arXiv subjects

Mohsen Arjmandi

Publications and source records attributed to Mohsen Arjmandi.

5 recordsLinked to original sources

arXiv2026

Harness or Model? Isolating the Harness Effect in Agentic Coding with a Contamination-Controlled Private Suite

An agentic coding system couples a language model to a harness: the tools, prompts and control flow that turn a chat model into an autonomous software engineer. Vendors ship harnesses tuned to their own models, and practitioners assume the vendor-native pairing solves more tasks. We measure that assumption with paired same-model contrasts on a private, contamination-controlled suite of 256 repository and post-cutoff contest tasks. The same 80 tasks ran under claude-agent-sdk and under deepagents on claude-opus-4-8, and under the openai-codex SDK and deepagents on gpt-5.5, with gemini-3.5-flash and deepseek-v3.2 as side cells. 792 of 800 planned runs were graded by an isolated oracle. Neither contrast resolves an average advantage for either harness: -1.25 pp for Opus 4.8 (48.8% vs 50.0%, task-bootstrap 95% CI [-10.0, +7.5]) and +1.25 pp for GPT-5.5 (55.6% vs 54.4%, CI [-4.4, +6.9]). The Opus average combines opposite strata: the native harness trails by 9.0 pp on the 61 repository tasks and leads by 23.7 pp on the 19 contest tasks (label-permutation p = 0.003). The partition was chosen after seeing the data and needs a designed replication. Correctness and completion also separate: 22 of 81 runs cancelled at the wall-clock ceiling had produced a passing patch. Re-priced from raw per-turn usage at frozen list prices, the neutral harness cost 1.3 to 1.6 times as much per solved task on Opus 4.8 and 1.2 times on GPT-5.5. These are observed-usage estimates. On the Anthropic account 58 runs left no usage record, and allocating that spend to either cell would move the Opus ratio between 0.7 and 2.3, so the billed ordering is unresolved. This revision corrects an August 2026 manuscript whose cost figures rested on a usage-semantics defect in our own telemetry (Section 5.1). We release the orchestrator, grading oracle, reanalysis code and derived aggregates. The tasks stay private.

cs.AI↗

arXiv2026

Distractor-Aware Truncation: Disentangling Context-Length Effects from Signal Loss in Long-Context LLM Benchmarks

A standard claim in the literature on retrieval-augmented and memory-augmented language models is that shorter context is better when the relevant information is preserved. We test this claim by running every sample of two long-context benchmarks -- BABILong and GraphWalks (BFS) -- at four context-retention fractions (100%, 75%, 50%, 25%) under two truncation protocols. The first is the naive protocol implicitly used in much prior work: drop content from the middle of the prompt. The second is distractor-aware: identify the task-relevant content for each sample and drop only the rest. We evaluate three sizes of the Claude family (Haiku 4.5, Sonnet 4.6, Opus 4.7) and, to test cross-provider generality, GPT-5.5 from a different provider; we apply the same protocol to two further benchmarks (MRCR v2, Oolong). Under naive truncation, score collapses monotonically (paired Wilcoxon, Holm-corrected p_adj < 0.05 in all eight BABILong and GraphWalks cells). Under the distractor-aware protocol -- which preserves the signal by construction -- performance is preserved or improves: the two smaller Claude models show statistically significant gains on BABILong, while the larger models (Opus 4.7 and GPT-5.5) sit at their full-context ceiling. The naive collapse and its distractor-aware recovery replicate on GPT-5.5, ruling out a single-provider artifact. The mechanism is direct: under the naive protocol the answer-bearing content survives in fewer than 1% of samples at 25% retention; under the distractor-aware protocol it is preserved by construction. The naive protocol is therefore not a measurement of context-window effects; it is a measurement of how often middle-removal happens to spare the answer. We conclude that future studies of context-length effects must specify how they distinguish signal from distractor, or they are at best ambiguous between two opposite hypotheses.

cs.AI↗

arXiv2026

The LLM Proposes, the Executive Disposes: A Self-Verifying Agent Instrument that Dissociates Commitment Drift from Binding Drift in Long-Horizon Agents

How do you verify a long-horizon agent when its own state and self-reports are exactly what you cannot trust? We present an agent instrument built so that verification is structural rather than post-hoc. A deterministic Executive owns all belief; a language model may only file typed proposals, and a claim is admitted only when a prediction pre-registered before acting is matched against observation by code. Two properties make the instrument a verifier of its own science, not just of the agent: every run invalidates itself when per-organ write-error, render-size, or salted-canary-echo floors are breached (four of the first eight architecture runs were invalidated, each localizing a real defect); and a render-invisible shadow reference compiles the plan the full system would have committed in every ablation cell, so drift metrics are defined even where the mechanism under test has been removed. Using this instrument we report a clean, single-variable result on a failure every long-horizon agent suffers: ablating the commitment mechanism flips goal-abandonment from 0.00 to 1.00 while binding error stays flat at 0.00 (three seeds per cell, up to 394 reference beats per run, every run gated valid). The binding channel, by contrast, does not reappear as per-beat drift when its repair is ablated -- because binding is code-owned, the failure class is structurally absorbed, its only residue appearing one layer upstream as a collapse in hypothesis formation. We report these under full disclosure that task efficacy is null (zero level completions across 52 gated runs on ARC-AGI-3), pre-registered as a structural defeater. The contribution is a verification methodology for agent development and the drift decomposition it makes measurable.

cs.AI↗

arXiv2026

GRID: Grammar-Railed Decoding for Enterprise SQL Generation

Large language models can write SQL, but enterprise deployment demands more than plausible text: outputs must be syntactically valid, must respect per-role and per-schema policy, must carry provable (not best-effort) guarantees, must not slow down as generations grow, and must leave a compliance-grade record of every decision. We present GRID (Grammar-Railed Decoding), a grammar-constrained decoding engine that keys exact next-token masks on parser configurations (lexer scan state x LALR(1) stack) rather than on token sequences, and uses the incrementally advanced LALR(1) parser itself as a viable-prefix oracle. LLM tokens are bridged to grammar terminals by a byte-level trie walk with a context-independent/context-dependent split that makes cache-key soundness hold by construction. Role-based access control is compiled into the language: role projections subset the grammar's productions and schema lexicons restrict identifier terminals, so forbidden verbs and identifiers are unreachable at mask level. Four guarantees (soundness, completeness, termination, and near-constant per-token cost) are stated with explicit preconditions and each paired with a test or benchmark. Rust kernels bring the per-token mask to a 3.6-6.7 us median, ahead of llguidance at p50 and p90 on two tokenizers with zero false rejects; per-token guard cost is position-flat at n=16,000. On Spider, constrained decoding is worth +13 execution-accuracy points at 0.5B, and one checker-guided repair pass over the provably mask-unenforceable residue (column-level policy) lifts a 7B model to 94.5% executable. A hash-chained per-token audit trail replays bit-identically with 100% tamper detection. We state plainly what the mask cannot do (distribution faithfulness, column-level RBAC, non-LALR(1) languages) and where measured cost remains.

cs.AI↗

arXiv2026

Sensi: Learn One Thing at a Time -- Curriculum-Based Test-Time Learning for LLM Game Agents

Large language model (LLM) agents deployed in unknown environments must learn task structure at test time, but current approaches require thousands of interactions to form useful hypotheses. We present Sensi, an LLM agent architecture for the ARC-AGI-3 game-playing challenge that introduces structured test-time learning through three mechanisms: (1) a two-player architecture separating perception from action, (2) a curriculum-based learning system managed by an external state machine, and (3) a database-as-control-plane that makes the agents context window programmatically steerable. We further introduce an LLM-as-judge component with dynamically generated evaluation rubrics to determine when the agent has learned enough about one topic to advance to the next. We report results across two iterations: Sensi v1 solves 2 game levels using the two-player architecture alone, while Sensi v2 adds curriculum learning and solves 0 levels - but completes its entire learning curriculum in approximately 32 action attempts, achieving 50-94x greater sample efficiency than comparable systems that require 1600-3000 attempts. We precisely diagnose the failure mode as a self-consistent hallucination cascade originating in the perception layer, demonstrating that the architectural bottleneck has shifted from learning efficiency to perceptual grounding - a more tractable problem.

cs.AI↗