. We designed a large language model (LLM)-based visit preparation agent to guide patients before an appointment by gathering clinical context, setting visit expectations, providing relevant health information, building a prioritized list of questions for their clinician, and generating a summary. In a prospective consented randomized study in the Google Health app, 802 U.S. adults held 866 health-related conversations with the visit preparation agent (standard or concise variant) or a minimally prompted control chatbot built on the same LLM. The visit preparation agent significantly outperformed the control across blinded clinician evaluations and patient self-reports. In clinician reviews of completed sessions (n = 272), the agent achieved a 16.6% higher rate of comprehensive preparation (67.2% vs. 50.6%; P < 0.05) and an 8.5% higher rate of alignment with patients' health context (98.9% vs. 90.4%; P < 0.01), while maintaining high medical safety and appropriateness across all study arms. Patient post-surveys (n = 460) showed 16.8% higher visit preparedness (73.8% vs. 57.0%; P < 0.01), 14.3% higher confidence in knowing what to ask (81.4% vs. 67.1%; P < 0.01), and 12.0% higher overall satisfaction (74.0% vs. 62.0%; P < 0.05). Clinician and participant metrics were not significantly correlated, indicating that expert review and patient self-assessment capture complementary dimensions of patient-facing AI. These findings suggest that LLM chatbots can safely help patients prepare for clinical visits, with greater benefit when following a structured workflow, and motivate future studies on in-visit communication and clinical outcomes.
https://arxiv.org/abs/2610.41437
The central bottleneck in visual generation and editing has migrated from achieving pixel-level fidelity to satisfying densely constrained user specifications through increasingly agentic workflows. Prevailing agentic generation pipelines remain shallow generate-verify-rewrite loops treating VLM judgments as coarse visual feedback, either discarding repair experience or admitting ungated updates that poison skill library. With memorize and govern periods left open, they degrade into ungoverned iterators of repeated trial-and-error rather than continual self-evolving harness. Towards this issue, we present \textbf{VEvo-Harness}, the first causally-guarded continual self-evolving harness system for agentic visual generation. VEvo-Harness introduces four coupled innovations: (1) \textit{a visual traceback} that densifies sparse judgments into root-cause attributions with a hierarchical verification tree; (2) \textit{a visual continual governance} that admits only causally valid skill patches through counterfactual dual-arm image generation replay; (3) \textit{a lifecycle-managed harness state} that hierarchically distills root-cause-anchored episodes across working, experience, and pattern tiers into a persistent skill library of routable and causally verified capabilities; (4) \textit{a heterogeneous sandbox policy} that orchestrates a diverse action space of repair primitives, dynamically routing cost-aware interventions based on root causes to select the most effective strategy. VEvo-Harness surpasses state-of-the-art agentic methods and rivals proprietary generators (\textit{e.g.}, GPT-Image, Nano-Pro) while maintaining the continual harness evolution and generalization.
https://arxiv.org/abs/2610.39158
Overly restrictive eligibility criteria contribute to widespread enrollment failure in clinical trials, yet published recommendations for how specific criteria should be broadened remain disconnected from trial design at scale. We introduce RECITE (Revising Eligibility Criteria Incorporating Textual Evidence), a framework for automated discovery, extraction, and implementation of evidence-based eligibility criteria revisions. RECITE uses protocol amendment documents from this http URL to construct a dataset of 11,913 curated instances across 5,735 trials, each pairing original criteria with documentary evidence and target revisions. We benchmark fifteen LLM configurations under truncated-to-context-window and retrieval-augmented generation conditions, on a 3,116-instance sample under an LLM-as-judge protocol validated against ten domain experts (judge vs. human quadratic-weighted Cohen's $\kappa_{qw} = 0.694 \pm 0.096$). The best open-weight model, Gemma 2 9B, achieves $\kappa_{qw}$-aligned ordinal score $3.0 \pm 0.9$ on a 0--4 scale (normalized 0.742) and the best closed-weight model, GPT-4o, reaches $3.0 \pm 0.8$ (normalized 0.745). Using an agentic literature discovery system, we then identified 44 paper--trial matches across five publications providing trial-design and EC-modification evidence. Our findings suggest that existing clinical knowledge can be operationalized into actionable trial design recommendations.
https://arxiv.org/abs/2610.41368
Existing visual preference evaluation relies on costly human annotations or preference reward models, whereas online marketplace transaction prices are readily available and reflect real purchasing behavior, offering potential low-cost supervision. However, transaction prices conflate visual preferences with non-visual factors such as provenance, demand, and competition, making aggregate accuracy insufficient to distinguish model errors, unreliable price signals, and protocol confounds. To address this identifiability challenge, we introduce MarketImage, a diagnostic framework that identifies when transaction prices reflect visual preferences, where they fail, and whether multimodal language models can recover human-supported visual preference signals. MarketImage comprises three components: (i) MarketImageArt, 266 six-image comparison sets with transaction prices and price-blind human rankings; (ii) MarketImageLens, a tie-preserving protocol that partitions 3,990 within-set image pairs into price-human agreement, conflict, and price-tie regions while separately auditing presentation-order effects; and (iii) MarketValuator, six elicitation methods spanning direct comparison, independent scoring, budget constraints, and multi-agent aggregation to evaluate signal recovery by static visual scorers and three multimodal language models. Experiments show that only 24.2% of image pairs have a non-tied price direction, of which 34.7% agree with the human majority. Within this region, HPSv2 leads at 66.4% Recoverable Accuracy; Qwen's budgeted and aggregated variants trail baselines, while GPT interface gains remain statistically unresolved. Thus, transaction prices encode recoverable visual preferences only under limited conditions and should be treated as uncertain proxies rather than ground truth.
https://arxiv.org/abs/2610.41358