Related papers: CIVeX: Causal Intervention Verification for Langua…
When a model produces a correct solution under reinforcement learning with verifiable rewards (RLVR), every token receives the same reward signal regardless of whether it was a decisive reasoning step or a grammatical filler. A natural fix…
Interactive agent benchmarks map an agent run to a binary outcome through outcome checks. When these checks rely on surface level signals or fail to capture the agent's actual action path, they cannot reliably determine whether the run…
Current Chain-of-Thought (CoT) verification methods predict reasoning correctness based on outputs (black-box) or activations (gray-box), but offer limited insight into why a computation fails. We introduce a white-box method: Circuit-based…
Symbolic execution is a program analysis technique executing programs with symbolic instead of concrete inputs. This principle allows for exploring many program paths at once. Despite its wide adoption -- in particular for program testing…
As LLM-based agents increasingly rely on external tools, it is important to evaluate their ability to sustain tool-grounded reasoning beyond familiar workflows and short-range interactions. We introduce AgentEscapeBench, an…
Mining genuine mechanisms underlying the complex data generation process in real-world systems is a fundamental step in promoting interpretability of, and thus trust in, data-driven models. Therefore, we propose a variation-based cause…
LLM-based autonomous research agents report false claims: tasks marked "complete" despite missing artifacts, contradictory metrics, or failed executions. EviBound is an evidence-bound execution framework that eliminates false claims through…
CIMTx provides efficient and unified functions to implement modern methods for causal inferences with multiple treatments using observational data with a focus on binary outcomes. The methods include regression adjustment, inverse…
Large language models are increasingly used in scientific writing, yet they can fabricate citation-shaped references that appear plausible but fail bibliographic verification. Existing detectors often reduce verification to binary…
Large language models (LLMs) are increasingly used as automatic judges for summarization and dialogue evaluation. Prior work has documented biases such as position, verbosity, and style preferences, but largely focuses on outcomes, leaving…
Misalignment between claims and their cited evidence is a common failure mode in reports generated by large language models, limiting their reliability in scientific and other high-stakes settings. We present DeepSciVerify, a two-stage…
Large language models (LLMs) are increasingly used for semantic query processing over large corpora. A set of semantic operators derived from relational algebra has been proposed to provide a unified interface for expressing such queries,…
The remarkable reasoning and code generation capabilities of large language models (LLMs) have spurred significant interest in applying LLMs to enable task automation in digital chip design. In particular, recent work has investigated early…
Agentic AI systems automate enterprise workflows but existing defenses--guardrails, semantic filters--are probabilistic and routinely bypassed. We introduce authenticated workflows, the first complete trust layer for enterprise agentic AI.…
Software is prone to security vulnerabilities. Program analysis tools to detect them have limited effectiveness in practice due to their reliance on human labeled specifications. Large language models (or LLMs) have shown impressive code…
Agentic AI coding systems can inspect repositories, plan implementation steps, edit files, call tools, run tests, and submit pull requests. These capabilities make software and hardware development faster in some settings, but current…
Generative agents based on large language models reproduce believable human behavior in cooperative settings, but how they should reason in situations where rule-breaking may be required, such as fire evacuation or authority-supervised…
Program verification tools are often implemented as front-end translations of an input program into an intermediate verification language (IVL) such as Boogie, GIL, Viper, or Why3. The resulting IVL program is then verified using an…
Symbolic execution has always been plagued by the inability to handle programs that require highly structured inputs. Most often, the symbolic execution engine gets overwhelmed by the sheer number of infeasible paths and fails to explore…
Tool using agents often fail for operational reasons even when language understanding is strong. Common causes include invalid arguments, interface drift, weak recovery, and inefficient retry behavior. We introduce ToolMisuseBench, an…