paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?

Kun Chen, Haorong Hong, Peizhong Gao, Jianfeng Lin, Tongxu Luo, Yuxuan Xie, Chenxu Liu, Jieling He, Zhongyuan Liu, Zeno Zeng

Recent large language models (LLMs) can operate as coding agents that build complete games from natural language requests. Game development is especially demanding because program logic, visual and audio content, interfaces, interaction and playability must function together in one executable artifact. Measuring this capability therefore requires evaluation of both game product and the development process. Existing benchmarks often assess the game development capabilities of LLMs by evaluating the final artifact or an isolated development stage. Our analysis of complete human-agent development trajectories identifies three stages that together span the lifecycle of game development with a coding agent: initial game generation, bug diagnosis and repair, and optimization over multiple turns. Therefore, we introduce GameXpert-Bench, which operationalizes the three lifecycle stages as three complementary benchmark tracks. GameGen evaluates complete game creation from a single request in an empty workspace. GameFix evaluates diagnosis and repair when defects are reported or left for the agent to discover. GameOpt evaluates cumulative optimization through request chains seeded by real development trajectories between users and agents. We evaluate each track using live game interaction, deterministic behavioral tests, or final product criteria with regression checks. The suite contains 97 generation tasks across 11 genres; 100 repair tasks from 50 game levels verified by humans, each with 19-27 injected bugs; and 17 optimization chains with six turns and 102 requests. Across the three tracks, current agents are more reliable at producing playable foundations and implementing explicit requirements than at discovering defects, verifying runtime behavior, and preserving functionality across changes.

arXiv

GUI-Primitives: Diagnosing Spatial Reasoning Failures in Vision-Language GUI Grounding

Md Abrar Jahin, Md Rizwan Parvez

Computer-use agents ground natural-language instructions in screenshots to locate interface elements, yet existing benchmarks do not isolate whether models bind relational language to the correct element. We introduce GUI-Primitives, a 994-item benchmark of contrastive instruction pairs over seven spatial relations in graphical user interfaces (left/right, above/below, containment, alignment, proximity, list ordinal, occlusion). Each pair holds the screenshot and anchor fixed while changing the relation expression, so the correct target moves between two designated candidates. Five annotators validate a 196-item subset ($κ= 0.94$ well-formedness; $κ= 0.79$ target selection). Nineteen vision-language models reach at most $32\%$ strict point-in-box accuracy. Because models emit unconstrained coordinates, we classify each prediction by the candidate region it falls within. Predictions fall outside both candidates on $60-92\%$ of items. Conditional on falling within a candidate region, target selection reaches 0.82-0.90 for horizontal position, vertical position, proximity, and list ordinal, but does not differ significantly from 0.50 for containment and occlusion: most failures reflect candidate localization rather than relation understanding. Across ten models, benchmark accuracy correlates with ScreenSpot-Pro accuracy (Spearman $ρ= +0.74$), an exploratory association at this sample size. Marking the two designated candidates raises selection accuracy by 35--57 percentage points, an oracle diagnostic that supplies the candidate set rather than a deployable method. We release the benchmark, predictions, and code.

arXiv

Training a Knowledge Base: Supervised Structure Learning for Agent-Curated Document Stores

Yu Pan, Hongfeng Yu

Retrieval-augmented generation treats the document store as a frozen input, and the offline pipelines that do build structure over it build it unsupervised -- a whole corpus indexed at uniform effort, with no signal about which structure a question will need. We instead treat the knowledge base as a non-parametric model trained on (question, answer) pairs: a curator agent answers a supervised question against the current store, is shown the gold answer, then edits the store. The store carries forward, and we evaluate the curated store with a test set, on two contamination-free benchmarks: KBGym, a fictional-universe generator we release, and PhantomWiki. Generalization is probed with four question groups of decreasing overlap with the training set: the trained questions themselves, and unseen questions sharing both of their keys with training, one key, or neither. The curated store's advantage grows with overlap -- from parity where no key was shared, through +0.176 F1 where both keys were, to 25% fewer actions at +0.294 F1 on the trained questions, the one cell significant on both benchmarks -- while matching HippoRAG's gains with 1,913 links against its 196,112: per point of corpus covered, 1.5x the action saving and 2.1x the accuracy gain. Accuracy rises steadily with the share of the corpus the indexes cover, so training on more questions widens coverage, and with it the generalization.

arXiv

Do Large Language Models Perform Well on Comprehending Poetic Logic in Modern Chinese Poetry?

Tian Lan, Shanshan Wang, Zehua Duo, Jiang Li, Guanglai Gao, Derek F. Wong, Xiangdong Su

Large Language Models (LLMs) have achieved significant progress across a wide range of natural language processing (NLP) tasks, yet their ability to understand literary texts, particularly modern Chinese poetry, remains largely unexplored. The unique literary characteristics of modern Chinese poetry necessitate a distinct form of reasoning for effective comprehension. Unlike conventional texts that convey clear information, the unique "poetic logic" of modern Chinese poetry requires a holistic reasoning approach that goes beyond superficial semantic analysis to be understood. However, current evaluation paradigms largely ignore this critical dimension. To address this gap, we propose Peony, the first benchmark specifically designed for evaluating the poetic logic of modern Chinese poetry. We define poetic logic as four tasks across three levels, namely stanza, line, and imagery, and systematically evaluate and analyze six mainstream LLMs based on Peony. We evaluate these models under both non-thinking and thinking configurations. The experimental results reveal the limitations of current LLMs in understanding the poetic logic of modern Chinese poetry and validate the effectiveness and necessity of Peony. Our data and code will be available.

arXiv

Convergence in Science, Divergence in Religion: Calibrated Framing Differences Across Wikipedia's Language Editions

Hung-Hsuan Chen

When Wikipedia's language editions describe the same concept, how differently do they frame it? Prior work measures coverage gaps between editions; we measure framing distance for matched concepts. We analyze 2,799 valid articles from 3,000 possible concept-language observations, spanning 150 Wikidata-anchored concepts, 20 language editions, 4 domains, and a calibration set. Raw embedding distances reflect both content differences and how well the encoder aligns each language pair. Even among calibration concepts with stable cross-cultural denotations (e.g., chemical elements, numbers, colors), the largest language-pair mean distance is 3.6 times the smallest, and distances are typically smaller within language families. We define a baseline-adjusted distance (calibrated distance): the distance between two language versions of a concept minus the mean distance for calibration concepts in the same language pair. This adjustment substantially reduces pair-specific alignment differences and the language-family pattern. Across three multilingual encoders (LaBSE, multilingual MPNet, and CMLM), scientific articles align more closely than calibration articles, and all three rank religion first and science/technology last. Concept-level rankings are highly consistent across encoders (Spearman rho=0.75-0.79 for MPNet and CMLM relative to LaBSE). Religion lies significantly above the calibration baseline under LaBSE. Within politics, divergence concentrates on concepts such as censorship and refugee, while democracy and human rights are among the most aligned. Code, data, and per-language-pair calibration baselines are released.\footnote{https://github.com/hhchen1105/cross-linqual-concept}

arXiv

PatchGate: Narrowing the Verbalization Gap with Intrinsic Object Inventories in Frozen Vision-Language Models

Jihyung Ko, Eunji Jung, Hyeongsub Kim, Ziseok Lee, Jae Won Cho, Sanghyun Jo, Kyungsu Kim

Reliable image captioning in Vision-Language Models (VLMs) requires captions to be both precise and complete, avoiding unsupported object mentions while covering visible objects. Existing training-free methods primarily address the former requirement, suppressing unsupported object words by intervening on model-predicted mentions during generation. Because they operate only on objects the model is already likely to mention, visible objects omitted from the output remain difficult to recover. We propose PatchGate, a training-free framework that extracts prompt-free object evidence intrinsic to a frozen VLM before generation and uses it to narrow the gap between an intrinsic object set and final object mentions. In the first stage, Visual Evidence eXtraction (VEX) reads patch-level lexical evidence from the latter half of LM decoder layers and constructs an image-conditioned object set without any task prompt. In the second stage, Visual-Evidence Inclusion-Exclusion Decoding (VIED) uses this object evidence to calibrate decoding logits, promoting evidence-supported but under-verbalized objects and suppressing weakly supported but over-verbalized objects. On AMBER, PatchGate improves both sides of object-level reliability, increasing visible-object coverage from 49.4 to 56.0 (+13.4%) and reducing object hallucination by lowering CHAIR from 7.5 to 6.6 (-12.0%), without external detectors or fine-tuning and with one extra forward pass.

arXiv

MCite-RL: Towards Reliable Multimodal RAG via Citation-enhanced Agentic Reinforcement Learning

Suifeng Zhao, Zida Liu, Xinyu Lei, Lei Sun, Jun Gao, Sujian Li

Multimodal Retrieval-Augmented Generation (RAG) with visual citation is crucial for ensuring the traceability and verifiability of MLLMs. However, current RAG and SFT-based methods struggle to achieve robust cross-modal reasoning, causing imprecise visual citations or decoupling between the citation and the generated answers. To address these limitations, we propose MCite-RL, a citation-enhanced agentic reinforcement learning framework designed for reliable multimodal RAG. MCite-RL introduces an Agentic Refinement module for visual citation that employs iterative retrieval, reasoning, and recursive cropping to progressively narrow the search space, transforming citation into a dynamic, evidence-driven reasoning process rather than a static step. Furthermore, we incorporate a Citation-enhanced Reward mechanism that integrates both process-level and outcome-level feedback within a reinforcement learning paradigm to jointly optimize answer accuracy and source traceability. Extensive experiments on benchmarks such as Wiki-VISA, FinRAGBench-V, and MMLongBench-Doc demonstrate that MCite-RL effectively achieves the joint optimization of citation precision and answer quality.

arXiv

More Computational Resources Do Not Ensure Higher Scholarly Impact: Evidence from Leading NLP Conference Papers

Shuai Chen, Tong Bao, Jitong Peng, Chengzhi Zhang

Computational resources are increasingly central to NLP research, but how closely reported GPU capability aligns with scholarly impact remains unclear. We analyze 13,921 ACL, EMNLP, and NAACL main-conference papers published between 2020 and 2025, using GPU resources as our operational measure of computational resources. From full texts, we extract GPU models and counts, standardize each paper's largest reported configuration into a comparable hardware-capability measure, and link these data to citation, award, topic, and institutional metadata. GPU reporting became more common but remained incomplete, while reported capability increased mainly through newer hardware generations and medium-scale multi-GPU configurations. Resource concentration substantially exceeded impact concentration: the annual top 20% of GPU-quantifiable papers accounted for 83.9%-89.9% of reported GPU capability, but only 27%-32% of citations and 20%-33% of paper awards. In adjusted models, a tenfold increase in aggregate reported GPU capability was associated with a 3.52-percentage-point increase in within-NLP topic-year citation percentile, but increased model R^2 by only 0.0042. GPU count showed more consistent positive associations with citation and award outcomes than newer hardware generation. Overall, reported GPU resources are associated with scholarly impact but provide little standalone explanation of research influence.

arXiv

Lexical Coupling in GUI Element Grounding: Sentence Embeddings Track Labels across Mobile and Web

Qijia Chen, Giulio Jacucci

GUI grounding evaluations that expose UI elements as text metadata often treat high instruction-element embedding similarity as evidence of semantic grounding. Across three mobile and web benchmarks, we show that this interpretation is frequently confounded by visible-label recovery. Lexical baselines remain competitive at top-1, label-poor targets remain weak for text-only methods, and encoder top-1 hits are predictable from lexical rank, candidate-pool size, and label type. We evaluate each action as a same-screen ranking task, comparing five off-the-shelf single-vector encoders with lexical baselines. Encoders recover some lexical misses, but deployable fusion gains are much smaller than target-aware oracle gains. These findings show that embedding-based evaluations can conflate visible-label recovery with semantic GUI grounding. Embedding-based evaluations should therefore report lexical baselines, label-type stratification, and deployable-fusion diagnostics. Our released repository provides analysis scripts and detexted per-step panels: https://github.com/qijia123/lexical-coupling-release.

arXiv

No One Model Catches Every Harm: Benchmarking Content Moderation Across Safety Scenarios

Afshin Orojlooyjadid, Hitesh Patel

Large Language Models (LLMs) are increasingly deployed in real-world applications, yet they remain vulnerable to generating harmful content. From adversarial jailbreaks that bypass safety filters to implicit hate that evades detection, the range of risks these models pose continues to grow. While both specialized content moderators and general-purpose LLMs are being used as safety layers, the question of which model is best suited for which type of harmful content remains unanswered. We present the most comprehensive evaluation of LLM safety capabilities to date, systematically testing \textbf{53} models across \textbf{11} datasets that we organize into four distinct categories. Our evaluation under both prompt-only and prompt-response settings uncovers critical blind spots: large frontier models that lead on one category fall significantly behind smaller, specialized alternatives on others, and real-world conversational safety remains largely unsolved across all model families. These findings challenge the assumption that scale alone ensures safety, and provide the community with a structured framework for informed model selection.

arXiv

Evaluation Awareness in Language Models: Representation, Verbalization, and Control

Farzaneh Heidari, Amin Memarian, Guillaume Rabusseau

Both capability and safety benchmarks rest upon the assumption that the behavior of language models undergoing a test is informative about their behavior in deployment. This assumption can fail, should models infer that they are being evaluated and condition their response on such context. This hypothesis, termed ``evaluation awareness'', has been observed in frontier and open-weight language models alike. We provide a systematic study of this phenomenon, by probing for it across six language models (from four families and three sizes) and three metrics. More precisely, we examine whether (i) being under evaluation is linearly represented within the models' activations space, (ii) it is verbalized in their output tokens (as scored by an LLM-as-judge), and (iii) steering causally affects their behavior. For the open-checkpoint Olmo models, we further test these measures at every training stage. In doing so, we report that evaluation awareness is linearly decodable from the residual streams of every model (best AUROC $\geq 0.7$). By contrast, these representations align only in part with verbalization: their correlations and mutual information are nonzero in some settings, yet vary substantially across models, layers, and readout choices. Nevertheless, steering along probe-derived directions can shift the verbalization scores. Finally, a comparison across the Olmo checkpoints reveals that evaluation awareness is already present within base models, becomes amplified throughout the stages of supervised fine-tuning, and remains stable thereafter---unlike the effects of steering, that grow more pronounced at every successive training stage. These results show the need for evaluations to account for the disjunction between what models represent internally, what they verbalize, and their steering.

arXiv

Learning to Look Again: Loss-Gap Supervision for Free-form Crop Routing in Vision-Language Models

Jinchang Zhu, Rong Fu, Yi Ding, Chenghao Wu, Ying Liu, Menglin Yang

Vision-language models (VLMs) fail many detail-centric questions for a concrete reason: the answer is visible in the image, yet lost after the image is compressed into a low-resolution global view. Allocating more visual tokens to every query improves some OCR and document cases, but it spends computation indiscriminately and can disturb tasks that rely on global context. We propose GapSight, a framework for learning visual re-reading: a VLM first takes a global glance, then selectively returns to a free-form region when the question calls for local evidence. The supervision comes from the target model's own failure signal. Offline, we compare answer loss or multiple-choice option margin under a global-only view and candidate crop-augmented views; crops that improve the target answer become model-specific review labels. A lightweight free-form crop router distills these labels into a one-shot inference policy that predicts whether to review, expected utility, and a continuous crop box from the global state. Across LLaVA-1.5-7B, InternVL2.5-8B, and Qwen2-VL-2B-Instruct, GapSight improves the Base no-zoom baseline on six benchmarks spanning OCR, documents, charts, infographics, VStarBench, and MME-RealWorld-Lite. On InternVL2.5-8B, GapSight raises the six-benchmark average from 52.25 to 64.29, above CropVLM (57.16), ViCrop (55.84), and ZoomRefine (54.43). Mechanism analyses show that the router rescues concrete wrong answers, adapts its action rate by task, and forms a favorable token-performance profile. These results position loss-gap supervision as a practical route to teaching VLMs when and where to look again.

arXiv

FCPRAG: Fusion-Controller Parametric Retrieval-Augmented Generation for Stable Multi-Passage LoRA Injection

Jinchang Zhu, Jindong Li, Yi Ding, Xiaojian Nie, Rong Fu, Shuangyong Song, Haowei He, Menglin Yang

Parametric retrieval-augmented generation (PRAG) injects retrieved evidence into a large language model (LLM) through passage-specific LoRA adapters, reducing reliance on long in-context prompts. When multiple passages are retrieved for the same query, however, evidence-level fusion becomes a bottleneck: equal-weight merging can amplify weak or conflicting evidence, and translating retrieval signals into fusion weights often requires fragile global tuning. We propose FCPRAG, a fusion-controlled parametric RAG framework that adds a lightweight controller for retrieval-conditioned, sample-level adapter fusion. The controller predicts per-passage fusion scores together with sample-level calibration signals, including a mixing gate and an adaptive temperature, enabling fusion that stays selective under informative retrieval signals and conservative under uncertainty. FCPRAG is trained with merge-aware supervision derived from each adapter's marginal contribution within a multi-adapter merge, using training data only. We further show that a single dataset-level temperature is suboptimal under heteroscedastic retrieval uncertainty, motivating sample-level adaptation. Experiments on HotpotQA, 2WikiMultiHopQA, PopQA, and ComplexWebQuestions (CWQ) across three LLM backbones show that FCPRAG consistently improves F1 over standard RAG and parametric RAG baselines, with gains of up to 4.65% on 2WikiMultiHopQA and 7.55% on CWQ, while also reducing tuning cost and improving robustness under retrieval perturbations.

arXiv

Architecture as Capability Equalizer for Coding Agents

Arquimedes Canedo

LLM-based coding agents generate complete software systems from high-level descriptions, yet little is known about how the format of architecture specifications affects the quality of generated code or whether this effect depends on model capability. We present a controlled experiment comparing five informationally equivalent specification formats (informal prose, Mermaid diagrams with constraints and ADRs, OpenAPI, C4/Structurizr DSL, and TypeScript interface contracts with ArchUnit-style rules) across six models from three vendor families (Anthropic Claude, OpenAI GPT, Google Gemini). Across 90 multi-turn agent trials, specification format shows a strong format x model interaction. On the strongest models (Sonnet 4.6, GPT-5), format barely matters (quality spread 0.17-0.92). On weaker models, format produces spreads of 0.83-2.42 points, with code-proximate formats (OpenAPI, TypeScript contracts) recovering most of the capability gap. Mid-tier models can consume more tokens than frontier models for worse output when they enter compilation debugging loops that stronger models avoid. Self-validation rates collapse from 100% (Sonnet) to 0% (Gemini Flash) across the capability spectrum. TypeScript contracts triple API route coverage for the weakest model (33% to 100%). Structured architecture specifications serve as a capability equalizer, with value inversely proportional to model strength and the largest returns for cost-optimized deployments.

arXiv

LëtzCross: A Cross-Lingual Page-Level Benchmark for Multimodal Retrieval over Luxembourgish Documents

Omar El Bachyr, Fred Philippy, Laura Maria Bernardy, Saad Ezzini, Jacques Klein, Tegawende Bissyande

Recent page-image retrievers such as ColPali have improved retrieval over visually rich documents, yet little is known about how they behave in cross-lingual, low-resource settings. We introduce LëtzCross, a benchmark for cross-lingual page-level retrieval over Luxembourgish PDF documents, with document pages indexed as images and queries provided in English, French, German, and Luxembourgish. The benchmark combines text-focused QA pairs with visually grounded QA pairs, covering both textual and visual retrieval needs in PDF-based RAG. We use LëtzCross to compare OCR-based text-only retrievers with ColPali-style page-image retrievers and find that the latter perform better across query languages in this system-level comparison. We also examine single-language and multilingual fine-tuning. Fine-tuning transfers across query languages, with French yielding the highest mean performance on Luxembourgish queries among the single-language settings. In the multilingual setting, including Luxembourgish gives the strongest results and substantially improves retrieval for Luxembourgish queries.

arXiv

The Plan, Not the Decoder: Diagnosing and Repairing Compositional Failure in Reasoning-Augmented Text-to-Image Generation

Ashritha Gonuguntla

Reasoning-augmented text-to-image models such as GoT-R1 emit an explicit textual plan - object names, attributes, and bounding boxes - before generating image tokens. When such a model fails a compositional prompt, is the plan wrong, or is the plan right and the decoder unfaithful? Because the plan is machine-readable it can be edited before decoding, which makes the two separable. We first validate the ruler. Swapping the two bounding boxes inside the model's own chain demonstrably flips the generated layout: detector-based accuracy falls 0.75 -> 0.48 (p<1e-3), while a widely used VQA-based spatial metric rises. A five-rater human study agrees with the detector on 81% of items and with the VQA judge on 57%. All spatial results therefore use geometric scoring. Under sound measurement the decoder is a faithful executor: 94% of generated layouts realize the planned relation, and object-box binding survives reordering of the plan's object segments. The planner is the bottleneck. It writes wrong relations for phrasing-dependent reasons - 98% accuracy on "left" against 54% on "right" for semantically identical layouts, a raster-order bias we isolate with a mention-order control - and cluttered geometry that the decoder faithfully reproduces. Editing the plan therefore fixes the image without retraining: symbolic verification with resampling gives +5.0 points (p<1e-3), minimal in-place repair +6.0 (p=.02), rewriting only box geometry +10.7 (p<1e-4), and replacing the plan outright +13.3 (p=1e-4). Gains are indifferent to the plan's prose style and to its likelihood under the planner, but not to its geometry. Modular planner-decoder designs are therefore viable, provided the plan is internally consistent: box-text contradictions induce object duplication and identity fusion. We release the plan-fidelity evaluation protocol, all plans, and 12k generated images.

arXiv

From Association to Causation: Improving Retrieval Precision of Retrieval-Augmented Generation via Causal Relations and an Attention Mechanism

Jing Liu, Yongxing Qi, Muchen Jiang, Chengnan Hu, Qingqing Peng, Haoming Wang, Yuqing Wang, Yang Yu, Xu Zhang, Ting Wu

Retrieval-Augmented Generation (RAG) grounds LLM generation on retrieved documents, but the standard terminal retrieval stage--dense-vector similarity, optionally followed by reranking--often returns documents that share keywords with the query without containing the needed information, a failure mode that grows with the knowledge base. We trace it to a conceptual gap: similarity captures only associational relations, whereas the documents that matter are linked to the query causally. We model the terminal retrieval stage with a causal graph grounded in Reichenbach's common cause principle: the keywords shared by the query and a retrieved document form a latent common cause A, and the document's residual keywords form a latent set B linking the document to the ideal output. Since a retrieved document is a collider (A -> d <- B), retrieval itself opens an associational path between the query and B, which licenses a training-free, attention-style re-scoring rule: the cosine similarity between the query embedding and the weighted centroid embedding of B. Unlike causality-enhanced RAG variants that model causal relations inside the knowledge content, our graph models the causal structure of the retrieval process itself. On a real 471-document enterprise knowledge base, the method promotes a relevant guideline from rank 6 to the top 3; on a controlled diagnostic corpus reproducing the keyword-stuffing regime, it improves the mean target rank from 2.88 to 1.25, while a trained cross-encoder reranker barely helps (2.63). Conversely, on three BEIR benchmarks the score underperforms the similarity baseline, delineating the applicability boundary: the method guards the keyword-stuffing regime of growing proprietary knowledge bases and complements neural rerankers; a corpus-level calibration gate selects the correct regime with >= 95% reliability. A fully local testbed demonstrates deployability.

arXiv

Multi-Agent Orchestration with the Common-Sense Reasoning Capabilities of LLMs for Autonomous Driving

Mehdi Azarafza, Faezeh Pasandideh, Ali Ehteshami Bejnordi, Stefan Henkler, Achim Rettberg

Autonomous vehicles require robust perception and decision-making capabilities to operate in diverse and unseen scenarios. While reinforcement learning and rule-based methods can provide effective control and safety mechanisms, their performance may degrade in situations requiring contextual reasoning. Large Language Models (LLMs) have demonstrated strong capabilities in understanding multimodal information and generating contextual reasoning, however, their use for direct vehicle control can introduce latency and hallucination risks. To address these limitations, a hybrid framework is proposed. This system uses an orchestrator to coordinate PPO-trained reinforcement learning and PID control, with LLM common-sense reasoning applied throughout the framework. LLM reasoning is further employed iteratively to refine the RL reward function for dynamic driving environments. The proposed framework is evaluated in highly randomized CARLA scenarios under diverse environmental and traffic conditions. The results demonstrate the potential of integrating LLM-based reasoning with conventional autonomous driving methods while retaining structured control and safety mechanism.

arXiv

MileGPO: Milestone Inference with Local Evidence for Graph-Based Policy Optimization of Long-Horizon LLM Agents

Bo Qian, Yuting Wu, Shuang Zeng, Huaiyu Wan, Dalin Zhang, Jiqiang Liu

Credit assignment is challenging in long-horizon agentic reinforcement learning, where supervision often comes only from final rewards. Existing methods refine trajectory-level signals into step-level credits through step grouping or graph-based advantage estimation, but can overlook meaningful intermediate milestones. We propose MileGPO (Milestone Inference with Local Evidence for Graph-Based Policy Optimization), which derives process-level credit from grouped on-policy rollouts through three designs. Milestone Discovery identifies candidate milestones on successful rollouts and recurring traps on failed ones. Reliability-Calibrated Shaping (RCS) weights these candidates by outcome-based confidence, strengthening reliable milestones and traps while down-weighting uncertain ones. Progress-Contrastive Calibration (PCC) further tests whether a candidate reflects local progress and whether its incoming transition outperforms observed alternatives from the same state. MileGPO requires neither auxiliary models nor additional environment interaction. Experiments on ALFWorld and WebShop show state-of-the-art performance and a small in-distribution to out-of-distribution gap on ALFWorld. Ablations and credit diagnostics indicate that reliability weighting, local progress, and same-state branch evidence complement milestone discovery and resolve ambiguous intermediate credit.

arXiv

Agentic-DuplexGen: Decoupling Content, Timing, and Acoustics for Synthetic Dialogue Speech

Pengcheng Wang, Sheng Li, Jiyi Li, Takahiro Shinozaki

Synthetic conversational speech has become an important resource for developing and evaluating conversational speech systems. However, existing dialogue synthesis pipelines typically generate dialogue content first and then insert interruptions, overlap, and backchannels using handcrafted markers or timing rules, making conversational timing prescribed rather than interaction-driven. We present Agentic-DuplexGen, a dialogue synthesis framework that explicitly decouples content, timing, and acoustics. An LLM first generates the dialogue script, and then two full-duplex conversational models perform the script while listening to each other in real time. This allows conversational timing to emerge naturally while preserving the scripted content. Finally, a high-fidelity text-to-speech model re-renders the interaction without altering its timing. As a demonstration of the proposed framework, we construct a patient--clinician conversational speech corpus with construction-time annotations, including word timestamps, speaker activity, overlap regions, and interaction events. Experimental results show that the proposed framework produces conversational dynamics closer to real dialogue than conventional stitching-based synthesis.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.