Poster Session 1

Posters scheduled for this session have it as their primary poster session. Presenters may also join the other session if space permits.

Poster Session 1: 10:45–12:00 PDT. Poster Session 2: 15:00–16:15 PDT.

October 9, 2026 · Workshop room 10: Franciscan A&B / Ballroom level.

Assigned posters (39)

25 have confirmed in-person attendance; 14 have a default session assignment with attendance unconfirmed. Authors with a scheduling conflict may request a change.

• Allocation-Level Contamination Measurement under Strategic Optimization in Retrieval-Augmented Generation
• API Benchmarks Do Not Reliably Predict Chatbot Behavior — Default assignment; attendance unconfirmed.
• Benchmark Items as Measurement Instruments: Differential Item Functioning Across Response-Derived LLM Regimes
• Benchmarking as Information Design: Disclosure-Conditioned Generalized Accuracy for Strategic LLM Evaluation — Default assignment; attendance unconfirmed.
• Benchmarking Psychological Dynamics in Generative Agents
• Bounded Reachability & Jailbreak Detection via Contraction-Constrained State Space Models
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Can Generalist Agents Automate Data Curation?
• CertJudge: Evaluating Lean Formal-Code With Falsifiable Properties — Default assignment; attendance unconfirmed.
• Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows
• Delphi-Psychometric Evaluation of 3D Generative Models: Combining Structured LLM Elicitation with Item Response Theory
• DelusionEval: Measuring Delusion-Linked Behaviors in AI Chatbots
• Dimensionality and Measurement Precision in HLE's Multiple-Choice Subset
• Do LLMs Encode Event Co-Evolution Beyond Textual Similarity? — Default assignment; attendance unconfirmed.
• Do LLMs Quote Arbitrage-Free Option Prices? A Multi-Model Internal-Consistency Probe — Default assignment; attendance unconfirmed.
• Doubly Robust Predictive AI Evaluation
• Evaluation Awareness in Language Models: Mapping Behavior to Mechanism
• From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs
• Kalshi Bench: Outcome-Grounded Calibration as a Contamination-Resistant, Non-Stationary Measurement Primitive — Default assignment; attendance unconfirmed.
• LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs
• Many Agents, Few Witnesses: Effective Sample Size in Multi-Agent Evaluation
• Measurement Under Selection: Decoy-Calibrated Failure Audits for Language Models
• Measuring When Multi-Agent Collaboration Pays: A Matched Four-Protocol Trace Resource for Scientific Reasoning
• Pattern-Driven Evaluation of LLM Code Optimization: Isolating Compiler-Transcendent Semantic Reasoning
• Psychometric Validation of LLM Benchmarks as Measurement Instruments Through Item Response Theory
• Removal Cost as a Measurement Axis for Open-Weight Language Model Safety — Default assignment; attendance unconfirmed.
• Safety Benchmarks as Measurement Instruments: A Crossed Evaluation of LLM Harm Benchmarks — Default assignment; attendance unconfirmed.
• Searching for "Harmful Refusal": A Psychometric Audit of an AI Safety Benchmark
• SOP-BENCH: A Behavioral Benchmark for Whether SoPs Govern Long-Horizon Agent Behavior — Default assignment; attendance unconfirmed.
• The AI Evaluation Ecosystem
• The Future of Facts: Tracing the Factual Generation-Verification Gap — Default assignment; attendance unconfirmed.
• Towards Context-Aware Cloud Anomaly Detection: Benchmark, Agent, and Analysis
• Trace-Use Audits as Measurement: Interventional Evaluation of Post-Training Trace Reliance — Default assignment; attendance unconfirmed.
• What Transfers, and Why: A Behavioral Account of Cross-Benchmark Generalization in Long-Horizon Agents — Default assignment; attendance unconfirmed.
• When a Contamination Audit Says “Clean”: False-Clean Rate as a Robustness Metric for Benchmark Gaming — Default assignment; attendance unconfirmed.
• Where did the ambiguity go? Examining how multimodal models interpret polysemous words
• You Only Judge Once: Multi-response Reward Modeling in a Single Forward Pass
• Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
• Your Benchmark Score Is Not a Measurement: Capability Does Not Determine Cue-Robustness — Default assignment; attendance unconfirmed.