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

Knowledge Graph-Enhanced Zero-Shot Topic Classification: A Multi-Strategy Comparative Study

Shahana Akter, Yatharth Vohra, Ankita Shukla, Souvika Sarkar

Multi-label topic classification without labeled training data is a challenging task, specially when documents contain complex relational information. We present a zero-shot multi-label topic classification framework and systematically investigate how per-article knowledge graph augmentation affects its performance. The base framework classifies topics in documents without labeled training data and has four variants: article-only classification, keyword-enhanced classification, and self-consistency decoding variants of both. Then, we augment each base variant with per article knowledge graph. This graph is extracted from the input document through a pipeline similar to KGGen based on subject-predicate-object triples. We test all eight methods, four base and four graph augmented on fifteen LLMs and eight multi-label datasets across different domains. For the base framework, keyword-enhanced classification (AK) is the best performing method, and six out of fifteen LLMs surpass the sentence-encoder baseline. Graph augmentation has positive and negative impacts on small and large models, respectively. This shows that larger models already contain enough relational information from pretraining. Furthermore, the self-consistency decoding variant does not show performance improvements in any experiment while increasing computation costs about fivefold.

arXiv

Persona Prompting in Multimodal Urban Perception: Descriptive Convergence and Interpretive Variation

Neemias da Silva, Matt Ratto, Myriam Delgado, Rodrigo Minetto, Daniel Silver, Thiago H Silva

This study examines how persona prompting shapes language generated by two multimodal large language models in urban perception, a setting for examining subjective interpretations of shared visual evidence. We organize outputs into three functional levels: descriptive grounding (captions), intermediate semantic layer (perception tags), and interpretive framing (justifications). Using approximately 60,000 persona-conditioned annotations per model from Qwen3-VL-8B and Gemma-4-E4B-it, we find that captions converge strongly across persona profiles and show only small attribute-associated differences. Justifications vary substantially more: economic status produces the largest difference in both models, with political orientation and personality also prominent. Paired image-level comparisons confirm larger justification than caption differences for these three attributes. For perception tags, personas sharing the same attribute level produce more similar tag sets than personas with different attribute levels, with the largest separation observed for economic status. Exploratory topic analysis further reveals persona-specific evaluative emphasis. Across models, profile-pair similarity patterns are strongly correlated for all three output types, although agreement is lowest for justifications. Overall, persona prompting affects interpretive framing more strongly than descriptive grounding.

arXiv

To Memorize or to Retrieve: Scaling the Interaction Between Pretraining and Retrieval

Karan Singh, Michael Yu, Varun Gangal, Zhuofu Tao, Sachin Kumar, Emmy Liu, Steven Y. Feng

Retrieval-augmented generation (RAG) improves language model (LM) performance by providing relevant context at test time for knowledge-intensive situations. In this work, we systematically study the trade-off between pretraining and retrieval by training OLMo-2-based LMs ranging from 30M to 3B parameters on up to 100B DCLM tokens, while varying pretraining data scale, retrieval store size, and retrieval store source (pretraining vs. new data) across reasoning, scientific QA, and open-domain QA benchmarks. We find that retrieval gains depend on model capacity and pretraining exposure and are strongly front-loaded, with a median 91% of the largest observed improvement realized by one retrieval token per model parameter. However, the interaction is objective-dependent: smaller models gain more in gold-answer perplexity, whereas larger, more-pretrained models gain more in accuracy. Retrieval from previously seen data also preserves most of the held-out retrieval gain. Retrieval is therefore a task-, regime-, and metric-dependent complement to parametric learning whose value also depends on datastore size and information novelty. Overall, this motivates the explicit partitioning of data between internalization and external access for LM design.

arXiv

GraphWalker: Agentic Knowledge Graph Question Answering via Synthetic Trajectory Curriculum

Shuwen Xu, Yao Xu, Jiaxiang Liu, Chenhao Yuan, Wenshuo Peng, Jun Zhao, Kang Liu

Agentic knowledge graph question answering (KGQA) requires an agent to iteratively interact with knowledge graphs (KGs), posing challenges in both training data scarcity and reasoning generalization. Specifically, existing approaches often restrict agent exploration: prompting-based methods lack autonomous navigation training, while current training pipelines usually confine reasoning to predefined trajectories. To this end, this paper proposes GraphWalker, a novel agentic KGQA framework that addresses these challenges through Automated Trajectory Synthesis and Stage-wise Fine-tuning. GraphWalker adopts a two-stage SFT training paradigm: First, the agent is trained on structurally diverse trajectories synthesized from constrained random-walk paths, establishing a broad exploration prior over the KG; Second, the agent is further fine-tuned on a small set of expert trajectories to develop reflection and error recovery capabilities. Extensive experiments demonstrate that our stage-wise SFT paradigm unlocks a higher performance ceiling for a lightweight reinforcement learning (RL) stage, enabling GraphWalker to achieve state-of-the-art performance on CWQ and WebQSP. Additional results on GrailQA and our constructed GraphWalkerBench confirm that GraphWalker enhances generalization to out-of-distribution reasoning paths. The code is publicly available at https://github.com/XuShuwenn/GraphWalker.

arXiv

PRISM-$Δ$: Differential Subspace Steering for Prompt Highlighting in Large Language Models

Yuyao Ge, Shenghua Liu, Yiwei Wang, Baolong Bi, Lingrui Mei, Jiayu Yao, Jiafeng Guo, Xueqi Cheng

Prompt highlighting steers a large language model to prioritize user-specified text spans during generation. A key challenge of existing Key-editing approaches is extracting steering directions that capture the difference between relevant and irrelevant contexts, rather than shared structural patterns common to both. We propose PRISM-$Δ$ (Projection-based Relevance-Informed Steering Method), which decomposes the difference between positive and negative cross-covariance matrices to maximize discriminative energy while eliminating shared directions. Each attention head receives a continuous softplus importance weight, letting weak-but-useful heads contribute at reduced strength. The framework extends naturally to Value representations, capturing content-channel signal that Key-only methods leave unused. Across four benchmarks and five models, our methods match or exceed the best existing method on 19 of 20 configurations, with relative gains up to +13.0%, while halving the fluency cost of steering. Our methods also scale to long-context retrieval, outperforming the best existing method by up to +5.1% relative gain. PRISM-$Δ$ is compatible with FlashAttention and adds negligible memory overhead.

arXiv

SciTaRC: A Plan-Annotated Scientific Tabular QA Benchmark for Language Reasoning and Complex Computation

Hexuan Wang, Yaxuan Ren, Srikar Bommireddypalli, Shuxian Chen, Adarsh Prabhudesai, Rongkun Zhou, Elina Baral, Philipp Koehn

We introduce SciTaRC, an expert-authored benchmark for question answering over scientific tables that targets composite, multi-step reasoning. To enable fine-grained diagnostic analysis beyond end-task accuracy, SciTaRC pairs each question with a manually constructed reasoning plan and explicit complexity metrics. State-of-the-art models fail on at least 23% of these questions, while highly capable open-weight models like Llama-3.3-70B collapse on 65.5% of the benchmark. Error analysis shows that, in zero-shot settings, failures are driven primarily by question comprehension, where models misinterpret the scientific query and derive the wrong reasoning objective. To determine whether overcoming this gap is sufficient, we use the structured plans to decouple strategy formulation from execution. Surprisingly, providing oracle step-by-step plans yields only limited gains and fails to eliminate the performance gap. This reveals a substantial execution bottleneck: both natural language and code-based methods struggle to reliably carry out long-horizon computational chains over structured data. Ultimately, SciTaRC serves as a rigorous diagnostic testbed for studying both planning and execution in scientific table reasoning.

arXiv

Autorubric: A Unifying Framework for Rubric-Based LLM Evaluation on Non-Verifiable Tasks

Delip Rao, Chris Callison-Burch

Rubric-based LLM judges have become indispensable for evaluating and optimizing systems on non-verifiable tasks, where success cannot be reduced to exact programmatic checks. Yet the underlying judges remain vulnerable to position bias, stochastic inconsistency, criterion conflation, forced judgments under uncertainty, and model-dependent calibration. Rubrics structure evaluation but do not eliminate these failures; they add consequential choices about criterion design, scale types, weighting, aggregation, abstention, calibration, and reliability measurement. Despite extensive research across LLM evaluation, educational measurement, and psychometrics, the relevant methods remain scattered across papers and partial implementations. Researchers therefore pay a reinvention tax, repeatedly rebuilding evaluation machinery instead of accumulating knowledge on a common substrate. We introduce Autorubric, an open-source framework that makes rubric and judge choices explicit, reusable, and auditable. Through a unified API, it supports atomic evaluation of mixed criterion types alongside configurable bias mitigations, calibration, ensembling, abstention, and psychometric diagnostics. Evaluations spanning college chemistry grading, deep-research systems, and CHARM-100---a new mixed-criterion chatbot benchmark---reveal criterion-specific failures, systematic judge-family differences, and configuration effects that do not support a universal mitigation stack. We further demonstrate how per-criterion scores and explanations can support agent skill revision and reward modeling for reinforcement learning. By providing shared infrastructure from measurement through optimization, Autorubric gives the community a common basis for comparing methods, reproducing evaluation choices, and accumulating evidence across studies.

arXiv

InfMem: Learning System-2 Memory Control for Long-Context Agent

Xinyu Wang, Mingze Li, Peng Lu, Xiao-Wen Chang, Lifeng Shang, Jinping Li, Fei Mi, Prasanna Parthasarathi, Yufei Cui

Reasoning over ultra-long documents requires synthesizing sparse evidence scattered across distant segments under strict memory constraints. While streaming agents enable scalable processing, their passive memory update strategy often fails to preserve low-salience bridging evidence required for multi-hop reasoning. We propose InfMem, a control-centric agent that instantiates System-2-style control via a PreThink-Retrieve-Write protocol. InfMem actively monitors evidence sufficiency, performs targeted in-document retrieval, and applies evidence-aware joint compression to update a bounded memory. To ensure reliable control, we introduce a practical SFT-to-RL training recipe that aligns retrieval, writing, and stopping decisions with end-task correctness. On ultra-long QA benchmarks ranging from 32k to 1M tokens, InfMem consistently outperforms MemAgent across backbones. Specifically, InfMem improves average absolute accuracy by 10.17, 11.84, and 8.23 points on Qwen3-1.7B, Qwen3-4B, and Qwen2.5-7B, respectively, while reducing inference time by 3.9x on average and by up to 5.1x through adaptive early stopping. Code is available at https://github.com/UCMP13753/InfMem.

arXiv

From Chains to DAGs: Probing the Graph Structure of Reasoning in LLMs

Tianjun Zhong, Linyang He, Ziyang Li, Nima Mesgarani

Recent progress in large language models has renewed interest in how multi-step reasoning is represented internally. While prior work often treats reasoning as a linear chain, many reasoning problems can be more naturally modeled as directed acyclic graphs (DAGs), where intermediate conclusions branch, merge, and are reused. Whether such graph structure is reflected in model internals remains unclear. We introduce Reasoning DAG Probing, a framework for testing whether LLM hidden states linearly encode properties of an underlying reasoning DAG. We formalize each premise, intermediate conclusion, and final answer as a DAG node, and train lightweight probes to predict node depth, pairwise distance, and adjacency from hidden states. Using these probes, we analyze the layerwise emergence of DAG structure, reconstruct approximate reasoning graphs, and evaluate controls that disrupt reasoning-relevant structure. Across logical, mathematical, and code reasoning benchmarks, we find that DAG structure is meaningfully encoded in LLM representations: recoverability peaks in intermediate layers; later layers preferentially recover deeper nodes and longer-range dependencies; larger models exhibit stronger DAG recoverability. During autoregressive generation, post-trained models exhibit clearer, progressively strengthening DAG structure, which broadly anticipates answer correctness trends. These findings suggest that LLM reasoning is not purely sequential, but exhibits measurable internal graph structure.

arXiv

Diagnostic-Driven Layer-Wise Compensation for Post-Training Quantization of Encoder-Decoder ASR Models

Xinyu Wang, Ziyu Zhao, Yajie Luo, Yihong Wu, Liheng Ma, Jingrui Tian, Lei Ding, Xiao-Wen Chang, Peng Lu

Layer-wise post-training quantization reconstructs each layer from inputs already altered by the quantized prefix. QEP compensates for this drift with one model-wide coefficient, conflating the model-level operating point with residual variation across layers. We present FADE, which constructs layer-specific coefficients from normalized round-to-nearest distortion and a heuristic calibrated-solver response. It requires no training or per-model coefficient search and adds no inference-time operation. We evaluate seven Whisper, Moonshine, and Qwen3-ASR models at 3 and 4 bits on four English ASR benchmarks. Across 38 settings, FADE lowers mean word error rate relative to fixed QEP-0.5 in 31, although a development-tuned global coefficient recovers much of this gap. The largest absolute reductions occur in 3-bit settings whose final error remains too high for practical use; these results measure collapse mitigation rather than deployable accuracy. In two lower-WER 3-bit cases, FADE reduces the tuned-global result from 3.67 to 3.10 and from 13.03 to 11.63. Most 4-bit differences from the tuned control are within a descriptive tolerance, and one reverses. Paired reruns and within-seed permutations on an outcome-informed subset support assignment sensitivity in selected cases, but do not estimate a matrix-wide success rate. FADE is therefore a layer-wise alternative when per-model coefficient search is unavailable, not a universal replacement for tuned global compensation.

arXiv

Assessing Factual Music Comprehension in Large Audio Language Models

Daniel Chenyu Lin, Michael Freeman, John Thickstun

Large audio language models (LALMs) leverage multimodal representations to generate open-ended answers to natural language queries about audio. In this paper, we (1) provide empirical evidence that assessment of LALMs using the popular MusicQA dataset fails to measure whether a model's responses about music are factually correct, and (2) develop a new protocol for assessing the music comprehension capabilities of LALMs. Specifically, we propose an evaluation protocol that prompts a LALM for factually verifiable information, and parses its open-ended response into a structured format that can be objectively assessed using Precision, Recall, and F1 scores. Using this protocol, we define a benchmark consisting of six factual information retrieval tasks defined on three diverse datasets: MusicNet, the Free Music Archive, and OverClocked ReMix. We benchmark nine recent LALMs, including frontier models like Gemini and the latest open models like Music Flamingo, and release the suite of evaluation scripts at https://github.com/DCL2004/LALM-Eval to facilitate benchmarking of new LALMs.

arXiv

Beyond cognacy

Gerhard Jäger

Computational phylogenetics has become an established tool in historical linguistics, with many language families now analyzed using likelihood-based inference. However, standard approaches rely on expert-annotated cognate sets, which are sparse, labor-intensive to produce, and limited to individual language families. This paper explores alternatives by comparing the established method to two fully automated methods that extract phylogenetic signal directly from lexical data. One uses automatic cognate clustering with unigram/concept features; the other applies multiple sequence alignment (MSA) derived from a pair-hidden Markov model. Both are evaluated against expert classifications from Glottolog and typological data from Grambank. Also, the intrinsic strengths of the phylogenetic signal in the characters are compared. Results show that MSA-based inference yields trees more consistent with linguistic classifications, better predicts typological variation, and provides a clearer phylogenetic signal, suggesting it as a promising, scalable alternative to traditional cognate-based methods. This opens new avenues for global-scale language phylogenies beyond expert annotation bottlenecks.

arXiv

Large Language Models are Powerful Electronic Health Record Encoders

Stefan Hegselmann, Georg von Arnim, Tillmann Rheude, Noel Kronenberg, David Sontag, Gerhard Hindricks, Roland Eils, Benjamin Wild

Electronic Health Records (EHRs) offer considerable potential for clinical prediction, but their complexity and heterogeneity challenge traditional machine learning. Domain-specific EHR foundation models trained on unlabeled EHR data have shown improved predictive accuracy and generalization. However, their development is constrained by limited data access and site-specific vocabularies. We convert EHR data into plain text by replacing medical codes with natural-language descriptions, enabling general-purpose Large Language Models (LLMs) to produce high-dimensional embeddings for downstream prediction tasks without access to private medical training data. LLM-based embeddings perform on par with a specialized EHR foundation model, CLMBR-T-Base, across 15 clinical tasks from the EHRSHOT benchmark. In an external validation using the UK Biobank, an LLM-based model shows statistically significant improvements for some tasks, which we attribute to higher vocabulary coverage and slightly better generalization. Overall, we reveal a trade-off between the computational efficiency of specialized EHR models and the portability and data independence of LLM-based embeddings.

arXiv

CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversity

Ananya Sahu, Mohit Bansal, Elias Stengel-Eskin

While post-training improves the capabilities of large language models (LLMs), it generally lowers their output diversity and creativity, negatively impacting tasks that explicitly require creativity (e.g., story generation) as well as those that require it implicitly, e.g., reinforcement learning (RL). We instead propose CreativeInstruct, a scalable instruction-tuning method that teaches LLMs to balance creative, base-model-like generations with the quality of post-trained models, by learning to inject special [StartCreativity] spans that bias generation toward creativity. Furthermore, we introduce a structural diversity metric based on graph edit distance, which captures narrative level variation missed by purely lexical and semantic metrics. On narrative generation, CreativeInstruct matches or exceeds the diversity of both multi-model baselines and distilled variants of their outputs, without sacrificing quality or requiring multiple models at inference time. These results are mirrored in our human evaluation, where we find that annotators rate CreativeInstruct generations as more creative than the post-trained LLMs' generations in 70.3% of cases. We also show the benefits of creative models as a substrate for RL: GRPO applied to a CreativeInstruct checkpoint improves by ~4% on AMC and ~5% points on MATH over the same training applied to the post-trained checkpoint.

arXiv

CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG

Gyuwan Kim, Cheoneum Park, Tao Yang

Recent optimization studies on Retrieval-Augmented Generation (RAG) have exploited chunk-level KV cache reuse to avoid processing long retrieved contexts for higher efficiency, while significant information redundancy and noise still remain in the coarse-grained chunks. This paper optimizes the Pareto frontier under low prefill latency constraints while maximizing accuracy by proposing CoinRAG (Contextualized Information Nugget KV Cache Reuse for Long-Context RAG). The name metaphorically reflects our core mechanism: much like assembling small tokens (or "coins") to accumulate a larger value, CoinRAG compositionally reuses offline-computed, fine-grained nugget caches to form a learned contextual representation efficiently in a more semantically relevant but compact manner. Specifically, instead of full-chunk encoding, CoinRAG identifies query-relevant semantic units within retrieved chunks through two-stage retrieval and seamlessly assembles their sliced KV representations with a chunk-level context. Extensive evaluations on LongBench multi-hop question answering tasks demonstrate that CoinRAG significantly reduces operational costs and outperforms the other baselines with a new Pareto frontier and an average 5.3% relative improvement in answer quality (F1) under a standard fast prefill latency budget.

arXiv

SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent

Mingxuan Zheng, Yujin Zhou, Chuxue Cao, Boqin Yin, Yuyao Zhang, Jiapeng Sun, Shuaishuai Gong, Sirui Han, Yike Guo

LLM agents increasingly adapt to recurring tasks by accumulating procedural knowledge in skills. These skills are lightweight, reusable textual artifacts that are loaded into the agent's context without weight updates. Recent methods refine skills through iterative task execution, failure diagnosis, and trajectory-guided text-space updates. However, existing frameworks lack explicit diagnosis--outcome feedback and treat deletion as a generic edit operation rather than a dedicated mechanism for consolidating accumulated knowledge. We introduce SkillProx, a proximal-gradient-inspired forward--backward framework that couples closed-loop diagnostic evolution with utility-aware proximal refinement. Motivated by a composite objective balancing task loss and skill complexity, the forward stage re-executes diagnosis-driven edits on the same task batch, rolls back regressions, and feeds measured outcomes into subsequent diagnoses. The backward stage decomposes the resulting skill into auditable knowledge units, estimates their contributions using a frozen leave-one-out utility audit, and applies validation-gated consolidation, demotion, or removal. Experiments on in-distribution and out-of-distribution benchmarks across multiple backbone LLMs show that SkillProx improves average accuracy by 3.0 percentage points over the strongest gradient-based baseline. Component ablations demonstrate the complementary effects of closed-loop diagnosis and proximal refinement.

arXiv

An Exploratory Evaluation of LLM-Assisted Rewriting of Moderate-Complexity Financial Sentences for DisCoCat-Based Sentiment Analysis

Brian Llinas, Nikos Chrisochoides

Quantum natural language processing (QNLP) provides a grammar-aware framework for text modeling, and Distributional Compositional Categorical (DisCoCat) is one of its theoretically grounded formulations. Prior work on financial sentiment analysis has identified practical limitations of DisCoCat, including parser sensitivity, high simulation cost, and difficulty handling longer sentences. We study an LLM-assisted preprocessing workflow that uses controlled rewriting to compress, simplify, or decompose moderate-complexity financial sentiment sentences into parser-compatible, circuit-efficient variants while preserving sentiment-bearing meaning. We compare prompting strategies, language models, and filtering configurations with the low-complexity-only DisCoCat baseline of Stein et al. At the circuit level, the strongest compression variants reduce average qubit and gate counts by more than 70 percent relative to the raw moderate-complexity subset. Across repeated training runs, GPT-4.1-mini with Prompt B achieves the highest observed mean accuracy, $0.550 \pm 0.035$, compared with $0.521 \pm 0.050$ for the baseline. Larger training splits do not necessarily improve downstream performance; across evaluated configurations, training-split size has a moderately negative association with accuracy (Pearson $r=-0.446$). These results provide exploratory evidence that LLM-assisted rewriting can make some moderate-complexity inputs usable within the evaluated DisCoCat configuration, while highlighting prompt design, filtering, and circuit-aware preprocessing as considerations for more scalable QNLP-based financial sentiment analysis.

arXiv

PsychoAgent: An Affect-Sensitive Cognitive Architecture for Conflict-Aware Memory in LLM Agents

Mohammad Amanlou, Parham Abed Azad, Farbod Davoodi, Mostafa Masumi, Behnam Bahrak, Abdol-Hossein Vahabie

Human-like cognition does not select past experience by topical similarity alone: affective significance and unresolved conflict also shape what becomes accessible. We present PsychoAgent, a cognitive architecture for LLM agents that separates factual and affective memory and integrates both through a conflict-aware executive controller. Affective memories are first filtered by semantic relevance and then re-ranked by salience, preserving topical fit while allowing emotionally important traces to enter the prompt. Across three controlled conflict scenarios, the full architecture retrieved more conflict-critical memories than semantic-affective and single-memory RAG baselines (0.933 vs. 0.500 and 0.667), with a small semantic-similarity cost. Five blinded raters evaluated 27 outputs. After within-rater standardization, the full architecture had the highest overall mean (+0.22 SD), but corrected pairwise differences were not significant. A three-day illustrative trace further shows persistent affect, offline memory recombination, and selective memory reweighting. The findings support affect-sensitive retrieval as an inspectable mechanism for modeling human-like conflict effects in LLM agents.

arXiv

SABRE: Scalable and Automated Benchmarking of VLMs under Stress

Zixuan Lan, Luzhe Sun, Matthew R. Walter, Jiawei Zhou

Vision-language models (VLMs) are improving rapidly, but benchmark development lags behind, making weaknesses hard to identify. Building stress tests is costly: samples must satisfy controlled conditions, remain answerable, and challenge current models. We present SABRE, a scalable, automated pipeline that converts a Test Primer (a Markdown Task Design with Data Schema) into structured specifications, generated or edited images, and question-answer pairs. Automated filtering removes candidates solved by a Filtering VLM, while human review verifies candidate validity and supports annotation correction and localized image repair. We instantiate SABRE-Prior to test whether VLMs follow visual evidence instead of relying on world priors -- learned expectations about familiar objects and scenes. Its 600 images and 1,000 questions span Context (unexpected entities in familiar scenes), Texture (counterfactual materials), Attribute (noncanonical component counts), and Language Elicitation (answers suggested by language but unsupported by the image). Across six VLMs, macro-average accuracy ranges from 17.8% to 31.3% (22.6% mean). A real-image Attribute control is comparably difficult for the Filtering VLM. SABRE-Counting and SABRE-Spatial pilots show that the workflow supports other stress-test settings. These results establish SABRE as a reusable framework for constructing and refreshing VLM stress tests rather than a single fixed benchmark.

arXiv

ResidencyRL: Reinforcement Learning in Simulated Clinical Environments

Valentin Liévin, Samuel Schmidgall, Tim Strother, Alex Bijamov, Akshay Goel, Anil Palepu, Chunjong Park, Vahid Balazadeh, Min Woo Sun, Marius Guerard, Justin Chen, Dave Steiner, Vikram Dhillon, Ibrahim Azar, Akhil Mehta, Nicholas Spetsieris, Shilpan Shah, Maen Abdelrahim, Amit Dahiya, Yun Liu, Katherine Chou, Yossi Matias, Avinatan Hassidim, Dale R. Webster, Quoc V Le, Raia Hadsell, Joelle Barral, Carey Radebaugh, Aleksandra Faust, Shekoofeh Azizi, Mike Schaekermann, Po-Hsuan Cameron Chen, Tao Tu, David Racz, Lin Yang

In medical education, physicians convert academic knowledge into clinical expertise through residency: years of training across thousands of encounters, with diverse sources of feedback and progressively greater autonomy. Much of clinical reasoning relies on the patient encounter, a dialogue in which a clinician elicits history, refines diagnostic hypotheses, and decides management under uncertainty. While large language models (LLMs) excel on static medical benchmarks, methods to optimize the full sequence of clinical decisions remain underdeveloped. We present ResidencyRL, a reinforcement learning (RL) method for training clinical artificial intelligence (AI) agents through simulated multi-turn clinical encounters (up to 60 dialogue turns and 8 tool calls per trajectory). ResidencyRL pairs the policy agent with LLM simulators capable of complex, adversarial behaviors, training against a structured reward aligned to diagnostic accuracy, management quality, communication, documentation, and safety. On held-out evaluations, the ResidencyRL agent improves diagnostic accuracy by 7.0% under adversarial conditions (88.0% vs. 81.0%) and reduces missed red flag rates by 31%, demonstrating rigorous mitigation of premature closure. Blinded expert clinicians validated these gains, preferring the trained agent in 87.6% of side-by-side comparisons. The procedural competencies transfer to unseen benchmarks: the agent outperforms the base model across all six clinical axes of the AMIE multi-visit benchmark, and shows consistent directional improvements on AgentClinic and CRAFT-MD. Our findings demonstrate that sequential clinical decision-making can be effectively learned through multi-turn RL in simulation, yielding robust, generalizable capabilities, paving the way towards clinical mastery. Prospective validation with real-world workflows remains necessary to establish clinical utility.

Keep browsing

More papers from top AI conferences

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